基于机器视觉的煤质快速分析方法研究
|
摘要
随着科技的发展，选煤自动化程度逐步提高，推动了煤炭洗选效率和经济效益的增长。然而国内选煤厂的自动控制还停留在自动启停车、介质密度桶液位控制、自动加药控制、产品灰分实时监测等零散反馈控制阶段，未能对整个生产环节进行实时监测和调控，主要原因在于目前没有任何技术能够实时监测入料煤和产品煤组成信息，进而不能对整个生产环节进行实时控制。为此，论文提出了基于机器视觉的煤质快速分析方法，力图在线测定煤的粒度组成、密度组成和平均灰分。
论文以太西无烟煤为研究对象，建立了一套煤质快速分析实验系统。提出了三种煤粒图像分割方法即非接触煤粒背光图像分割方法、煤堆图像局部分割方法和煤堆图像整体分割方法。非接触煤粒背光图像分割方法主要针对背光散粒煤图像，采用双峰法、面积阈值和孔洞填充算法精确分割不重叠煤粒；煤堆图像局部分割方法为半自动分割方法，结合人工勾勒目标区域和彩色图像分割方法识别煤堆中的目标煤粒区域，其中还涉及到形态学图像处理、分水岭边缘处理、面积阈值区域筛选和煤粒区域最小外接矩形截取等算法；煤堆图像整体分割方法采用对比度受限自适应直方图均衡法、最小值和最大值滤波算法增强图像，进而引入Hessian矩阵和高斯函数的多尺度线性滤波器进行煤粒边缘检测，其效果比传统边缘检测算法更可靠更精确，最终采用双阈值边缘连接和标记分水岭分割算法识别煤粒区域；前两种图像分割方法主要用于精确建立预测模型，而第三种图像分割方法用于煤质快速分析；同时还提出了一种煤堆图像分割效果量化方法，结果表明煤堆图像整体分割方法误差区域百分比为12.76%。
建立了一个基于机器视觉的煤粒质量预测模型，将煤粒图像二维信息转化为三维信息。通过对比分析煤粒区域实际大小与图像测量大小，表明图像测量方法精度很高；发现了煤粒区域面积与周长、最小外接矩形长和宽之间的指数关系，并分别采用最小二乘法建立了三个指数关系模型；采用多重线性回归方法（MLR）建立并优化了煤粒厚度预测模型，结合煤粒区域面积和密度提出了煤粒质量预测模型，测试结果表明煤样质量预测相对误差在±6%以内。
提出了一种基于机器视觉的煤堆粒度组成快速分析方法。通过对比分析，采用最小外接矩形宽（DB）表征煤粒粒度；通过建立表面煤粒区域所属粒级的概率模型，提出了煤堆表面重叠误差校正方法；采用R-R粒度特性方程探寻煤堆整体粒度分布参数和表面粒度分布参数之间的内在关系，提出了煤堆颗粒偏析误差校正方法；结合上述研究提出了一种煤堆粒度组成预测方法，测试结果表明实验次数越多，预测误差越小，两种误差校正方法能够有效减小粒度组成预测误差，前20次煤堆粒度组成平均预测误差最高为3.79%，最低为0.03%。
提出了一种基于机器视觉的煤堆密度组成快速分析方法。本文提取了煤粒表面50个颜色、光泽和纹理特征参数，并对其进行异常点检测和标准化处理；采用箱线图对所有特征参数进行了初步分析，探索其随煤粒粒级和密度级的变化趋势，初步筛选特征参数；随后采用核主成分分析（KPCA）和遗传算法（GA）进一步优化特征参数，结果表明GA特征筛选方法效果更佳；支持向量机分类器（SVM）相对于BP、RBF和PNN神经网络能够更准确的预测煤粒密度级；窄粒级煤粒密度级预测准确率远高于全粒级煤粒，并且窄粒级中煤粒密度级预测准确率随粒级增大而升高；结合上述研究提出了一种分粒级进行的煤堆密度组成分析方法，测试结果表明实验次数越多，预测误差呈降低趋势，前20次各密度级组成平均预测误差最高为8.03%，最低为0.87%。
提出了一种基于机器视觉的煤堆各密度级灰分和总灰快速分析方法。通过建立煤粒灰分与密度的二次多项式模型，确定煤粒表面特征参数随灰分的变化趋势应与其随密度级的变化趋势一致；采用遗传算法（GA）筛选特征参数，结合支持向量机（SVM）建立煤粒灰分预测模型；结果表明全粒级煤粒灰分预测模型精度不如窄粒级灰分预测模型，并且灰分预测模型精度随粒级增大而升高，SVM预测模型比BP和RBF神经网络模型更适合用于煤粒灰分信息预测；结合上述研究提出了一种分粒级进行的煤堆各密度级灰分与总灰分析方法，测试结果表明预测误差随实验次数增多呈降低趋势，前20次各密度级平均灰分预测误差最高为3.39%，最低为0.22%，总灰平均误差为0.73%。
初步尝试了基于机器视觉的煤质快速分析半工业试验。在神华宁煤太西选煤厂设计开发了一套原煤可选性实时预测系统和一套超纯煤灰分实时预测系统，运行情况表明煤质快速分析方法是可行的，两套设备基本能够满足现场环境实时煤质预测要求；实时预测的入料原煤粒度组成、密度组成和灰分信息绝对误差均在10%以内，并可实时显示可选性曲线；实时预测的超纯煤灰分绝对误差平均值为0.12%；本文研究内容的初步应用表明了煤质快速方法的有效性，后续研究将继续提高系统稳定性和预测精度。
Coal separation efficiency and economic benefit were increased with thescientific and technological development and the increasing automation degree of coalpreparation. However, the automatic controls of domestic coal preparation plants werestill stayed as several feedback control phases, such as automatic launching andstopping machine, liquid level control of medium density barrels, automatic dosingcontrol, real-time ash monitoring. The real-time monitoring and controlling of thewhole production processes has not been realized. The main reason is the afunction ofreal-time monitoring of raw coal and products quality. Hence, this paper proposed themethods of fast analysis of coal property based on machine vision, mainly includingsize distribution analysis, density distribution analysis and ash content analysis.
Tai-xi anthracite was taken as research object, and a fast analysis system of coalproperty were built for experiments. According to the need of fast analysis of coalproperty, three image segmentation methods of coal particles were proposed,including segmentation method of non-touching coal particle image,local-segmentation method of coal pile image and whole-segmentation method of coalpile image. Segmentation method of non-touching coal particle image mainly aimedto backlit images of non-touching coal particles, and two-peaks method, areathreshold, hole-filling method were used to segment coal particles accurately.Local-segmentation method of coal pile image is a semi-automatic segmentationmethod, combined with drawing the outline of the target region by manual and colorimage segmentation method. Related algorithms also include morphologicalprocessing, watershed edge processing, area threshold method and minimumcircumscribed rectangle interception. Whole-segmentation method of coal pile imageused CLAHE, minimum and maximum filter algorithms to enhance image.Multi-scale linear filter by Hessian matrix and Gaussian function was used to detectthe coal particle edges, and the effect is better than traditional edge detectionalgorithms. Finally double-threshold edge connection and marked watershedalgorithm were taken to identify the coal particle region. The first two imagesegmentation methods were mainly used to establish the estimated models accurately,and the third image segmentation method was used for fast analysis of coal property.Meanwhile, a segmentation effect quantitative method of coal pile images wasproposed, and the error percentage of the above segmentation method is12.76%.
In order to estimate the3D information of coal particle from its2D information, a mass estimation model for coal particles was established in this paper. Actual sizeand measured size by image processing were contrasted and analyzed, showing theimage measuring method is accurate. The exponential relationships between area andperimeter, minimum circumscribed rectangle length and breadth were found and threeexponential models were established by least square method. Thickness estimationmodel of coal particles was established and improved by multiple linear regressionmethod, and then mass estimation model of coal particles were proposed with areaand density of coal particles. Test results indicated the absolute errors of estimatedmass of coal samples are less than6%.
A fast analysis method of size distribution of coal piles by machine vision wasproposed. Ten size features were contrasted and analyzed, and then the breadth ofminimum bounding rectangle were determined as the best particle sizecharacterization of coal particles. Through establishing the size-fraction probabilitymodel of surface coal particles, a surface overlapping error correction method wasproposed. R-R granularity characteristic equation was used to explore the innerrelationship between equation parameters of the whole coal pile and the surface, andthen a granular segregation error correction method was proposed. Combined withabove researches, an analysis method of size distribution prediction of coal piles wasproposed, and the results indicated the more test times, the smaller prediction errors.The above two correction methods were useful to reduce the prediction errors. Thehighest error of the first twenty estimated results of coal pile size distribution is3.79%,and the lowest error is0.03%.
A fast analysis method of density distribution of coal piles by machine visionwas proposed. Fifty color, luster and texture features were extracted and processed byoutlier detection and standardized treatment. Box-plots were used to analyze thevariation tendency of all features with the increasing of size fractions and densityfractions, and then selecting all the features initially. KPCA and GA were used tooptimize the left features, and results indicated GA is more suitable for featureselection. SVM is better than BP, RBF and PNN to predict the density fraction of coalparticles. The prediction accuracy of narrow size fractions is much higher than thewhole size fraction, and the bigger size fractions, the higher prediction accuracy.Combined with above researches, an analysis method of density distributionprediction of coal piles by each narrow size fraction model was proposed, and theresults indicated the more test times, the smaller prediction errors. The highest error of the first twenty estimated results of coal pile density distribution is8.03%, and thelowest error is0.87%.
A fast analysis method of total ash content and ash content of each densityfraction of coal piles by machine vision was proposed. Through establishing thequadratic polynomial model of ash content and density of coal particles, the variationtendency of features with the increasing of ash content should be consistent with thatof features with the increasing of density. GA method was used to select the features,and SVM was used to establish the prediction model of ash content. Results indicatedthe prediction accuracy of narrow size fractions is higher than the whole size fraction,and the bigger size fractions, the higher prediction accuracy. SVM model is betterthan BP and RBF models in ash content prediction. Combined with above researches,an analysis method of total ash content and ash content of each density fraction ofcoal piles by each narrow size fraction model was proposed, and the results indicatedthe more test times, the smaller prediction errors. The highest error of the first twentyestimated results of coal pile density distribution is3.39%, the lo west error is0.22%,and the average error of total ash content is0.73%.
Pilot-scale tests of fast analysis of coal property by machine vision were carriedout in a preliminary attempt. An online washability prediction system of raw coal andan online ash content prediction system of ultra-pure coal were designed andestablished in ShenHua Ningmei Taixi coal preparation plant. Test results indicatedthe fast analysis methods of coal property are feasible and the above two systems areable to satisfy the prediction requirements of coal preparation plant basically. Thereal-time prediction absolute errors of size distribution, density distribution and ashcontents are all less than10%and the washability curves is able to show in real time.The real-time prediction absolute error of ultra-pure coal ash contents is0.12%. Theprimary applications show the availability of analysis methods proposed in this paper.System stability and prediction accuracy should be improved and enhanced in futureresearch.
论文以太西无烟煤为研究对象，建立了一套煤质快速分析实验系统。提出了三种煤粒图像分割方法即非接触煤粒背光图像分割方法、煤堆图像局部分割方法和煤堆图像整体分割方法。非接触煤粒背光图像分割方法主要针对背光散粒煤图像，采用双峰法、面积阈值和孔洞填充算法精确分割不重叠煤粒；煤堆图像局部分割方法为半自动分割方法，结合人工勾勒目标区域和彩色图像分割方法识别煤堆中的目标煤粒区域，其中还涉及到形态学图像处理、分水岭边缘处理、面积阈值区域筛选和煤粒区域最小外接矩形截取等算法；煤堆图像整体分割方法采用对比度受限自适应直方图均衡法、最小值和最大值滤波算法增强图像，进而引入Hessian矩阵和高斯函数的多尺度线性滤波器进行煤粒边缘检测，其效果比传统边缘检测算法更可靠更精确，最终采用双阈值边缘连接和标记分水岭分割算法识别煤粒区域；前两种图像分割方法主要用于精确建立预测模型，而第三种图像分割方法用于煤质快速分析；同时还提出了一种煤堆图像分割效果量化方法，结果表明煤堆图像整体分割方法误差区域百分比为12.76%。
建立了一个基于机器视觉的煤粒质量预测模型，将煤粒图像二维信息转化为三维信息。通过对比分析煤粒区域实际大小与图像测量大小，表明图像测量方法精度很高；发现了煤粒区域面积与周长、最小外接矩形长和宽之间的指数关系，并分别采用最小二乘法建立了三个指数关系模型；采用多重线性回归方法（MLR）建立并优化了煤粒厚度预测模型，结合煤粒区域面积和密度提出了煤粒质量预测模型，测试结果表明煤样质量预测相对误差在±6%以内。
提出了一种基于机器视觉的煤堆粒度组成快速分析方法。通过对比分析，采用最小外接矩形宽（DB）表征煤粒粒度；通过建立表面煤粒区域所属粒级的概率模型，提出了煤堆表面重叠误差校正方法；采用R-R粒度特性方程探寻煤堆整体粒度分布参数和表面粒度分布参数之间的内在关系，提出了煤堆颗粒偏析误差校正方法；结合上述研究提出了一种煤堆粒度组成预测方法，测试结果表明实验次数越多，预测误差越小，两种误差校正方法能够有效减小粒度组成预测误差，前20次煤堆粒度组成平均预测误差最高为3.79%，最低为0.03%。
提出了一种基于机器视觉的煤堆密度组成快速分析方法。本文提取了煤粒表面50个颜色、光泽和纹理特征参数，并对其进行异常点检测和标准化处理；采用箱线图对所有特征参数进行了初步分析，探索其随煤粒粒级和密度级的变化趋势，初步筛选特征参数；随后采用核主成分分析（KPCA）和遗传算法（GA）进一步优化特征参数，结果表明GA特征筛选方法效果更佳；支持向量机分类器（SVM）相对于BP、RBF和PNN神经网络能够更准确的预测煤粒密度级；窄粒级煤粒密度级预测准确率远高于全粒级煤粒，并且窄粒级中煤粒密度级预测准确率随粒级增大而升高；结合上述研究提出了一种分粒级进行的煤堆密度组成分析方法，测试结果表明实验次数越多，预测误差呈降低趋势，前20次各密度级组成平均预测误差最高为8.03%，最低为0.87%。
提出了一种基于机器视觉的煤堆各密度级灰分和总灰快速分析方法。通过建立煤粒灰分与密度的二次多项式模型，确定煤粒表面特征参数随灰分的变化趋势应与其随密度级的变化趋势一致；采用遗传算法（GA）筛选特征参数，结合支持向量机（SVM）建立煤粒灰分预测模型；结果表明全粒级煤粒灰分预测模型精度不如窄粒级灰分预测模型，并且灰分预测模型精度随粒级增大而升高，SVM预测模型比BP和RBF神经网络模型更适合用于煤粒灰分信息预测；结合上述研究提出了一种分粒级进行的煤堆各密度级灰分与总灰分析方法，测试结果表明预测误差随实验次数增多呈降低趋势，前20次各密度级平均灰分预测误差最高为3.39%，最低为0.22%，总灰平均误差为0.73%。
初步尝试了基于机器视觉的煤质快速分析半工业试验。在神华宁煤太西选煤厂设计开发了一套原煤可选性实时预测系统和一套超纯煤灰分实时预测系统，运行情况表明煤质快速分析方法是可行的，两套设备基本能够满足现场环境实时煤质预测要求；实时预测的入料原煤粒度组成、密度组成和灰分信息绝对误差均在10%以内，并可实时显示可选性曲线；实时预测的超纯煤灰分绝对误差平均值为0.12%；本文研究内容的初步应用表明了煤质快速方法的有效性，后续研究将继续提高系统稳定性和预测精度。
Coal separation efficiency and economic benefit were increased with thescientific and technological development and the increasing automation degree of coalpreparation. However, the automatic controls of domestic coal preparation plants werestill stayed as several feedback control phases, such as automatic launching andstopping machine, liquid level control of medium density barrels, automatic dosingcontrol, real-time ash monitoring. The real-time monitoring and controlling of thewhole production processes has not been realized. The main reason is the afunction ofreal-time monitoring of raw coal and products quality. Hence, this paper proposed themethods of fast analysis of coal property based on machine vision, mainly includingsize distribution analysis, density distribution analysis and ash content analysis.
Tai-xi anthracite was taken as research object, and a fast analysis system of coalproperty were built for experiments. According to the need of fast analysis of coalproperty, three image segmentation methods of coal particles were proposed,including segmentation method of non-touching coal particle image,local-segmentation method of coal pile image and whole-segmentation method of coalpile image. Segmentation method of non-touching coal particle image mainly aimedto backlit images of non-touching coal particles, and two-peaks method, areathreshold, hole-filling method were used to segment coal particles accurately.Local-segmentation method of coal pile image is a semi-automatic segmentationmethod, combined with drawing the outline of the target region by manual and colorimage segmentation method. Related algorithms also include morphologicalprocessing, watershed edge processing, area threshold method and minimumcircumscribed rectangle interception. Whole-segmentation method of coal pile imageused CLAHE, minimum and maximum filter algorithms to enhance image.Multi-scale linear filter by Hessian matrix and Gaussian function was used to detectthe coal particle edges, and the effect is better than traditional edge detectionalgorithms. Finally double-threshold edge connection and marked watershedalgorithm were taken to identify the coal particle region. The first two imagesegmentation methods were mainly used to establish the estimated models accurately,and the third image segmentation method was used for fast analysis of coal property.Meanwhile, a segmentation effect quantitative method of coal pile images wasproposed, and the error percentage of the above segmentation method is12.76%.
In order to estimate the3D information of coal particle from its2D information, a mass estimation model for coal particles was established in this paper. Actual sizeand measured size by image processing were contrasted and analyzed, showing theimage measuring method is accurate. The exponential relationships between area andperimeter, minimum circumscribed rectangle length and breadth were found and threeexponential models were established by least square method. Thickness estimationmodel of coal particles was established and improved by multiple linear regressionmethod, and then mass estimation model of coal particles were proposed with areaand density of coal particles. Test results indicated the absolute errors of estimatedmass of coal samples are less than6%.
A fast analysis method of size distribution of coal piles by machine vision wasproposed. Ten size features were contrasted and analyzed, and then the breadth ofminimum bounding rectangle were determined as the best particle sizecharacterization of coal particles. Through establishing the size-fraction probabilitymodel of surface coal particles, a surface overlapping error correction method wasproposed. R-R granularity characteristic equation was used to explore the innerrelationship between equation parameters of the whole coal pile and the surface, andthen a granular segregation error correction method was proposed. Combined withabove researches, an analysis method of size distribution prediction of coal piles wasproposed, and the results indicated the more test times, the smaller prediction errors.The above two correction methods were useful to reduce the prediction errors. Thehighest error of the first twenty estimated results of coal pile size distribution is3.79%,and the lowest error is0.03%.
A fast analysis method of density distribution of coal piles by machine visionwas proposed. Fifty color, luster and texture features were extracted and processed byoutlier detection and standardized treatment. Box-plots were used to analyze thevariation tendency of all features with the increasing of size fractions and densityfractions, and then selecting all the features initially. KPCA and GA were used tooptimize the left features, and results indicated GA is more suitable for featureselection. SVM is better than BP, RBF and PNN to predict the density fraction of coalparticles. The prediction accuracy of narrow size fractions is much higher than thewhole size fraction, and the bigger size fractions, the higher prediction accuracy.Combined with above researches, an analysis method of density distributionprediction of coal piles by each narrow size fraction model was proposed, and theresults indicated the more test times, the smaller prediction errors. The highest error of the first twenty estimated results of coal pile density distribution is8.03%, and thelowest error is0.87%.
A fast analysis method of total ash content and ash content of each densityfraction of coal piles by machine vision was proposed. Through establishing thequadratic polynomial model of ash content and density of coal particles, the variationtendency of features with the increasing of ash content should be consistent with thatof features with the increasing of density. GA method was used to select the features,and SVM was used to establish the prediction model of ash content. Results indicatedthe prediction accuracy of narrow size fractions is higher than the whole size fraction,and the bigger size fractions, the higher prediction accuracy. SVM model is betterthan BP and RBF models in ash content prediction. Combined with above researches,an analysis method of total ash content and ash content of each density fraction ofcoal piles by each narrow size fraction model was proposed, and the results indicatedthe more test times, the smaller prediction errors. The highest error of the first twentyestimated results of coal pile density distribution is3.39%, the lo west error is0.22%,and the average error of total ash content is0.73%.
Pilot-scale tests of fast analysis of coal property by machine vision were carriedout in a preliminary attempt. An online washability prediction system of raw coal andan online ash content prediction system of ultra-pure coal were designed andestablished in ShenHua Ningmei Taixi coal preparation plant. Test results indicatedthe fast analysis methods of coal property are feasible and the above two systems areable to satisfy the prediction requirements of coal preparation plant basically. Thereal-time prediction absolute errors of size distribution, density distribution and ashcontents are all less than10%and the washability curves is able to show in real time.The real-time prediction absolute error of ultra-pure coal ash contents is0.12%. Theprimary applications show the availability of analysis methods proposed in this paper.System stability and prediction accuracy should be improved and enhanced in futureresearch.
引文
[1].任世华,罗腾,赵路正.煤炭开发利用碳减排潜力分析[J].中国能源,2013.35(11).
[2].马剑.我国煤炭洗选加工现状及十二五发展构想[J].煤炭加工与综合利用,2011.4:1-4.
[3]. Unay, D., Automatic grading of Bi-colored apples by multispectral machine vision [J].Computers and electronics in agriculture,2011.75(1):204-212.
[4]. Yang, L., Research on air-conditioning fault diagnos is method based on SVM [C]. In NaturalComputation (ICNC),2010Sixth International Conference on.2010: IEEE.
[5]. Zhang, X., A license plate recognition system based on tamura texture in complex conditions[C]. in Information and Automation (ICIA),2010IEEE International Conference on.2010:IEEE.
[6]. Pang, C., A Special Local Clustering Algorithm for Identifying the Genes Associated WithAlzheimer's Disease [C]. NanoBioscience, IEEE Transactions on,2010.9(1):44-50.
[7]. Sun, T., C. Tseng and M. Chen, Electric contacts inspection using machine vision [J]. Imageand Vision Computing,2010.28(6):890-901.
[8]. Mao-cong, X.U., Application of online coal ash determinor in coal preparation plant [J]. CoalQuality Technology,2008.6:17.
[9].展慧等.基于近红外光谱和机器视觉融合技术的板栗缺陷检测[J].农业工程学报,2011.27(2):345-349.
[10].陈艳等.基于GPS和机器视觉的组合导航定位方法[J].农业工程学报,2011.27(3):126-130.
[11]. Chavez, R., N. Cheimanoff and J. Schleifer. Sampling problems during grain sizedistribution measurements [C]. In Proceedings of the Fifth International Symposium on RockFragmentation by Blasting-FRAGBLAST.1996.
[12]. Lin, C.L. and J.D. Miller, The development of a PC, image-based, on-line particle-sizeanalyzer [J]. TRANSACTIONS-SOCIETY OF MINING ENGINEERS OF AIME,1994:29--29.
[13]. Kemeny, J.M., et al., Analys is of rock fragmentation using digital image processing [J].Journal of Geotechnical Engineering,1993.119(7):1144-1160.
[14]. Wu, X., J.M. Kemeny. A segmentation method for multi-connected particle delineation [J].in Applications of Computer Vis ion, Proceedings,1992., IEEE Workshop on.1992: IEEE.
[15]. Petruk, W., Automatic image analysis for mineral beneficiation [J]. JOM Journal of theMinerals, Metals and Materials Society,1988.40(4):29-31.
[16]. Petruk, W., Automatic image analys is to determine mineral behaviour during mineralbeneficiation [C]. Process Mineralogy. VIII. Applications of Mineralogy to MineralBeneficiation Technology, Metallurgy, and Mineral Exploration and Evaluation, WithEmphasis on Precious Metal Ores,1988:347-357.
[17]. King, R.P., Determination of the distribution of size of irregularly shaped particles frommeasurements on sections or projected areas [J]. Powder Technology,1982.32(1):87-100.
[18].阳春华.基于聚类预分割和高低精度距离重构的彩色浮选泡沫图像分割[J].电子与信息学报,2008.30(6):1286-1290.
[19].王勇.煤泥浮选泡沫图像灰度行程及其统计纹理特征[J].煤炭学报,2006.31(1):94-98.
[20]. Liu, J.J., Flotation froth monitoring using multiresolutional multivariate image analysis [J].Minerals Engineering,2005.18(1):65-76.
[21].Bezuidenhout, M., J. Van Deventer and D.W. Moolman, The identification of perturbationsin a base metal flotation plant using computer vision of the froth surface [J]. Mineralsengineering,1997.10(10):1057-1073.
[22].Sadr-Kazemi, N. and J.J. Cilliers, An image processing algorithm for measurement offlotation froth bubble size and shape distributions [J]. Minerals Engineering,1997.10(10):1075-1083.
[23].Hargrave, J.M. and S.T. Hall, Diagnosis of concentrate grade and mass flowrate in tinflotation from colour and surface texture analysis [J]. Minerals Engineering,1997.10(6):613-621.
[24].Moolman, D.W., et al., The interrelationship between surface froth characteristics andindustrial flotation performance [J]. Minerals Engineering,1996.9(8):837-854.
[25].Oestreich, J.M., W.K. Tolley and D.A. Rice, The development of a color sensor system tomeasure mineral compositions [J]. Minerals Engineering,1995.8(1–2):31-39.
[26].Moolman, D.W., C. Aldrich and J. Van Deventer, The monitoring of froth surfaces onindustrial flotation plants using connectionist image processing techniques [J]. Mineralsengineering,1995.8(1):23-30.
[27].Petruk, W., et al. An image analysis and materials balancing procedure for evaluating oresand mill products to obtain optimum recoveries [C]. In Proc.23rd Ann. Meeting CanadianMineral Processors. CIM, Ottawa, Canada.1991.
[28].Petruk, W., Short course on image analysis applied to mineral and earth sciences [J]. Shortcourse handbook,1989.16.
[29].Barbery, G., Mineral liberation: measurement, simulation and practical use in mineralprocessing [J].1991: éditions GB.
[30].Lin, C.L., Y.K. Yen and J.D. Miller. Evaluation of a PC image-based on-line coarse particlesize analyzer [J].1993.
[31].Lin, C.L., Y.K. Yen and J.D. Miller, Plant-site evaluations of the OPSA system for on-lineparticle size measurement from moving belt conveyors [J]. Minerals Engineering,2000.13(8):897-909.
[32].Maerz, N.H., Image sampling techniques and requirements for automated image analys is ofrock fragmentation [J]. Proceedings of the FRAGBLAST,1996.5:115-120.
[33].Maerz, N.H., T.C. Palangio and J.A. Franklin. WipFrag image based granulometry system[C]. in Proceedings of the FRAGBLAST5Workshop on Measurement of BlastFragmentation, Montreal, Quebec, Canada.1996: AA Balkema.
[34].Maerz, N.H. Reconstructing3-D block size distributions from2-D measurements on sections[C]. in Proceedings of the FRAGBLAST5workshop on measurement of blast fragmentation,Montreal, Quebec, Canada.1996: AA Balkema.
[35].Wang, W.X. and O. Stephansson, On-line system for monitoring the size distribution ofaggregates on a conveyor belt [J]. Measurement of Blast fragmentation,1996:167-174.
[36].Girdner, K.K., et al. The split system for analyzing the size distribution of fragmented rock[C]. In Measurement of Blast Fragmentation: Proceedings of the Fragblast.1996.
[37].Palangio, T.C. and J.A. Franklin. Practical guidelines for lighting and photography [C]. InProceedings of the FRAGBLAST5Workshop on Measurement of Blast Fragmentation,Montreal, Quebec, Canada.1996: AA Balkema.
[38].Dahlhielm, S., Industrial applications of image analysis–The IPACS system [J].Measurement of blast fragmentation. Balkema, Rotterdam,1996:59-65.
[39].Downs, D.C. and B.E. Kettunen, On-line fragmentation measurement utilizing the CIASsystem [J]. Measurement of blast fragmentation. Balkema, Rotterdam,1996:79-82.
[40].Havermann, T. and W. Vogt, TUCIPS–A system for the estimation of fragmentation afterproduction blasts [J]. Measurement of blast fragmentation. Balkema, Rotterdam,1996:67-71.
[41].Kleine, T.H. and A.R. Cameron, Blast fragmentation measurement using GoldSize.Measurement of blast fragmentation [J]. Balkema, Rotterdam,1996:83-89.
[42].Schleifer, J. and B. Tessier, FRAGSCAN: A tool to measure fragmentation of blasted rock.Measurement of Blast Fragmentation [J], Franklin and Katsabanis (eds),1996:73-78.
[43].Wang, W.X. and O. Stephansson, On-line system for monitoring the size distribution ofaggregates on a conveyor belt [J]. Measurement of Blast fragmentation,1996:167-174.
[44].Girdner, K.K., et al. The split system for analyzing the size distribution of fragmented rock[C]. In Measurement of Blast Fragmentation: Proceedings of the Fragblast.1996.
[45].Maerz, N.H., Image sampling techniques and requirements for automated image analys is ofrock fragmentation [C]. Proceedings of the FRAGBLAST,1996.5:115-120.
[46].Kemeny, J.M. Practical technique for determining the size distribution of blasted benches,waste dumps and heap leach sites [C]. In International Journal of Rock Mechanics andMining Sciences and Geomechanics Abstracts.1995: Elsevier.
[47].Maerz, N.H. and W. Zhou, Calibration of optical digital fragmentation measuring systems [J].Fragblast,2000.4(2):126-138.
[48].Maerz, N.H. Online fragmentation analysis: Achievements in the mining industry [C]. InProceedings of the7th Annual ICAR Symposium, International Center for AggregatesResearch, University of Texas at Austin, April19-21.1999.
[49].Maerz, N.H. Aggregate sizing and shape determination using digital image processing [C]. InCenter For Aggregates Research (ICAR) Sixth Annual Symposium Proceedings.1998.
[50].Maerz, N.H. and W. Zhou, Optical digital fragmentation measuring systems–inherent sourcesof error [J]. Fragblast,1998.2(4):415-431.
[51].Schleifer, J. and B. Tessier, Fragmentation assessment using the Fragscan system: Quality ofa blast [J]. Fragblast,2002.6(3-4):321-331.
[52].Hundal, H.S., et al., Particle shape characterization using image a nalysis and neural networks[J]. Powder Technology,1997.91(3):217-227.
[53].Fernlund, J.,3-D image analys is size and shape method applied to the evaluation of the LosAngeles test [J]. Engineering geology,2005.77(1):57--67.
[54].Fernlund, J., Image analysis method for determining3-D shape of coarse aggregate [J].Cement and Concrete Research,2005.35(8):1629--1637.
[55].Fernlund, J.M., The effect of particle form on sieve analys is: a test by image analysis [J].Engineering Geology,1998.50(1):111--124.
[56].Petersen, K.R.P., C. Aldrich and J.S.J. Van Deventer, Analys is of ore particles based ontextural pattern recognition [J]. Minerals Engineering,1998.11(10):959-977.
[57].Persson, A., Image analysis of shape and size of fine aggregates [J]. Engineering geology,1998.50(1):177--186.
[58].Mora, C.F. and A. Kwan, Sphericity, shape factor, and convexity measurement of coarseaggregate for concrete using digital image processing [J]. Cement and concrete research,2000.30(3):351--358.
[59].Mora, C.F., A. Kwan and H.C. Chan, Particle size distribution analys is of coarse aggregateusing digital image processing [J]. Cement and Concrete Research,1998.28(6):921--932.
[60].Das, A. A Revisit to Aggregate Shape Parameters [M].2006.
[61].Pons, M.N., et al., Particle morphology: from visualisation to measurement [J]. PowderTechnology,1999.103(1):44-57.
[62].Wang, W.X., Binary image segmentation of aggregates based on polygonal approximationand classification of concavities [J]. Pattern Recognition,1998.31(10):1503-1524.
[63].Wang, W., Image analysis of particles by modified Ferret method—best-fit rectangle [J].Powder technology,2006.165(1):1-10.
[64].Wang, W., Image analysis of aggregates [J]. Computers\&Geosciences,1999.25(1):71--81.
[65].Wang, W., Rock Particle Image Segmentation and Systems [J]. Pattern RecognitiionTechniques, Technology and Applications chap. VIII:197-226.
[66].Wei-xing, W., Particle Size Estimation Based on Edge Density [J]. Journal of ElectronicScience and Technology,2005.3(4).
[67].Taylor, M.A., Quantitative measures for shape and size of particles [J]. Powder Technology,2002.124(1–2):94-100.
[68].Thurley, M.J., Automated online measurement of limestone particle size distributions using3D range data [J]. Journal of Process Control,2011.21(2):254-262.
[69].Thurley, M.J. On-line3D surface measurement of iron ore green pellets [J].2006.
[70].Thurley, M.J. and T. Andersson, An industrial3D vis ion system for size measurement of ironore green pellets using morphological image segmentation [J]. Minerals engineering,2008.21(5):405--415.
[71].Thurley, M.J. and K.C. Ng, Identification and sizing of the entirely visible rocks from a3Dsurface data segmentation of laboratory rock piles [J]. Computer Vision and ImageUnderstanding,2008.111(2):170-178.
[72].Thurley, M.J. and K.C. Ng, Identifying, visualizing, and comparing regions in irregularlyspaced3D surface data [J]. Computer Vision and Image Understanding,2005.98(2):239-270.
[73].Thurley, M.J. and K.C. Ng, Modelling the relationship between the surface fragments and thepile size distribution in laboratory rock piles [J]. URL http://image3d6. eng. monash. edu. au.
[74].Thurley, M.J., Three dimensional data analys is for the separation and sizing of rock piles inmining [D].2002: Monash University.
[75].Vallebuona, G., K. Arburo and A. Casali, A procedure to estimate weight particledistributions from area measurements [J]. Minerals engineering,2003.16(4):323-329.
[76].Banta, L., K. Cheng and J. Zaniewski, Estimation of limestone particle mass from2D images[J]. Powder technology,2003.132(2):184-189.
[77].Guyot, O., et al., VisioRock, an integrated vision technology for advanced control ofcomminution circuits [J]. Minerals engineering,2004.17(11):1227-1235.
[78].Salinas, R.A., U. Raff and C. Farfan, Automated estimation of rock fragment distributionsusing computer vision and its application in mining [C]. IEE Proceedings-Vision, Image andSignal Processing,2005.152(1):1-8.
[79].Murtagh, F., et al., A machine vision approach to the grading of crushed aggregate [J].Machine Vision and Applications,2005.16(4):229--235.
[80].Murtagh, F., et al., Grading of construction aggregate through machine vision: Results andprospects [J]. Computers in industry,2005.56(8):905--917.
[81].Murtagh, F. and J. Starck, Wavelet and curvelet moments for image classification:Application to aggregate mixture grading [J]. Pattern Recognition Letters,2008.29(10):1557-1564.
[82].Erdogan, S.T., et al., Three-dimensional shape analys is of coarse aggregates: New techniquesfor and preliminary results on several different coarse aggregates and reference rocks [J].Cement and Concrete Research,2006.36(9):1619-1627.
[83].Al-Thyabat, S. and N.J. Miles, An improved estimation of size distribution from particleprofile measurements [J]. Powder technology,2006.166(3):152-160.
[84].Al-Thyabat, S., N.J. Miles and T.S. Koh, Estimation of the size distribution of particlesmoving on a conveyor belt [J]. Minerals engineering,2007.20(1):72-83.
[85].Andersson, T., M.J. Thurley and O. Marklund. Pellet size estimation using spherical fitting[J].2007.
[86].Andersson, T. and M.J. Thurley. Visibility classification of rocks in piles [J].2008.
[87].Andersson, T. and M.J. Thurley, Minimizing profile error when estimating the sieve-sizedistribution of iron ore pellets using ordinal logistic regression [J]. Powder Technology,2011.206(3):218--226.
[88].Andersson, T., M.J. Thurley and J.E. Carlson, A machine vision system for estimation of sizedistributions by weight of limestone particles [J]. Minerals Engineering,2012.25(1):38-46.
[89].Koh, T.K., et al., Improving particle size measurement using multi-flash imaging [J].Minerals Engineering,2009.22(6):537-543.
[90].Liao, C., J. Yu and Y. Tarng, On-line full scan inspection of particle size and shape usingdigital image processing [J]. Particuology,2010.8(3):286--292.
[91].Liao, C.W. and Y.S. Tarng, On-line automatic optical inspection system for coarse particlesize distribution [J]. Powder Technology,2009.189(3):508-513.
[92].Aldrich, C., et al., Online Analysis of Coal on A Conveyor Belt by use of Machine Visionand Kernel Methods [J]. International Journal of Coal Preparation and Utilization,2010.30(6):331--348.
[93].Igathinathane, C., et al., Machine vision based particle size and size distributiondetermination of airborne dust particles of wood and bark pellets [J]. Powder Technology,2009.196(2):202-212.
[94].Igathinathane, C., U. Ulusoy and L.O. Pordesimo, Comparison of particle size distribution ofcelestite mineral by machine vision ΣVolume approach and mechanical sieving [J]. PowderTechnology,2012.215–216:137-146.
[95].Ko, Y. and H. Shang, A neural network-based soft sensor for particle size distribution usingimage analysis [J]. Powder Technology,2011.212(2):359-366.
[96].Ko, Y. and H. Shang, Time delay neural network modeling for particle s ize in SAG mills [J].Powder Technology,2011.205(1):250-262.
[97].Jain, A., M.J. Metzger and B.J. Glasser, Effect of particle size distribution on segregation invibrated systems [J]. Powder Technology,2012.
[98].苑玮琦,王建军.基于局部灰度极值法的水泥生料球图像边缘检测[J].模式识别与人工智能,1997.10(4):376-381.
[99].苑玮琦,王建军.计算机图象识别技术在水泥生料球粒度检测中的应用[J].基础自动化,1997.4(2):39-41.
[100].苑玮琦,王建军,张宏勋.生料球粒度在线检测方法研究[J].仪器仪表学报,1998.1(19):29-33.
[101].苑玮琦.球形物料图像的分割方法研究[J].信号处理,1998.14(1):66-70.
[102].苑玮琦,张宏勋.料球粒径的非接触检测方法[J].现代计量测试,1997.5(2):15-19.
[103].蔡健荣,赵杰文,方如明.基于计算机视觉的粒度检测方法研究[J].农业工程学报,2002.18(3):161-164.
[104].黄胜国,杨英杰,蓝青叁.显微图像分析系统及其在矿物粒度分析中的应用研究[J].岩矿测试,2003(04):269-272.
[105].杨英杰,黄胜国,蓝青叁.显微图像识别及其在粒度分析中的应用[J].矿业工程,2003(04):36-38.
[106].敖广武,温春友,张学东.基于小波变换的球团矿图像边缘检测[J].烧结球团,2005.30(5):29-32.
[107].温春友,邵志勇.基于数字图像处理的球团矿粒度检测[J].烧结球团,2004.29(2):38-40.
[108].侯小红.基于图像处理的煤粉颗粒检测技术研究[J],2006,太原理工大学硕士学位论文.
[109].张学礼.计算机数字图像处理技术在在线矿物粒度检测中的应用[J],2006,昆明理工大学.
[110].张学礼,贾瑞强.矿物粒度测定方法的比较及发展前瞻[J].矿业工程,2006.4(4):50-52.
[111].宋玉丹. Image J在矿物初碎检测中的应用[D],2008,太原理工大学.
[112].辛登科,张玉杰,苏治果.图像处理在粉末粒度在线检测系统中的应用[J].计算机工程与设计,2008(13):3510-3512.
[113].王大海.显微图像粒度检测系统研究[J].矿冶,2008(02):114-116.
[114].王大海,贾玉珍,靳冰.一种多粒度集群数据库并发控制新算法[J].河北工程大学学报(自然科学版),2010(04):86-91.
[115].李银华,路新惠,靳贺敏.基于图像处理的金刚石磨粒体积计算研究[J].计算机工程与设计,2009(18):4242-4244.
[116].路新惠,高士忠,张瑜.图像处理技术在金刚石粒度检测中的应用[J].工业控制计算机,2010(08):99-100.
[117].魏炳辉.基于粒度分析的矿物颗粒图像处理及参数分析研究与实现[J],2010,江西理工大学.
[118].刘伟华.基于机器视觉的煤尘在线检测系统关键技术研究[D],2011,山东大学.
[119].梁栋华,张国英,于飞. BOSA-Ⅰ矿石粒度图像分析仪的研究与应用[J].中国计量协会冶金分会2011年会论文集,2011.
[120].张国英.基于图像的原矿碎石粒度检测与分析系统[J].冶金自动化,2012.36(3):63-67.
[121].刘伊夫.基于DM6446的球团粒度检测系统研究[D],2011,辽宁科技大学.
[122].曾珽.矿石粘连颗粒检测与分割算法研究[J],2012,江西理工大学.55.
[123].李珍香,罗宏宇.一种基于PC机的煤泥浮选自动识别系统[J].电脑开发与应用,2000(02):30-31.
[124].李珍香,罗宏宇.浮选泡沫的计算机图像处理与识别方法[J].煤炭技术,1999(06):17-19.
[125].Aldrich, C., et al., Online monitoring and control of froth flotation systems with machinevision: A review [J]. International Journal of Mineral Processing,2010.96(1–4):1-13.
[126].Cipriano, A., et al., A real time visual sensor for supervision of flotation cells [J]. MineralsEngineering,1998.11(6):489-499.
[127].Cipriano, A., et al. Expert supervision of flotation cells using digital image processing [C].in Proceedings of the20th International Mineral Processing Congress.1997.
[128].Symonds, P.J. and G. De Jager. A technique for automatically segmenting images of thesurface froth structures that are prevalent in industrial flotation cells [C]. In Communicationsand Signal Processing,1992. COMSIG'92., Proceedings of the1992South AfricanSymposium on.1992: IEEE.
[129].Moolman, D.W., Digital image processing as a tool for on-line monitoring of froth inflotation plants [J]. Minerals Engineering,1994.7(9):1149-1164.
[130].Wang, W., F. Bergholm and B. Yang, Froth delineation based on image classification [J].Minerals engineering,2003.16(11):1183-1192.
[131].Wang, W. and O. Stephansson. A robust bubble delineation algorithm for froth images [C].In Intelligent Processing and Manufacturing of Materials,1999. IPMM'99. Proceedings of theSecond International Conference on.1999: IEEE.
[132].Hargrave, J.M., N.J. Miles and S.T. Hall, The use of grey level measurement in predictingcoal flotation performance [J]. Minerals engineering,1996.9(6):667-674.
[133].曾荣.浮选泡沫图象边缘检测方法的研究[J].中国矿业大学学报,2002(05):84-88.
[134].曾荣.沃国经.图像处理技术在镍选矿厂中的应用[J].矿冶,2002(01):37-41.
[135].曾荣.沃国经.图像处理技术在浮选过程中的应用[J].有色金属,2001(04):70-72.
[136].王凡,路迈西.煤泥浮选泡沫层中气泡特征的提取[J].中国矿业大学学报,2001(06):24-27.
[137].王凡,路迈西.煤泥浮选泡沫的图像处理[J].煤炭科学技术,2001(11):28-30.
[138].王勇,路迈西.表征煤泥浮选泡沫图象特征的最佳色彩方案[J].中国矿业大学学报,2002(06):71-73.
[139].王勇,路迈西.煤泥浮选泡沫图像灰度行程及其统计纹理特征[J].煤炭学报,2006(01):94-98.
[140].王勇,路迈西.煤泥浮选泡沫图像灰度直方图及其统计纹理特征研究[J].选煤技术,2006(01):13-16.
[141].刘文礼,陈子彤,路迈西.煤泥浮选泡沫的数字图像处理[J].燃料化学学报,2002(03):198-203.
[142].刘文礼,路迈西.数字图像处理技术在煤泥浮选泡沫图像纹理特征的提取及识别上的应用[J].选煤技术,2004(04):78-81
[143].刘文礼,路迈西.煤泥浮选泡沫图像纹理特征的提取及泡沫状态的识别[J].化工学报,2003(06):830-835.
[144].刘文礼,路迈西.煤泥浮选泡沫数字图象处理研究(之一)——浮选泡沫视觉特征的线邻域提取算法[J].中国矿业大学学报,2002(02):13-16.
[145].刘文礼,路迈西.煤泥浮选泡沫数字图象处理研究(之二)——煤泥浮选泡沫视觉特征的面邻域提取算法[J].中国矿业大学学报,2002(03):20-23.
[146].刘文礼,路迈西.浮选泡沫特征及其状态识别[J].中国煤炭,2003(05):51-53.
[147].黄玉华,路迈西.基于灰色系统理论的煤泥浮选泡沫数字图像处理算法研究[J].选煤技术,2006(04):6-8.
[148].Kaartinen, J., Machine-vision-based control of zinc flotation—a case study [J]. ControlEngineering Practice,2006.14(12):1455-1466.
[149].谷莹莹.基于分水岭变换的浮选泡沫图像分割[J].北京石油化工学院学报,2007(01):61-66.
[150].林小竹,谷莹莹,赵国庆.煤泥浮选气泡比表面积的计算方法[J].煤炭学报,2007(08):874-878.
[151].林小竹,谷莹莹,赵国庆.煤泥浮选泡沫图像分割与特征提取[J].煤炭学报,2007(03):304-308.
[152].桂卫华,阳春华.一种基于DSP的嵌入式浮选泡沫图像监控装置[J],2013.9.
[153].桂卫华,阳春华.一种基于图像特征分析的浮选回收率预测方法[J],2008.8.
[154].桂卫华,阳春华.一种浮选泡沫图像视觉监控装置[J],2009.8.
[155].桂卫华,阳春华.一种基于纹理单元分布的硫浮选过程故障检测方法[J],2012.13.
[156].阳春华.一种基于机器视觉的浮选泡沫图像识别设备及精矿品位预测方法[J],2007.11.
[157].阳春华.用于浮选泡沫图像分析的关键特征提取方法[J],2008.10.
[158].阳春华.一种基于泡沫图像特征和通风量的硫浮选液位测量方法[J],2012.12.
[159].何桂春.浮选泡沫图像处理技术研究现状与进展[J].有色金属科学与工程,2011(02):57-63.
[160].何桂春,黄开启.浮选指标与浮选泡沫数字图像关系研究[J].金属矿山,2008(08):96-101.
[161].杨洪薇,肖志涛,翁秀梅.基于分水岭和模糊C均值聚类的图像分割方法[J].天津工业大学学报,2008(01):53-55.
[162].牟春洁,张国英.基于区域边界生长的图像分割方法[J].北京石油化工学院学报,2009(04):8-12.
[163].牟春洁,张国英.基于射线的泡沫图象分割算法[J].北京石油化工学院学报,2010(01):36-40.
[164].唐朝晖,杜金芳,陈青.一种基于混合神经网络的浮选pH值预测模型[J].控制工程,2012(03):416-419.
[165].唐朝晖.基于特征的构件化软件设计关键技术研究[C], in第三十二届中国控制会议2013:中国陕西西安.5.
[166].唐朝晖.泡沫浮选过程视觉监控系统软件构件化设计与开发[C],第25届中国控制与决策会议2013:中国贵州贵阳.5.
[167].唐朝晖.基于数字图像处理的浮选泡沫速度特征提取及分析[J].中南大学学报(自然科学版),2009(06):1616-1622.
[168].唐朝晖.基于小波变换的浮选泡沫图像纹理特征提取[J].计算机工程,2011(18):206-208.
[169].唐朝晖,朱楚梅,刘金平.基于LBPV的浮选泡沫图像纹理特征提取[J].计算机应用研究,2011(10):3934-3936.
[170].王建昆.浮选过程泡沫图像特征识别研究[J].云南冶金,2009(01):65-67.
[171].周开军.矿物浮选泡沫图像形态特征提取方法与应用[J],2010,中南大学.151.
[172].周开军.基于泡沫特征与LS-SVM的浮选回收率预测[J].仪器仪表学报,2009(06):1295-1300.
[173].周开军.基于图像特征提取的浮选关键参数智能预测算法[J].控制与决策,2009(09):1300-1305.
[174].刘金平.基于Gabor小波的浮选泡沫图像纹理特征提取[J].仪器仪表学报,2010(08):1769-1775.
[175].沃国经. FP-01浮选泡沫图像处理系统[C],首届全国有色金属自动化技术与应用学术年会2003:中国南昌.3.
[176].沃国经. FP-01浮选泡沫图像处理系统[J].有色冶金设计与研究,2003(S1):87-89.
[177].Jones, M.P., Applied mineralogy: a quantitative approach [J].1987: Springer.
[178].Petruk, W., Automatic image analysis for mineral beneficiation. JOM Journal of theMinerals [J], Metals and Materials Society,1988.40(4):29-31.
[179].Technology, C.C.F.M., M.P.L. Canada and W. Petruk, The MP-SEM-IPS image analysissystem [J].1986: Canada Centre for Mineral and Energy Technology.
[180].Bonifazi, G., Digital multispectral techniques and automated image analysis procedures forindustrial ore modeling [J]. Minerals Engineering,1995.8(7):779-794.
[181]. Laine, S., H. Lappalainen and S. J ms-Jounela, On-line determination of ore type usingcluster analysis and neural networks [J]. Minerals engineering,1995.8(6):637-648.
[182].Peng, Z. and T.B. Kirk, Computer image analysis of wear particles in three-dimensions formachine condition monitoring [J]. Wear,1998.223(1):157-166.
[183].Perez, C., et al. Lithological composition sensor based on digital image feature extraction,genetic selection of features and neural classification [C]. In Information Intelligence andSystems,1999. Proceedings.1999International Conference on.1999.
[184].Perez, C.A., et al., Ore grade estimation by feature selection and voting us ing boundarydetection in digital image analysis [J]. International Journal of Mineral Processing,2011.101(1–4):28-36.
[185].刘富强.基于图像处理与识别技术的煤矿矸石自动分选[J].煤炭学报,2000(05):534-537.
[186].马宪民.煤矸石在线识别与自动分选系统的研究[J].西安科技学院学报,2003(01):66-68.
[187].马宪民.一种基于小波变换的煤矸石图像边缘检测方法[J].仪器仪表学报,2006(S3):2130-2131.
[188].马宪民,蒋勇.煤与矸石识别的数字图像处理方法探讨[C],中国煤炭学会煤矿机电一体化专业委员会、中国电工技术学会煤矿电工专业委员会2004年学术年会2004:中国浙江杭州.3.
[189].马宪民,蒋勇.煤矸石二值图像的Roberts快速边缘检测法[C],第三届全国信息获取与处理学术会议2005:中国浙江.3.
[190].马宪民,蒋勇.煤与矸石识别的数字图像处理方法探讨[J].煤矿机电,2004(05):9-11.
[191].马宪民,蒋勇,卜祥莉.基于图像处理的煤矸石自动分选系统的研究[C],2003年中国智能自动化会议2003:中国香港.4.
[192].马宪民,蒋勇,王雪娟.一种煤矸石图像边缘提取的小波分析法[C],第十四届全国煤矿自动化学术年会、中国煤炭学会自动化专业委员会学术会议2004:山东青岛.3.
[193].马宪民,田红,龚尚福.煤矸石在线识别与自动分选系统的研究[C],2001年中国智能自动化会议2001:中国云南昆明.4.
[194].Casali, A., et al., Grindability soft-sensors based on lithological composition and on-linemeasurements [J]. Minerals Engineering,2001.14(7):689-700.
[195].Ke, J., Neural-Network Modelling Of Placer Ore Grade Spatial Variability [J].2002,University of Alaska Fairbanks.
[196].Lepist, L., et al., Rock image classification using non-homogenous textures and spectralimaging[J]. WSCG proc., WSCG,2003.
[197].Lepist, L., I. Kunttu and A. Visa, Rock image classification using color features in Gaborspace [J]. Journal of Electronic Imaging,2005.14(4):040503-040503-3.
[198].Paclík, P., S. Verzakov and R.P. Duin, Improving the maximum-likelihood co-occurrenceclassifier: a study on classification of inhomogeneous rock images [C], In Image Analysis.2005, Springer.998-1008.
[199].Raadnui, S., Wear particle analys is—utilization of quantitative computer image analysis: areview [J]. Tribology International,2005.38(10):871-878.
[200].Singh, N., et al., Textural identification of basaltic rock mass using image processing andneural network [J]. Computational Geosciences,2010.14(2):301-310.
[201].Singh, V. and S.M. Rao, Application of image processing in mineral industry: a case studyof ferruginous manganese ores [J]. Mineral Processing and Extractive Metallurgy,2006.115(3):155-160.
[202].Singh, V. and S.M. Rao, Application of image processing and radial basis neural networktechniques for ore sorting and ore classification [J]. Minerals Engineering,2005.18(15):1412-1420.
[203].Sun, J., et al., Classification of Infrared Monitor Images of Coal Us ing an Feature TextureStatistics and Improved BP Network [J]. Journal of China University of Mining andTechnology,2007.17(4):489-493.
[204].Ma, X. A revised edge detection algorithm based on wavelet transform for coal gangueimage [J]. In Machine Learning and Cybernetics,2007International Conference on.2007:IEEE.
[205].Donskoi, E., Modelling and optimization of hydrocyclone for iron ore fines beneficiation—using optical image analysis and iron ore texture classification [J]. International Journal ofMineral Processing,2008.87(3–4):106-119.
[206].Dal Grande, F., A. Santomaso and P. Canu, Improving local composition measurements ofbinary mixtures by image analys is [J]. Powder Technology,2008.187(3):205-213.
[207].Kachanubal, T. and S. Udomhunsakul, Rock textures classification based on textural andspectral features [J]. Proc. of World Academy of Science, Eng. and Tech,2008.29:110-116.
[208].Gon alves, L.B., F.R. Leta and S.C. de Valente. Macroscopic rock texture imageclassification using an hierarchical neuro-fuzzy system [C]. in Systems, Signals and ImageProcessing,2009. IWSSIP2009.16th International Conference on.2009: IEEE.
[209].Chatterjee, S., S. Bandopadhyay and D. Machuca, Ore grade prediction using a geneticalgorithm and clustering based ensemble neural network model [J]. MathematicalGeosciences,2010.42(3):309-326.
[210].Chatterjee, S., et al., Image-based quality monitoring system of limestone ore grades [J].Computers in Industry,2010.61(5):391-408.
[211].叶润青,牛瑞卿,张良培.基于多尺度分割的岩石图像矿物特征提取及分析[J].吉林大学学报(地球科学版),2011(04):1253-1261.
[212].叶润青.基于图像分类的矿物含量测定及精度评价[J].中国矿业大学学报,2011(05):810-815.
[213].何敏,王培培,蒋慧慧.基于SVM和纹理的煤和煤矸石自动识别[J].计算机工程与设计,2012(03):1117-1121.
[214].Banta, L., K. Cheng and J. Zaniewski, Estimation of limestone particle mass from2Dimages[J]. Powder Technology,2003.132(2–3):184-189.
[215].程鹏飞.植物病害的图像处理及特征值提取方法的研究[J],2005,山西农业大学.48.
[216].何春.基于特征的交通标志图像识别的应用研究[J],2013,广东工业大学.71.
[217].张振升,朱名日,潘泽锴.基于图像处理的蔗糖结晶颗粒识别方法[J].计算机系统应用,2010(03):95-99.
[218].刘兆艳.基于机器视觉的稻种品种识别研究[J],2006,浙江大学.62.
[219].唐强.基于图像模式识别技术的昆虫识别研究[J],2006,昆明理工大学.61.
[220].胡永刚.基于数学形态学的遥感图像边缘检测算法[J],2006,燕山大学.74.
[221].姚进.基于数学形态学的图像边缘检测研究[J],2005,山东师范大学.65.
[222].Vincent, L. and P. Soille, Watersheds in digital spaces: an efficient algorithm based onimmersion simulations [C]. IEEE transactions on pattern analysis and machine intelligence,1991.13(6):583-598.
[223].陈家新,王纪刚.一种改进的医学图像分水岭分割算法[J].计算机应用研究,2013.
[224].陈婷婷.采用模糊形态学和分水岭算法的图像分割研究[J],2008,西南大学.62.
[225].卢蓉.一种提取目标图像最小外接矩形的快速算法[J].计算机工程,2010(21):178-180.
[226].袁佐云,牛兴和,刘传云.基于最小外接矩形的稻米粒型检测方法[J].粮食与饲料工业,2006(09):7-8.
[227].邓玥.天空区域图像的增强算法的改进[J].激光与红外,2012(09):1080-1085.
[228].刘燕君,刘奇.基于同态滤波与直方图均衡化的超声图像增强[J].中国组织工程研究与临床康复,2011(48):9031-9034.
[229].Pizer, S.M., et al., Adaptive histogram equalization and its variations[J]. Computer vision,graphics, and image processing,1987.39(3):355-368.
[230].Pizer, S.M., et al. Contrast-limited adaptive histogram equalization: speed and effectiveness[J]. In Visualization in Biomedical Computing,1990., Proceedings of the First Conference on.1990: IEEE.
[231].江涛,王永仲.基于改进递归最大值滤波的红外点目标检测[J].红外技术,2004.26(3):41-44.
[232].邢藏菊.一种用于抑制椒盐噪声的多窗口中值滤波器[J].2002.
[233].康牧,许庆功,王宝树.一种Roberts自适应边缘检测方法[J].西安交通大学学报,2008(10):1240-1244.
[234].王冰.用Roberts算子进行边缘处理[J].甘肃科技,2008(10):18-20.
[235].樊娜,李晋惠.图像边缘检测的Prewitt算子的改进算法[J].西安工业学院学报,2005(01):37-39.
[236].侯艳,路迈西,张少波.用不同图像边缘检测算法识别粉煤灰等颗粒物[J].洁净煤技术,2008(06):77-79.
[237].刘煜,李言俊,张科.一种多像素图像边缘提取方法[J].光子学报,2007(02):380-384.
[238].江雯.基于Sobel算子的自适应图像缩放算法[J].计算机工程,2010(07):214-216.
[239].沈德海,侯建,鄂旭.基于改进的Sobel算子边缘检测算法[J].计算机技术与发展,2013(11).
[240].袁春兰.基于Sobel算子的图像边缘检测研究[J].激光与红外,2009(01):第85-87页.
[241].何新英.基于数学形态学和Canny算子的边缘提取方法[J].计算机应用,2008(02):477-478.
[242].周晓明.一种改进的Canny算子边缘检测算法[J].测绘工程,2008(01):第28-31页.
[243].郭薇.基于Hessian矩阵及梯度熵的疑似肺结节检测算法[J].仪器仪表学报,2009(08):1702-1706.
[244].李颖超,刘越,王涌天.基于多尺度Hessian矩阵和Gabor滤波的造影图像冠脉中心线提取[J].中国医学影像技术,2007(01):133-136.
[245].许燕.基于Hessian矩阵的冠状动脉中心线的跟踪算法[J].清华大学学报(自然科学版),2007(06):889-892.
[246].Kwan, A., C.F. Mora and H.C. Chan, Particle shape analysis of coarse aggregate usingdigital image processing [J]. Cement and Concrete Research,1999.29(9):1403--1410.
[247].Vallebuona, G., K. Arburo and A. Casali, A procedure to estimate weight particledistributions from area measurements [J]. Minerals Engineering,2003.16(4):323-329.
[248].刘晨敏,樊向林.原生煤粉粒度特性的研究[J].中州煤炭,2009(05):22-24.
[249].邬小骐,邵全渝,张国祥.原矿及破碎产品标准粒度特性方程的研究[J].有色冶金设计与研究,1997(04):7-11.
[250].闫培培,张兴芳,樊民强.一种包含偏斜系数的粒度特性方程[J].中国粉体技术,2013(03):58-61.
[251].高士忠.基于灰度共生矩阵的织物纹理分析[J].计算机工程与设计,2008(16):4385-4388.
[252].施建宇,张艳宁.使用图像特征构建快速有效的蛋白质折叠识别方法[J].生物物理学报,2009(02):106-116.
[253].王克奇.基于空间灰度共生矩阵的木材纹理特征提取[J].森林工程,2006(01):24-26.
[254].Haralick, R.M., Statistical and structural approaches to texture [J]. Proceedings of the IEEE,1979.67(5):786-804.
[255].Haralick, R.M., K. Shanmugam and I.H. Dinstein, Textural features for image classification.Systems [J], Man and Cybernetics, IEEE Transactions on,1973(6):610-621.
[256].Tamura, H., S. Mori and T. Yamawaki, Textural features corresponding to visual perception.Systems, Man and Cybernetics [C], IEEE Transactions on,1978.8(6):460-473.
[257].郝玉保.改进Tamura纹理特征的图像检索方法[J].测绘科学,2010(04):136-138.
[258].吕晓琪.基于图像分割的Tamura纹理特征算法的研究与实现[J].中国组织工程研究,2012(17):3160-3163.
[259].王顺杰,齐春,程玉胜. Tamura纹理特征在水下目标分类中的应用[J].应用声学,2012(02):135-139.
[260].梁晓霞,封筠.基于Gabor变换和灰度梯度共生矩阵的人耳识别研究[J].石家庄铁道大学学报(自然科学版),2011(01):78-83.
[261].刘凯,黄峰,罗坚.基于纹理特征的卫星云图台风自动识别方法[J].微型机与应用,2001(09):48-49.
[262].万鹏,龙长江.基于灰度-梯度共生矩阵的大米加工精度的机器视觉检测方法[J].粮食储藏,2010(04):48-51.
[263].夏德深,金盛,王健.基于分数维与灰度梯度共生矩阵的气象云图识别(Ⅱ)——灰度梯度共生矩阵对纹理统计特征的描述[J].南京理工大学学报,1999(04):289-292.
[264].方浩,贾睿,卢嘉鹏.基于颜色和纹理特征的道路图像分割[J].北京理工大学学报,2010(08):935-939.
[265].刘建立,左保齐,高卫东.非织造材料外观质量识别的小波纹理分析方法[J].计算机工程与设计,2011(08):2836-2840.
[266].罗涟玲.遥感图像森林类型小波纹理的SVM法分类[J].计算机工程与应用,2012(16):194-197.
[267].谢锋,林怡,陈映鹰.基于小波纹理与改进FCM的SAR机场类目标提取[J].同济大学学报(自然科学版),2009(01):115-120.
[268].丛瑜,肖怀铁,付强.基于核主分量分析的高分辨雷达目标特征提取与识别[J].电光与控制,2008(02):31-35.
[269].冯永玖.基于核主成分元胞模型的城市演化重建与预测[J].地理学报,2010(06):665-675.
[270].邵年华. KPCA_SVM水文时间序列预测模型的建立与应用[J].西北农林科技大学学报(自然科学版),2009(09):204-208.
[271].吴洪艳,黄道平.基于特征向量提取的核主元分析法[J].计算机科学,2009(07):185-187.
[272].Goldberg, D.E. and J.H. Holland, Genetic algorithms and machine learning [J]. Machinelearning,1988.3(2): p.95-99.
[273].Boser, B.E., I.M. Guyon and V.N. Vapnik. A training algorithm for optimal marginclassifiers [C]. In Proceedings of the fifth annual workshop on Computational learning theory.1992: ACM.
[274].叶航军,白雪生,徐光祐.基于支持向量机的人脸姿态判定[J].清华大学学报(自然科学版),2003(01):67-70.
[275].高学.一种基于支持向量机的手写汉字识别方法[J].电子学报,2002(05):651-654.
[276].王欢良,韩纪庆,张磊.基于支持向量机的变异语音分类研究[J].哈尔滨工业大学学报,2003(04):389-393.
[277].马金娜,田大钢.基于支持向量机的中文文本自动分类研究[J].系统工程与电子技术,2007(03):475-478.
[278].马金娜,田大钢.基于SVM的中文文本自动分类研究[J].计算机与现代化,2006(08):5-8.
[279].Chang, C. and C. Lin, LIBSVM: a library for support vector machines [J], Software (2001).
[280].高媛媛,刘强国.基于LIBSVM的葡萄酒品质评判模型[J].四川理工学院学报(自然科学版),2010(05):530-532.
[281].任立辉.基于LIBSVM的石油录井中岩屑岩性识别方法研究[J].中国海洋大学学报(自然科学版),2010(09):131-136.
[282].曾鸣,林磊,程文明.基于LIBSVM和时间序列的区域货运量预测研究[J].计算机工程与应用,2013(21):6-10.
[283].张泽琳，杨建国.煤灰分在线检测方法及设备[J].选煤技术,2012(2):59-63.
[2].马剑.我国煤炭洗选加工现状及十二五发展构想[J].煤炭加工与综合利用,2011.4:1-4.
[3]. Unay, D., Automatic grading of Bi-colored apples by multispectral machine vision [J].Computers and electronics in agriculture,2011.75(1):204-212.
[4]. Yang, L., Research on air-conditioning fault diagnos is method based on SVM [C]. In NaturalComputation (ICNC),2010Sixth International Conference on.2010: IEEE.
[5]. Zhang, X., A license plate recognition system based on tamura texture in complex conditions[C]. in Information and Automation (ICIA),2010IEEE International Conference on.2010:IEEE.
[6]. Pang, C., A Special Local Clustering Algorithm for Identifying the Genes Associated WithAlzheimer's Disease [C]. NanoBioscience, IEEE Transactions on,2010.9(1):44-50.
[7]. Sun, T., C. Tseng and M. Chen, Electric contacts inspection using machine vision [J]. Imageand Vision Computing,2010.28(6):890-901.
[8]. Mao-cong, X.U., Application of online coal ash determinor in coal preparation plant [J]. CoalQuality Technology,2008.6:17.
[9].展慧等.基于近红外光谱和机器视觉融合技术的板栗缺陷检测[J].农业工程学报,2011.27(2):345-349.
[10].陈艳等.基于GPS和机器视觉的组合导航定位方法[J].农业工程学报,2011.27(3):126-130.
[11]. Chavez, R., N. Cheimanoff and J. Schleifer. Sampling problems during grain sizedistribution measurements [C]. In Proceedings of the Fifth International Symposium on RockFragmentation by Blasting-FRAGBLAST.1996.
[12]. Lin, C.L. and J.D. Miller, The development of a PC, image-based, on-line particle-sizeanalyzer [J]. TRANSACTIONS-SOCIETY OF MINING ENGINEERS OF AIME,1994:29--29.
[13]. Kemeny, J.M., et al., Analys is of rock fragmentation using digital image processing [J].Journal of Geotechnical Engineering,1993.119(7):1144-1160.
[14]. Wu, X., J.M. Kemeny. A segmentation method for multi-connected particle delineation [J].in Applications of Computer Vis ion, Proceedings,1992., IEEE Workshop on.1992: IEEE.
[15]. Petruk, W., Automatic image analysis for mineral beneficiation [J]. JOM Journal of theMinerals, Metals and Materials Society,1988.40(4):29-31.
[16]. Petruk, W., Automatic image analys is to determine mineral behaviour during mineralbeneficiation [C]. Process Mineralogy. VIII. Applications of Mineralogy to MineralBeneficiation Technology, Metallurgy, and Mineral Exploration and Evaluation, WithEmphasis on Precious Metal Ores,1988:347-357.
[17]. King, R.P., Determination of the distribution of size of irregularly shaped particles frommeasurements on sections or projected areas [J]. Powder Technology,1982.32(1):87-100.
[18].阳春华.基于聚类预分割和高低精度距离重构的彩色浮选泡沫图像分割[J].电子与信息学报,2008.30(6):1286-1290.
[19].王勇.煤泥浮选泡沫图像灰度行程及其统计纹理特征[J].煤炭学报,2006.31(1):94-98.
[20]. Liu, J.J., Flotation froth monitoring using multiresolutional multivariate image analysis [J].Minerals Engineering,2005.18(1):65-76.
[21].Bezuidenhout, M., J. Van Deventer and D.W. Moolman, The identification of perturbationsin a base metal flotation plant using computer vision of the froth surface [J]. Mineralsengineering,1997.10(10):1057-1073.
[22].Sadr-Kazemi, N. and J.J. Cilliers, An image processing algorithm for measurement offlotation froth bubble size and shape distributions [J]. Minerals Engineering,1997.10(10):1075-1083.
[23].Hargrave, J.M. and S.T. Hall, Diagnosis of concentrate grade and mass flowrate in tinflotation from colour and surface texture analysis [J]. Minerals Engineering,1997.10(6):613-621.
[24].Moolman, D.W., et al., The interrelationship between surface froth characteristics andindustrial flotation performance [J]. Minerals Engineering,1996.9(8):837-854.
[25].Oestreich, J.M., W.K. Tolley and D.A. Rice, The development of a color sensor system tomeasure mineral compositions [J]. Minerals Engineering,1995.8(1–2):31-39.
[26].Moolman, D.W., C. Aldrich and J. Van Deventer, The monitoring of froth surfaces onindustrial flotation plants using connectionist image processing techniques [J]. Mineralsengineering,1995.8(1):23-30.
[27].Petruk, W., et al. An image analysis and materials balancing procedure for evaluating oresand mill products to obtain optimum recoveries [C]. In Proc.23rd Ann. Meeting CanadianMineral Processors. CIM, Ottawa, Canada.1991.
[28].Petruk, W., Short course on image analysis applied to mineral and earth sciences [J]. Shortcourse handbook,1989.16.
[29].Barbery, G., Mineral liberation: measurement, simulation and practical use in mineralprocessing [J].1991: éditions GB.
[30].Lin, C.L., Y.K. Yen and J.D. Miller. Evaluation of a PC image-based on-line coarse particlesize analyzer [J].1993.
[31].Lin, C.L., Y.K. Yen and J.D. Miller, Plant-site evaluations of the OPSA system for on-lineparticle size measurement from moving belt conveyors [J]. Minerals Engineering,2000.13(8):897-909.
[32].Maerz, N.H., Image sampling techniques and requirements for automated image analys is ofrock fragmentation [J]. Proceedings of the FRAGBLAST,1996.5:115-120.
[33].Maerz, N.H., T.C. Palangio and J.A. Franklin. WipFrag image based granulometry system[C]. in Proceedings of the FRAGBLAST5Workshop on Measurement of BlastFragmentation, Montreal, Quebec, Canada.1996: AA Balkema.
[34].Maerz, N.H. Reconstructing3-D block size distributions from2-D measurements on sections[C]. in Proceedings of the FRAGBLAST5workshop on measurement of blast fragmentation,Montreal, Quebec, Canada.1996: AA Balkema.
[35].Wang, W.X. and O. Stephansson, On-line system for monitoring the size distribution ofaggregates on a conveyor belt [J]. Measurement of Blast fragmentation,1996:167-174.
[36].Girdner, K.K., et al. The split system for analyzing the size distribution of fragmented rock[C]. In Measurement of Blast Fragmentation: Proceedings of the Fragblast.1996.
[37].Palangio, T.C. and J.A. Franklin. Practical guidelines for lighting and photography [C]. InProceedings of the FRAGBLAST5Workshop on Measurement of Blast Fragmentation,Montreal, Quebec, Canada.1996: AA Balkema.
[38].Dahlhielm, S., Industrial applications of image analysis–The IPACS system [J].Measurement of blast fragmentation. Balkema, Rotterdam,1996:59-65.
[39].Downs, D.C. and B.E. Kettunen, On-line fragmentation measurement utilizing the CIASsystem [J]. Measurement of blast fragmentation. Balkema, Rotterdam,1996:79-82.
[40].Havermann, T. and W. Vogt, TUCIPS–A system for the estimation of fragmentation afterproduction blasts [J]. Measurement of blast fragmentation. Balkema, Rotterdam,1996:67-71.
[41].Kleine, T.H. and A.R. Cameron, Blast fragmentation measurement using GoldSize.Measurement of blast fragmentation [J]. Balkema, Rotterdam,1996:83-89.
[42].Schleifer, J. and B. Tessier, FRAGSCAN: A tool to measure fragmentation of blasted rock.Measurement of Blast Fragmentation [J], Franklin and Katsabanis (eds),1996:73-78.
[43].Wang, W.X. and O. Stephansson, On-line system for monitoring the size distribution ofaggregates on a conveyor belt [J]. Measurement of Blast fragmentation,1996:167-174.
[44].Girdner, K.K., et al. The split system for analyzing the size distribution of fragmented rock[C]. In Measurement of Blast Fragmentation: Proceedings of the Fragblast.1996.
[45].Maerz, N.H., Image sampling techniques and requirements for automated image analys is ofrock fragmentation [C]. Proceedings of the FRAGBLAST,1996.5:115-120.
[46].Kemeny, J.M. Practical technique for determining the size distribution of blasted benches,waste dumps and heap leach sites [C]. In International Journal of Rock Mechanics andMining Sciences and Geomechanics Abstracts.1995: Elsevier.
[47].Maerz, N.H. and W. Zhou, Calibration of optical digital fragmentation measuring systems [J].Fragblast,2000.4(2):126-138.
[48].Maerz, N.H. Online fragmentation analysis: Achievements in the mining industry [C]. InProceedings of the7th Annual ICAR Symposium, International Center for AggregatesResearch, University of Texas at Austin, April19-21.1999.
[49].Maerz, N.H. Aggregate sizing and shape determination using digital image processing [C]. InCenter For Aggregates Research (ICAR) Sixth Annual Symposium Proceedings.1998.
[50].Maerz, N.H. and W. Zhou, Optical digital fragmentation measuring systems–inherent sourcesof error [J]. Fragblast,1998.2(4):415-431.
[51].Schleifer, J. and B. Tessier, Fragmentation assessment using the Fragscan system: Quality ofa blast [J]. Fragblast,2002.6(3-4):321-331.
[52].Hundal, H.S., et al., Particle shape characterization using image a nalysis and neural networks[J]. Powder Technology,1997.91(3):217-227.
[53].Fernlund, J.,3-D image analys is size and shape method applied to the evaluation of the LosAngeles test [J]. Engineering geology,2005.77(1):57--67.
[54].Fernlund, J., Image analysis method for determining3-D shape of coarse aggregate [J].Cement and Concrete Research,2005.35(8):1629--1637.
[55].Fernlund, J.M., The effect of particle form on sieve analys is: a test by image analysis [J].Engineering Geology,1998.50(1):111--124.
[56].Petersen, K.R.P., C. Aldrich and J.S.J. Van Deventer, Analys is of ore particles based ontextural pattern recognition [J]. Minerals Engineering,1998.11(10):959-977.
[57].Persson, A., Image analysis of shape and size of fine aggregates [J]. Engineering geology,1998.50(1):177--186.
[58].Mora, C.F. and A. Kwan, Sphericity, shape factor, and convexity measurement of coarseaggregate for concrete using digital image processing [J]. Cement and concrete research,2000.30(3):351--358.
[59].Mora, C.F., A. Kwan and H.C. Chan, Particle size distribution analys is of coarse aggregateusing digital image processing [J]. Cement and Concrete Research,1998.28(6):921--932.
[60].Das, A. A Revisit to Aggregate Shape Parameters [M].2006.
[61].Pons, M.N., et al., Particle morphology: from visualisation to measurement [J]. PowderTechnology,1999.103(1):44-57.
[62].Wang, W.X., Binary image segmentation of aggregates based on polygonal approximationand classification of concavities [J]. Pattern Recognition,1998.31(10):1503-1524.
[63].Wang, W., Image analysis of particles by modified Ferret method—best-fit rectangle [J].Powder technology,2006.165(1):1-10.
[64].Wang, W., Image analysis of aggregates [J]. Computers\&Geosciences,1999.25(1):71--81.
[65].Wang, W., Rock Particle Image Segmentation and Systems [J]. Pattern RecognitiionTechniques, Technology and Applications chap. VIII:197-226.
[66].Wei-xing, W., Particle Size Estimation Based on Edge Density [J]. Journal of ElectronicScience and Technology,2005.3(4).
[67].Taylor, M.A., Quantitative measures for shape and size of particles [J]. Powder Technology,2002.124(1–2):94-100.
[68].Thurley, M.J., Automated online measurement of limestone particle size distributions using3D range data [J]. Journal of Process Control,2011.21(2):254-262.
[69].Thurley, M.J. On-line3D surface measurement of iron ore green pellets [J].2006.
[70].Thurley, M.J. and T. Andersson, An industrial3D vis ion system for size measurement of ironore green pellets using morphological image segmentation [J]. Minerals engineering,2008.21(5):405--415.
[71].Thurley, M.J. and K.C. Ng, Identification and sizing of the entirely visible rocks from a3Dsurface data segmentation of laboratory rock piles [J]. Computer Vision and ImageUnderstanding,2008.111(2):170-178.
[72].Thurley, M.J. and K.C. Ng, Identifying, visualizing, and comparing regions in irregularlyspaced3D surface data [J]. Computer Vision and Image Understanding,2005.98(2):239-270.
[73].Thurley, M.J. and K.C. Ng, Modelling the relationship between the surface fragments and thepile size distribution in laboratory rock piles [J]. URL http://image3d6. eng. monash. edu. au.
[74].Thurley, M.J., Three dimensional data analys is for the separation and sizing of rock piles inmining [D].2002: Monash University.
[75].Vallebuona, G., K. Arburo and A. Casali, A procedure to estimate weight particledistributions from area measurements [J]. Minerals engineering,2003.16(4):323-329.
[76].Banta, L., K. Cheng and J. Zaniewski, Estimation of limestone particle mass from2D images[J]. Powder technology,2003.132(2):184-189.
[77].Guyot, O., et al., VisioRock, an integrated vision technology for advanced control ofcomminution circuits [J]. Minerals engineering,2004.17(11):1227-1235.
[78].Salinas, R.A., U. Raff and C. Farfan, Automated estimation of rock fragment distributionsusing computer vision and its application in mining [C]. IEE Proceedings-Vision, Image andSignal Processing,2005.152(1):1-8.
[79].Murtagh, F., et al., A machine vision approach to the grading of crushed aggregate [J].Machine Vision and Applications,2005.16(4):229--235.
[80].Murtagh, F., et al., Grading of construction aggregate through machine vision: Results andprospects [J]. Computers in industry,2005.56(8):905--917.
[81].Murtagh, F. and J. Starck, Wavelet and curvelet moments for image classification:Application to aggregate mixture grading [J]. Pattern Recognition Letters,2008.29(10):1557-1564.
[82].Erdogan, S.T., et al., Three-dimensional shape analys is of coarse aggregates: New techniquesfor and preliminary results on several different coarse aggregates and reference rocks [J].Cement and Concrete Research,2006.36(9):1619-1627.
[83].Al-Thyabat, S. and N.J. Miles, An improved estimation of size distribution from particleprofile measurements [J]. Powder technology,2006.166(3):152-160.
[84].Al-Thyabat, S., N.J. Miles and T.S. Koh, Estimation of the size distribution of particlesmoving on a conveyor belt [J]. Minerals engineering,2007.20(1):72-83.
[85].Andersson, T., M.J. Thurley and O. Marklund. Pellet size estimation using spherical fitting[J].2007.
[86].Andersson, T. and M.J. Thurley. Visibility classification of rocks in piles [J].2008.
[87].Andersson, T. and M.J. Thurley, Minimizing profile error when estimating the sieve-sizedistribution of iron ore pellets using ordinal logistic regression [J]. Powder Technology,2011.206(3):218--226.
[88].Andersson, T., M.J. Thurley and J.E. Carlson, A machine vision system for estimation of sizedistributions by weight of limestone particles [J]. Minerals Engineering,2012.25(1):38-46.
[89].Koh, T.K., et al., Improving particle size measurement using multi-flash imaging [J].Minerals Engineering,2009.22(6):537-543.
[90].Liao, C., J. Yu and Y. Tarng, On-line full scan inspection of particle size and shape usingdigital image processing [J]. Particuology,2010.8(3):286--292.
[91].Liao, C.W. and Y.S. Tarng, On-line automatic optical inspection system for coarse particlesize distribution [J]. Powder Technology,2009.189(3):508-513.
[92].Aldrich, C., et al., Online Analysis of Coal on A Conveyor Belt by use of Machine Visionand Kernel Methods [J]. International Journal of Coal Preparation and Utilization,2010.30(6):331--348.
[93].Igathinathane, C., et al., Machine vision based particle size and size distributiondetermination of airborne dust particles of wood and bark pellets [J]. Powder Technology,2009.196(2):202-212.
[94].Igathinathane, C., U. Ulusoy and L.O. Pordesimo, Comparison of particle size distribution ofcelestite mineral by machine vision ΣVolume approach and mechanical sieving [J]. PowderTechnology,2012.215–216:137-146.
[95].Ko, Y. and H. Shang, A neural network-based soft sensor for particle size distribution usingimage analysis [J]. Powder Technology,2011.212(2):359-366.
[96].Ko, Y. and H. Shang, Time delay neural network modeling for particle s ize in SAG mills [J].Powder Technology,2011.205(1):250-262.
[97].Jain, A., M.J. Metzger and B.J. Glasser, Effect of particle size distribution on segregation invibrated systems [J]. Powder Technology,2012.
[98].苑玮琦,王建军.基于局部灰度极值法的水泥生料球图像边缘检测[J].模式识别与人工智能,1997.10(4):376-381.
[99].苑玮琦,王建军.计算机图象识别技术在水泥生料球粒度检测中的应用[J].基础自动化,1997.4(2):39-41.
[100].苑玮琦,王建军,张宏勋.生料球粒度在线检测方法研究[J].仪器仪表学报,1998.1(19):29-33.
[101].苑玮琦.球形物料图像的分割方法研究[J].信号处理,1998.14(1):66-70.
[102].苑玮琦,张宏勋.料球粒径的非接触检测方法[J].现代计量测试,1997.5(2):15-19.
[103].蔡健荣,赵杰文,方如明.基于计算机视觉的粒度检测方法研究[J].农业工程学报,2002.18(3):161-164.
[104].黄胜国,杨英杰,蓝青叁.显微图像分析系统及其在矿物粒度分析中的应用研究[J].岩矿测试,2003(04):269-272.
[105].杨英杰,黄胜国,蓝青叁.显微图像识别及其在粒度分析中的应用[J].矿业工程,2003(04):36-38.
[106].敖广武,温春友,张学东.基于小波变换的球团矿图像边缘检测[J].烧结球团,2005.30(5):29-32.
[107].温春友,邵志勇.基于数字图像处理的球团矿粒度检测[J].烧结球团,2004.29(2):38-40.
[108].侯小红.基于图像处理的煤粉颗粒检测技术研究[J],2006,太原理工大学硕士学位论文.
[109].张学礼.计算机数字图像处理技术在在线矿物粒度检测中的应用[J],2006,昆明理工大学.
[110].张学礼,贾瑞强.矿物粒度测定方法的比较及发展前瞻[J].矿业工程,2006.4(4):50-52.
[111].宋玉丹. Image J在矿物初碎检测中的应用[D],2008,太原理工大学.
[112].辛登科,张玉杰,苏治果.图像处理在粉末粒度在线检测系统中的应用[J].计算机工程与设计,2008(13):3510-3512.
[113].王大海.显微图像粒度检测系统研究[J].矿冶,2008(02):114-116.
[114].王大海,贾玉珍,靳冰.一种多粒度集群数据库并发控制新算法[J].河北工程大学学报(自然科学版),2010(04):86-91.
[115].李银华,路新惠,靳贺敏.基于图像处理的金刚石磨粒体积计算研究[J].计算机工程与设计,2009(18):4242-4244.
[116].路新惠,高士忠,张瑜.图像处理技术在金刚石粒度检测中的应用[J].工业控制计算机,2010(08):99-100.
[117].魏炳辉.基于粒度分析的矿物颗粒图像处理及参数分析研究与实现[J],2010,江西理工大学.
[118].刘伟华.基于机器视觉的煤尘在线检测系统关键技术研究[D],2011,山东大学.
[119].梁栋华,张国英,于飞. BOSA-Ⅰ矿石粒度图像分析仪的研究与应用[J].中国计量协会冶金分会2011年会论文集,2011.
[120].张国英.基于图像的原矿碎石粒度检测与分析系统[J].冶金自动化,2012.36(3):63-67.
[121].刘伊夫.基于DM6446的球团粒度检测系统研究[D],2011,辽宁科技大学.
[122].曾珽.矿石粘连颗粒检测与分割算法研究[J],2012,江西理工大学.55.
[123].李珍香,罗宏宇.一种基于PC机的煤泥浮选自动识别系统[J].电脑开发与应用,2000(02):30-31.
[124].李珍香,罗宏宇.浮选泡沫的计算机图像处理与识别方法[J].煤炭技术,1999(06):17-19.
[125].Aldrich, C., et al., Online monitoring and control of froth flotation systems with machinevision: A review [J]. International Journal of Mineral Processing,2010.96(1–4):1-13.
[126].Cipriano, A., et al., A real time visual sensor for supervision of flotation cells [J]. MineralsEngineering,1998.11(6):489-499.
[127].Cipriano, A., et al. Expert supervision of flotation cells using digital image processing [C].in Proceedings of the20th International Mineral Processing Congress.1997.
[128].Symonds, P.J. and G. De Jager. A technique for automatically segmenting images of thesurface froth structures that are prevalent in industrial flotation cells [C]. In Communicationsand Signal Processing,1992. COMSIG'92., Proceedings of the1992South AfricanSymposium on.1992: IEEE.
[129].Moolman, D.W., Digital image processing as a tool for on-line monitoring of froth inflotation plants [J]. Minerals Engineering,1994.7(9):1149-1164.
[130].Wang, W., F. Bergholm and B. Yang, Froth delineation based on image classification [J].Minerals engineering,2003.16(11):1183-1192.
[131].Wang, W. and O. Stephansson. A robust bubble delineation algorithm for froth images [C].In Intelligent Processing and Manufacturing of Materials,1999. IPMM'99. Proceedings of theSecond International Conference on.1999: IEEE.
[132].Hargrave, J.M., N.J. Miles and S.T. Hall, The use of grey level measurement in predictingcoal flotation performance [J]. Minerals engineering,1996.9(6):667-674.
[133].曾荣.浮选泡沫图象边缘检测方法的研究[J].中国矿业大学学报,2002(05):84-88.
[134].曾荣.沃国经.图像处理技术在镍选矿厂中的应用[J].矿冶,2002(01):37-41.
[135].曾荣.沃国经.图像处理技术在浮选过程中的应用[J].有色金属,2001(04):70-72.
[136].王凡,路迈西.煤泥浮选泡沫层中气泡特征的提取[J].中国矿业大学学报,2001(06):24-27.
[137].王凡,路迈西.煤泥浮选泡沫的图像处理[J].煤炭科学技术,2001(11):28-30.
[138].王勇,路迈西.表征煤泥浮选泡沫图象特征的最佳色彩方案[J].中国矿业大学学报,2002(06):71-73.
[139].王勇,路迈西.煤泥浮选泡沫图像灰度行程及其统计纹理特征[J].煤炭学报,2006(01):94-98.
[140].王勇,路迈西.煤泥浮选泡沫图像灰度直方图及其统计纹理特征研究[J].选煤技术,2006(01):13-16.
[141].刘文礼,陈子彤,路迈西.煤泥浮选泡沫的数字图像处理[J].燃料化学学报,2002(03):198-203.
[142].刘文礼,路迈西.数字图像处理技术在煤泥浮选泡沫图像纹理特征的提取及识别上的应用[J].选煤技术,2004(04):78-81
[143].刘文礼,路迈西.煤泥浮选泡沫图像纹理特征的提取及泡沫状态的识别[J].化工学报,2003(06):830-835.
[144].刘文礼,路迈西.煤泥浮选泡沫数字图象处理研究(之一)——浮选泡沫视觉特征的线邻域提取算法[J].中国矿业大学学报,2002(02):13-16.
[145].刘文礼,路迈西.煤泥浮选泡沫数字图象处理研究(之二)——煤泥浮选泡沫视觉特征的面邻域提取算法[J].中国矿业大学学报,2002(03):20-23.
[146].刘文礼,路迈西.浮选泡沫特征及其状态识别[J].中国煤炭,2003(05):51-53.
[147].黄玉华,路迈西.基于灰色系统理论的煤泥浮选泡沫数字图像处理算法研究[J].选煤技术,2006(04):6-8.
[148].Kaartinen, J., Machine-vision-based control of zinc flotation—a case study [J]. ControlEngineering Practice,2006.14(12):1455-1466.
[149].谷莹莹.基于分水岭变换的浮选泡沫图像分割[J].北京石油化工学院学报,2007(01):61-66.
[150].林小竹,谷莹莹,赵国庆.煤泥浮选气泡比表面积的计算方法[J].煤炭学报,2007(08):874-878.
[151].林小竹,谷莹莹,赵国庆.煤泥浮选泡沫图像分割与特征提取[J].煤炭学报,2007(03):304-308.
[152].桂卫华,阳春华.一种基于DSP的嵌入式浮选泡沫图像监控装置[J],2013.9.
[153].桂卫华,阳春华.一种基于图像特征分析的浮选回收率预测方法[J],2008.8.
[154].桂卫华,阳春华.一种浮选泡沫图像视觉监控装置[J],2009.8.
[155].桂卫华,阳春华.一种基于纹理单元分布的硫浮选过程故障检测方法[J],2012.13.
[156].阳春华.一种基于机器视觉的浮选泡沫图像识别设备及精矿品位预测方法[J],2007.11.
[157].阳春华.用于浮选泡沫图像分析的关键特征提取方法[J],2008.10.
[158].阳春华.一种基于泡沫图像特征和通风量的硫浮选液位测量方法[J],2012.12.
[159].何桂春.浮选泡沫图像处理技术研究现状与进展[J].有色金属科学与工程,2011(02):57-63.
[160].何桂春,黄开启.浮选指标与浮选泡沫数字图像关系研究[J].金属矿山,2008(08):96-101.
[161].杨洪薇,肖志涛,翁秀梅.基于分水岭和模糊C均值聚类的图像分割方法[J].天津工业大学学报,2008(01):53-55.
[162].牟春洁,张国英.基于区域边界生长的图像分割方法[J].北京石油化工学院学报,2009(04):8-12.
[163].牟春洁,张国英.基于射线的泡沫图象分割算法[J].北京石油化工学院学报,2010(01):36-40.
[164].唐朝晖,杜金芳,陈青.一种基于混合神经网络的浮选pH值预测模型[J].控制工程,2012(03):416-419.
[165].唐朝晖.基于特征的构件化软件设计关键技术研究[C], in第三十二届中国控制会议2013:中国陕西西安.5.
[166].唐朝晖.泡沫浮选过程视觉监控系统软件构件化设计与开发[C],第25届中国控制与决策会议2013:中国贵州贵阳.5.
[167].唐朝晖.基于数字图像处理的浮选泡沫速度特征提取及分析[J].中南大学学报(自然科学版),2009(06):1616-1622.
[168].唐朝晖.基于小波变换的浮选泡沫图像纹理特征提取[J].计算机工程,2011(18):206-208.
[169].唐朝晖,朱楚梅,刘金平.基于LBPV的浮选泡沫图像纹理特征提取[J].计算机应用研究,2011(10):3934-3936.
[170].王建昆.浮选过程泡沫图像特征识别研究[J].云南冶金,2009(01):65-67.
[171].周开军.矿物浮选泡沫图像形态特征提取方法与应用[J],2010,中南大学.151.
[172].周开军.基于泡沫特征与LS-SVM的浮选回收率预测[J].仪器仪表学报,2009(06):1295-1300.
[173].周开军.基于图像特征提取的浮选关键参数智能预测算法[J].控制与决策,2009(09):1300-1305.
[174].刘金平.基于Gabor小波的浮选泡沫图像纹理特征提取[J].仪器仪表学报,2010(08):1769-1775.
[175].沃国经. FP-01浮选泡沫图像处理系统[C],首届全国有色金属自动化技术与应用学术年会2003:中国南昌.3.
[176].沃国经. FP-01浮选泡沫图像处理系统[J].有色冶金设计与研究,2003(S1):87-89.
[177].Jones, M.P., Applied mineralogy: a quantitative approach [J].1987: Springer.
[178].Petruk, W., Automatic image analysis for mineral beneficiation. JOM Journal of theMinerals [J], Metals and Materials Society,1988.40(4):29-31.
[179].Technology, C.C.F.M., M.P.L. Canada and W. Petruk, The MP-SEM-IPS image analysissystem [J].1986: Canada Centre for Mineral and Energy Technology.
[180].Bonifazi, G., Digital multispectral techniques and automated image analysis procedures forindustrial ore modeling [J]. Minerals Engineering,1995.8(7):779-794.
[181]. Laine, S., H. Lappalainen and S. J ms-Jounela, On-line determination of ore type usingcluster analysis and neural networks [J]. Minerals engineering,1995.8(6):637-648.
[182].Peng, Z. and T.B. Kirk, Computer image analysis of wear particles in three-dimensions formachine condition monitoring [J]. Wear,1998.223(1):157-166.
[183].Perez, C., et al. Lithological composition sensor based on digital image feature extraction,genetic selection of features and neural classification [C]. In Information Intelligence andSystems,1999. Proceedings.1999International Conference on.1999.
[184].Perez, C.A., et al., Ore grade estimation by feature selection and voting us ing boundarydetection in digital image analysis [J]. International Journal of Mineral Processing,2011.101(1–4):28-36.
[185].刘富强.基于图像处理与识别技术的煤矿矸石自动分选[J].煤炭学报,2000(05):534-537.
[186].马宪民.煤矸石在线识别与自动分选系统的研究[J].西安科技学院学报,2003(01):66-68.
[187].马宪民.一种基于小波变换的煤矸石图像边缘检测方法[J].仪器仪表学报,2006(S3):2130-2131.
[188].马宪民,蒋勇.煤与矸石识别的数字图像处理方法探讨[C],中国煤炭学会煤矿机电一体化专业委员会、中国电工技术学会煤矿电工专业委员会2004年学术年会2004:中国浙江杭州.3.
[189].马宪民,蒋勇.煤矸石二值图像的Roberts快速边缘检测法[C],第三届全国信息获取与处理学术会议2005:中国浙江.3.
[190].马宪民,蒋勇.煤与矸石识别的数字图像处理方法探讨[J].煤矿机电,2004(05):9-11.
[191].马宪民,蒋勇,卜祥莉.基于图像处理的煤矸石自动分选系统的研究[C],2003年中国智能自动化会议2003:中国香港.4.
[192].马宪民,蒋勇,王雪娟.一种煤矸石图像边缘提取的小波分析法[C],第十四届全国煤矿自动化学术年会、中国煤炭学会自动化专业委员会学术会议2004:山东青岛.3.
[193].马宪民,田红,龚尚福.煤矸石在线识别与自动分选系统的研究[C],2001年中国智能自动化会议2001:中国云南昆明.4.
[194].Casali, A., et al., Grindability soft-sensors based on lithological composition and on-linemeasurements [J]. Minerals Engineering,2001.14(7):689-700.
[195].Ke, J., Neural-Network Modelling Of Placer Ore Grade Spatial Variability [J].2002,University of Alaska Fairbanks.
[196].Lepist, L., et al., Rock image classification using non-homogenous textures and spectralimaging[J]. WSCG proc., WSCG,2003.
[197].Lepist, L., I. Kunttu and A. Visa, Rock image classification using color features in Gaborspace [J]. Journal of Electronic Imaging,2005.14(4):040503-040503-3.
[198].Paclík, P., S. Verzakov and R.P. Duin, Improving the maximum-likelihood co-occurrenceclassifier: a study on classification of inhomogeneous rock images [C], In Image Analysis.2005, Springer.998-1008.
[199].Raadnui, S., Wear particle analys is—utilization of quantitative computer image analysis: areview [J]. Tribology International,2005.38(10):871-878.
[200].Singh, N., et al., Textural identification of basaltic rock mass using image processing andneural network [J]. Computational Geosciences,2010.14(2):301-310.
[201].Singh, V. and S.M. Rao, Application of image processing in mineral industry: a case studyof ferruginous manganese ores [J]. Mineral Processing and Extractive Metallurgy,2006.115(3):155-160.
[202].Singh, V. and S.M. Rao, Application of image processing and radial basis neural networktechniques for ore sorting and ore classification [J]. Minerals Engineering,2005.18(15):1412-1420.
[203].Sun, J., et al., Classification of Infrared Monitor Images of Coal Us ing an Feature TextureStatistics and Improved BP Network [J]. Journal of China University of Mining andTechnology,2007.17(4):489-493.
[204].Ma, X. A revised edge detection algorithm based on wavelet transform for coal gangueimage [J]. In Machine Learning and Cybernetics,2007International Conference on.2007:IEEE.
[205].Donskoi, E., Modelling and optimization of hydrocyclone for iron ore fines beneficiation—using optical image analysis and iron ore texture classification [J]. International Journal ofMineral Processing,2008.87(3–4):106-119.
[206].Dal Grande, F., A. Santomaso and P. Canu, Improving local composition measurements ofbinary mixtures by image analys is [J]. Powder Technology,2008.187(3):205-213.
[207].Kachanubal, T. and S. Udomhunsakul, Rock textures classification based on textural andspectral features [J]. Proc. of World Academy of Science, Eng. and Tech,2008.29:110-116.
[208].Gon alves, L.B., F.R. Leta and S.C. de Valente. Macroscopic rock texture imageclassification using an hierarchical neuro-fuzzy system [C]. in Systems, Signals and ImageProcessing,2009. IWSSIP2009.16th International Conference on.2009: IEEE.
[209].Chatterjee, S., S. Bandopadhyay and D. Machuca, Ore grade prediction using a geneticalgorithm and clustering based ensemble neural network model [J]. MathematicalGeosciences,2010.42(3):309-326.
[210].Chatterjee, S., et al., Image-based quality monitoring system of limestone ore grades [J].Computers in Industry,2010.61(5):391-408.
[211].叶润青,牛瑞卿,张良培.基于多尺度分割的岩石图像矿物特征提取及分析[J].吉林大学学报(地球科学版),2011(04):1253-1261.
[212].叶润青.基于图像分类的矿物含量测定及精度评价[J].中国矿业大学学报,2011(05):810-815.
[213].何敏,王培培,蒋慧慧.基于SVM和纹理的煤和煤矸石自动识别[J].计算机工程与设计,2012(03):1117-1121.
[214].Banta, L., K. Cheng and J. Zaniewski, Estimation of limestone particle mass from2Dimages[J]. Powder Technology,2003.132(2–3):184-189.
[215].程鹏飞.植物病害的图像处理及特征值提取方法的研究[J],2005,山西农业大学.48.
[216].何春.基于特征的交通标志图像识别的应用研究[J],2013,广东工业大学.71.
[217].张振升,朱名日,潘泽锴.基于图像处理的蔗糖结晶颗粒识别方法[J].计算机系统应用,2010(03):95-99.
[218].刘兆艳.基于机器视觉的稻种品种识别研究[J],2006,浙江大学.62.
[219].唐强.基于图像模式识别技术的昆虫识别研究[J],2006,昆明理工大学.61.
[220].胡永刚.基于数学形态学的遥感图像边缘检测算法[J],2006,燕山大学.74.
[221].姚进.基于数学形态学的图像边缘检测研究[J],2005,山东师范大学.65.
[222].Vincent, L. and P. Soille, Watersheds in digital spaces: an efficient algorithm based onimmersion simulations [C]. IEEE transactions on pattern analysis and machine intelligence,1991.13(6):583-598.
[223].陈家新,王纪刚.一种改进的医学图像分水岭分割算法[J].计算机应用研究,2013.
[224].陈婷婷.采用模糊形态学和分水岭算法的图像分割研究[J],2008,西南大学.62.
[225].卢蓉.一种提取目标图像最小外接矩形的快速算法[J].计算机工程,2010(21):178-180.
[226].袁佐云,牛兴和,刘传云.基于最小外接矩形的稻米粒型检测方法[J].粮食与饲料工业,2006(09):7-8.
[227].邓玥.天空区域图像的增强算法的改进[J].激光与红外,2012(09):1080-1085.
[228].刘燕君,刘奇.基于同态滤波与直方图均衡化的超声图像增强[J].中国组织工程研究与临床康复,2011(48):9031-9034.
[229].Pizer, S.M., et al., Adaptive histogram equalization and its variations[J]. Computer vision,graphics, and image processing,1987.39(3):355-368.
[230].Pizer, S.M., et al. Contrast-limited adaptive histogram equalization: speed and effectiveness[J]. In Visualization in Biomedical Computing,1990., Proceedings of the First Conference on.1990: IEEE.
[231].江涛,王永仲.基于改进递归最大值滤波的红外点目标检测[J].红外技术,2004.26(3):41-44.
[232].邢藏菊.一种用于抑制椒盐噪声的多窗口中值滤波器[J].2002.
[233].康牧,许庆功,王宝树.一种Roberts自适应边缘检测方法[J].西安交通大学学报,2008(10):1240-1244.
[234].王冰.用Roberts算子进行边缘处理[J].甘肃科技,2008(10):18-20.
[235].樊娜,李晋惠.图像边缘检测的Prewitt算子的改进算法[J].西安工业学院学报,2005(01):37-39.
[236].侯艳,路迈西,张少波.用不同图像边缘检测算法识别粉煤灰等颗粒物[J].洁净煤技术,2008(06):77-79.
[237].刘煜,李言俊,张科.一种多像素图像边缘提取方法[J].光子学报,2007(02):380-384.
[238].江雯.基于Sobel算子的自适应图像缩放算法[J].计算机工程,2010(07):214-216.
[239].沈德海,侯建,鄂旭.基于改进的Sobel算子边缘检测算法[J].计算机技术与发展,2013(11).
[240].袁春兰.基于Sobel算子的图像边缘检测研究[J].激光与红外,2009(01):第85-87页.
[241].何新英.基于数学形态学和Canny算子的边缘提取方法[J].计算机应用,2008(02):477-478.
[242].周晓明.一种改进的Canny算子边缘检测算法[J].测绘工程,2008(01):第28-31页.
[243].郭薇.基于Hessian矩阵及梯度熵的疑似肺结节检测算法[J].仪器仪表学报,2009(08):1702-1706.
[244].李颖超,刘越,王涌天.基于多尺度Hessian矩阵和Gabor滤波的造影图像冠脉中心线提取[J].中国医学影像技术,2007(01):133-136.
[245].许燕.基于Hessian矩阵的冠状动脉中心线的跟踪算法[J].清华大学学报(自然科学版),2007(06):889-892.
[246].Kwan, A., C.F. Mora and H.C. Chan, Particle shape analysis of coarse aggregate usingdigital image processing [J]. Cement and Concrete Research,1999.29(9):1403--1410.
[247].Vallebuona, G., K. Arburo and A. Casali, A procedure to estimate weight particledistributions from area measurements [J]. Minerals Engineering,2003.16(4):323-329.
[248].刘晨敏,樊向林.原生煤粉粒度特性的研究[J].中州煤炭,2009(05):22-24.
[249].邬小骐,邵全渝,张国祥.原矿及破碎产品标准粒度特性方程的研究[J].有色冶金设计与研究,1997(04):7-11.
[250].闫培培,张兴芳,樊民强.一种包含偏斜系数的粒度特性方程[J].中国粉体技术,2013(03):58-61.
[251].高士忠.基于灰度共生矩阵的织物纹理分析[J].计算机工程与设计,2008(16):4385-4388.
[252].施建宇,张艳宁.使用图像特征构建快速有效的蛋白质折叠识别方法[J].生物物理学报,2009(02):106-116.
[253].王克奇.基于空间灰度共生矩阵的木材纹理特征提取[J].森林工程,2006(01):24-26.
[254].Haralick, R.M., Statistical and structural approaches to texture [J]. Proceedings of the IEEE,1979.67(5):786-804.
[255].Haralick, R.M., K. Shanmugam and I.H. Dinstein, Textural features for image classification.Systems [J], Man and Cybernetics, IEEE Transactions on,1973(6):610-621.
[256].Tamura, H., S. Mori and T. Yamawaki, Textural features corresponding to visual perception.Systems, Man and Cybernetics [C], IEEE Transactions on,1978.8(6):460-473.
[257].郝玉保.改进Tamura纹理特征的图像检索方法[J].测绘科学,2010(04):136-138.
[258].吕晓琪.基于图像分割的Tamura纹理特征算法的研究与实现[J].中国组织工程研究,2012(17):3160-3163.
[259].王顺杰,齐春,程玉胜. Tamura纹理特征在水下目标分类中的应用[J].应用声学,2012(02):135-139.
[260].梁晓霞,封筠.基于Gabor变换和灰度梯度共生矩阵的人耳识别研究[J].石家庄铁道大学学报(自然科学版),2011(01):78-83.
[261].刘凯,黄峰,罗坚.基于纹理特征的卫星云图台风自动识别方法[J].微型机与应用,2001(09):48-49.
[262].万鹏,龙长江.基于灰度-梯度共生矩阵的大米加工精度的机器视觉检测方法[J].粮食储藏,2010(04):48-51.
[263].夏德深,金盛,王健.基于分数维与灰度梯度共生矩阵的气象云图识别(Ⅱ)——灰度梯度共生矩阵对纹理统计特征的描述[J].南京理工大学学报,1999(04):289-292.
[264].方浩,贾睿,卢嘉鹏.基于颜色和纹理特征的道路图像分割[J].北京理工大学学报,2010(08):935-939.
[265].刘建立,左保齐,高卫东.非织造材料外观质量识别的小波纹理分析方法[J].计算机工程与设计,2011(08):2836-2840.
[266].罗涟玲.遥感图像森林类型小波纹理的SVM法分类[J].计算机工程与应用,2012(16):194-197.
[267].谢锋,林怡,陈映鹰.基于小波纹理与改进FCM的SAR机场类目标提取[J].同济大学学报(自然科学版),2009(01):115-120.
[268].丛瑜,肖怀铁,付强.基于核主分量分析的高分辨雷达目标特征提取与识别[J].电光与控制,2008(02):31-35.
[269].冯永玖.基于核主成分元胞模型的城市演化重建与预测[J].地理学报,2010(06):665-675.
[270].邵年华. KPCA_SVM水文时间序列预测模型的建立与应用[J].西北农林科技大学学报(自然科学版),2009(09):204-208.
[271].吴洪艳,黄道平.基于特征向量提取的核主元分析法[J].计算机科学,2009(07):185-187.
[272].Goldberg, D.E. and J.H. Holland, Genetic algorithms and machine learning [J]. Machinelearning,1988.3(2): p.95-99.
[273].Boser, B.E., I.M. Guyon and V.N. Vapnik. A training algorithm for optimal marginclassifiers [C]. In Proceedings of the fifth annual workshop on Computational learning theory.1992: ACM.
[274].叶航军,白雪生,徐光祐.基于支持向量机的人脸姿态判定[J].清华大学学报(自然科学版),2003(01):67-70.
[275].高学.一种基于支持向量机的手写汉字识别方法[J].电子学报,2002(05):651-654.
[276].王欢良,韩纪庆,张磊.基于支持向量机的变异语音分类研究[J].哈尔滨工业大学学报,2003(04):389-393.
[277].马金娜,田大钢.基于支持向量机的中文文本自动分类研究[J].系统工程与电子技术,2007(03):475-478.
[278].马金娜,田大钢.基于SVM的中文文本自动分类研究[J].计算机与现代化,2006(08):5-8.
[279].Chang, C. and C. Lin, LIBSVM: a library for support vector machines [J], Software (2001).
[280].高媛媛,刘强国.基于LIBSVM的葡萄酒品质评判模型[J].四川理工学院学报(自然科学版),2010(05):530-532.
[281].任立辉.基于LIBSVM的石油录井中岩屑岩性识别方法研究[J].中国海洋大学学报(自然科学版),2010(09):131-136.
[282].曾鸣,林磊,程文明.基于LIBSVM和时间序列的区域货运量预测研究[J].计算机工程与应用,2013(21):6-10.
[283].张泽琳，杨建国.煤灰分在线检测方法及设备[J].选煤技术,2012(2):59-63.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |