金属断口图像处理研究进展
|
摘要
论述了金属断口图像处理在国内外的发展与研究现状,以及金属断口图像的预处理过程、对图像的特征提取以及模式识别3个部分,并基于空间域及变换域对三部分的方法进行统计分析以及归纳总结。同时,针对算法的运算时间及速率、识别率以及鲁棒性等性能指标,对金属断口图像的识别综合性能进行判断分析和探讨。指出现阶段金属断口图像处理算法存在的不足之处及其进一步的发展方向,这将为断口图像智能诊断技术的发展提供有力的参考。
This article mainly discusses the development and research status of metal fracture image processing at home and abroad.This topic covers three parts of metal fracture image preprocessing,image feature extraction and pattern recognition.Based on spatial domain and transform domain,the three methods are statistically analyzed and summarized.At the same time,according to the algorithm 's computing time,speed,recognition rate,robustness and other performance indicators,the comprehensive performance of metal fracture image recognition is analyzed and discussed.At the same time,the shortcomings of metal fracture image processing algorithm and their further development direction are pointed out,which will provide a powerful reference for the development of intelligent image fracture imaging technology.
This article mainly discusses the development and research status of metal fracture image processing at home and abroad.This topic covers three parts of metal fracture image preprocessing,image feature extraction and pattern recognition.Based on spatial domain and transform domain,the three methods are statistically analyzed and summarized.At the same time,according to the algorithm 's computing time,speed,recognition rate,robustness and other performance indicators,the comprehensive performance of metal fracture image recognition is analyzed and discussed.At the same time,the shortcomings of metal fracture image processing algorithm and their further development direction are pointed out,which will provide a powerful reference for the development of intelligent image fracture imaging technology.
引文
[1]钟群鹏,赵子华,张峥.断口学的发展及微观断裂机理研究[J].机械强度,2005,27(3):358-370.
[2]Solomon C,Breckon T.Fundamentals of digital image processing:A practical approach with examples in Matlab[M].Wiley-Blackwell,A John Wiley&Sons,Ltd.,Publication,2011:1-55.
[3]聂鹏,李志农,邬冠华.Bandelet变换在金属断口图像去噪中的应用[J].噪声与振动控制,2010,30(5):149-152.
[4]吴松林,瞿洋,张凤鸣.断口显微图象信息的层次结构及其表示[J].信息与控制,1996,25(2):109-114.
[5]Afraites L,Atlas A,Karami F,et al.Some class of parabolic systems applied to image processing[J].Discrete and Continuous Dynamical Systems-Series B(DCDS-B),2017,21(6):1671-1687.
[6]Wang Q,Weng G R.Application of snakes model in metal fracture images processing[J].Advanced Materials Research,2013,659:139-142.
[7]侯娟,李志农.小波变换压缩感知在断口图像重构中的应用研究[J].南昌航空大学学报:自然科学版,2017,31(1):41-46.
[8]Mallat S.Geometrical grouplets[J].Applied and Computational Harmonic Analysis,2009,26(2):161-180.
[9]梁鹏,李志农,肖尧先.循环平移Contourlet变换在金属断口图像消噪中的应用[J].兵器材料科学与工程,2011,34(4):13-16.
[10]周志宇.基于Grouplet变换的金属断口图像处理方法研究[D].南昌:南昌航空大学,2013:9-73.
[11]Tang J,Huang L.Feature extraction of partial discharge grayscale images for identification based on multifractal spectrum using fluorescence fiber sensor[J].Optical Engineering,2014,53(5):053102.
[12]韩太坤,李志农.基于灰度共生矩阵与局部线性嵌入的金属断口图像识别方法研究[J].机械强度,2014(1):129-133.
[13]Cavalin P,Oliveira L S,Koerich A L,et al.Wood defect detection using grayscale images and an optimized feature set[C].IEEE Industrial Electronics,2006:3408-3412.
[14]吴松林,苏恩泽.基于边缘邻域形态分析的纹理视觉模式识别[J].信号处理,1995(4):312-316.
[15]Manjunath B S,Ma W Y.Texture features for browsing and retrieval of image data[J].IEEE Trans Pami,1996,18(8):837-842.
[16]Du H,Hu Q,Jiang M,et al.Two-dimensional principal component analysis based on Schatten p-norm for image feature extraction[J].Journal of Visual Communication&Image Representation,2015,32:55-62.
[17]Chen Y,Jiang H,Li C,et al.Deep feature extraction and classification of hyperspectral images based on convolutional neural networks[J].IEEE Transactions on Geoscience&Remote Sensing,2016,54(10):6232-6251.
[18]Muhammad B,Abu-Bakar A R.Face detection in profile views using fast discrete curvelet transform(FDCT)and support vector machine(SVM)[J].International Journal on Smart Sensing and Intelligent Systems,2016,27(2):118-133.
[19]Gilles J,Tran G,Osher S.2D empirical transforms.Wavelets,Ridgelets and Curvelets revisited[J].Siam Journal on Imageing Sciences,2014,7(1):157-186.
[20]陈烽.多特征空间下金属断口图像自适应识别方法的改进研究[J].世界有色金属,2016(16):61-62.
[21]李凌,黎明,鲁宇明.基于模糊灰度共生矩阵与隐马尔可夫模型的断口图像识别[J].中国图象图形学报,2010,15(9):1370-1375.
[22]颜云辉,马朋仁,曹宇光,等.金属断口图像句法模式识别与分类方法[J].中国机械工程,2004,15(3):259-262.
[23]Albukhanajer W A,Jin Y,Briffa J A.Classifier ensembles for image identification using multi-objective Pareto features[J].Neurocomputing,2017,238:316-327.
[24]Zheng X L,Zhang R,Zeng X.Elevator door protection method based on new moving image identification[J].Journal of Computational Methods in Sciences&Engineering,2015,15(4):611-623.
[25]颜云辉,杨会林,王成明.金属断口图像的非线性模式识别方法[J].东北大学学报:自然科学版,2004,25(9):884-886.
[26]Yamagiwa K,Izumi S,Sakai S.Detecting method of striation region of fatigue fracture surface using wavelet transform[J].Journal of the Society of Materials Science Japan,2004,53(3):306-312.
[27]何其贵,余春平,余丽萍.基于断口图像纹理特征提取仿真方法研究[J].计算机仿真,2011,28(9):279-282.
[28]Li C C,Yin L W,Chen D.Study on plant pest images identification based on lifting wavelet transform[J].Applied Mechanics&Materials,2014,687-691:3640-3643.
[29]Zou R B,Shi C C.A sea-sky line identification algorithem based on shearlets for infrared image[J].Advanced Materials Research,2014,846-847:1031-1035.
[30]孙熠,李志农,闫敬文.基于Grouplet熵与关联向量机的断口图像识别方法研究[J].失效分析与预防,2015,10(1):1-5.
[31]梁鹏,李志农.基于Contourlet-RVM航空构件断口图像识别方法研究[J].机械强度,2013,35(4):395-399.
[32]Xu J,Yang X H,Shao X X.A new medical image mosaic algorithm based on fuzzy sets recognition method[C].International Conference on Bioinformatics and Biomedical Technology,IEEE,2010:180-184.
[33]Chen G,Hu J,Li D,et al.Image recognition of maize diseases based on fuzzy clustering and support vector machine algorithm[J].NJAS-Wageningen Journal of Life Sciences,2012,10(1-2):433-438.
[34]汪东平,涂敏.基于深度学习的刑侦图像处理新方法[J].江西警察学院学报,2017(6):53-56.
[35]蒋子源.用深度学习技术解决图像语义分割问题[J].电子制作,2017(20):39-40.
[36]黄祥钧,邢武,李锋.基于句法模式识别的脉搏波特征信息研究[J].中国医疗器械杂志,2005,29(5):325-327.
[37]Zhou L,Wang L,Liu L,et al.Support vector machines for neuroimage analysis:Interpretation from discrimination[M].Springer International Publishing,2014:191-220.
[38]董超,田联房.最速上升关联向量机高光谱影像分类[J].光学精密工程,2012,20(6):1398-1405.
[39]Keller J M,Gray M R,Givens J A.A fuzzy K-nearest neighbor algorithm[J].IEEE Transactions on Systems Man&Cybernetics,2012,15(4):580-585.
[40]Lei Y,Zuo M J.Gear crack level identification based on weighted K,nearest neighbor classification algorithm[J].Mechanical Systems&Signal Processing,2009,23(5):1535-1547.
[41]张琳,陈燕,李桃迎,等.决策树分类算法研究[J].计算机工程,2011,37(13):66-67.
[42]史朝辉,王晓丹,赵士敏,等.改进的SVM决策树分类算法[J].空军工程大学学报:自然科学版,2006,7(2):32-35.
[2]Solomon C,Breckon T.Fundamentals of digital image processing:A practical approach with examples in Matlab[M].Wiley-Blackwell,A John Wiley&Sons,Ltd.,Publication,2011:1-55.
[3]聂鹏,李志农,邬冠华.Bandelet变换在金属断口图像去噪中的应用[J].噪声与振动控制,2010,30(5):149-152.
[4]吴松林,瞿洋,张凤鸣.断口显微图象信息的层次结构及其表示[J].信息与控制,1996,25(2):109-114.
[5]Afraites L,Atlas A,Karami F,et al.Some class of parabolic systems applied to image processing[J].Discrete and Continuous Dynamical Systems-Series B(DCDS-B),2017,21(6):1671-1687.
[6]Wang Q,Weng G R.Application of snakes model in metal fracture images processing[J].Advanced Materials Research,2013,659:139-142.
[7]侯娟,李志农.小波变换压缩感知在断口图像重构中的应用研究[J].南昌航空大学学报:自然科学版,2017,31(1):41-46.
[8]Mallat S.Geometrical grouplets[J].Applied and Computational Harmonic Analysis,2009,26(2):161-180.
[9]梁鹏,李志农,肖尧先.循环平移Contourlet变换在金属断口图像消噪中的应用[J].兵器材料科学与工程,2011,34(4):13-16.
[10]周志宇.基于Grouplet变换的金属断口图像处理方法研究[D].南昌:南昌航空大学,2013:9-73.
[11]Tang J,Huang L.Feature extraction of partial discharge grayscale images for identification based on multifractal spectrum using fluorescence fiber sensor[J].Optical Engineering,2014,53(5):053102.
[12]韩太坤,李志农.基于灰度共生矩阵与局部线性嵌入的金属断口图像识别方法研究[J].机械强度,2014(1):129-133.
[13]Cavalin P,Oliveira L S,Koerich A L,et al.Wood defect detection using grayscale images and an optimized feature set[C].IEEE Industrial Electronics,2006:3408-3412.
[14]吴松林,苏恩泽.基于边缘邻域形态分析的纹理视觉模式识别[J].信号处理,1995(4):312-316.
[15]Manjunath B S,Ma W Y.Texture features for browsing and retrieval of image data[J].IEEE Trans Pami,1996,18(8):837-842.
[16]Du H,Hu Q,Jiang M,et al.Two-dimensional principal component analysis based on Schatten p-norm for image feature extraction[J].Journal of Visual Communication&Image Representation,2015,32:55-62.
[17]Chen Y,Jiang H,Li C,et al.Deep feature extraction and classification of hyperspectral images based on convolutional neural networks[J].IEEE Transactions on Geoscience&Remote Sensing,2016,54(10):6232-6251.
[18]Muhammad B,Abu-Bakar A R.Face detection in profile views using fast discrete curvelet transform(FDCT)and support vector machine(SVM)[J].International Journal on Smart Sensing and Intelligent Systems,2016,27(2):118-133.
[19]Gilles J,Tran G,Osher S.2D empirical transforms.Wavelets,Ridgelets and Curvelets revisited[J].Siam Journal on Imageing Sciences,2014,7(1):157-186.
[20]陈烽.多特征空间下金属断口图像自适应识别方法的改进研究[J].世界有色金属,2016(16):61-62.
[21]李凌,黎明,鲁宇明.基于模糊灰度共生矩阵与隐马尔可夫模型的断口图像识别[J].中国图象图形学报,2010,15(9):1370-1375.
[22]颜云辉,马朋仁,曹宇光,等.金属断口图像句法模式识别与分类方法[J].中国机械工程,2004,15(3):259-262.
[23]Albukhanajer W A,Jin Y,Briffa J A.Classifier ensembles for image identification using multi-objective Pareto features[J].Neurocomputing,2017,238:316-327.
[24]Zheng X L,Zhang R,Zeng X.Elevator door protection method based on new moving image identification[J].Journal of Computational Methods in Sciences&Engineering,2015,15(4):611-623.
[25]颜云辉,杨会林,王成明.金属断口图像的非线性模式识别方法[J].东北大学学报:自然科学版,2004,25(9):884-886.
[26]Yamagiwa K,Izumi S,Sakai S.Detecting method of striation region of fatigue fracture surface using wavelet transform[J].Journal of the Society of Materials Science Japan,2004,53(3):306-312.
[27]何其贵,余春平,余丽萍.基于断口图像纹理特征提取仿真方法研究[J].计算机仿真,2011,28(9):279-282.
[28]Li C C,Yin L W,Chen D.Study on plant pest images identification based on lifting wavelet transform[J].Applied Mechanics&Materials,2014,687-691:3640-3643.
[29]Zou R B,Shi C C.A sea-sky line identification algorithem based on shearlets for infrared image[J].Advanced Materials Research,2014,846-847:1031-1035.
[30]孙熠,李志农,闫敬文.基于Grouplet熵与关联向量机的断口图像识别方法研究[J].失效分析与预防,2015,10(1):1-5.
[31]梁鹏,李志农.基于Contourlet-RVM航空构件断口图像识别方法研究[J].机械强度,2013,35(4):395-399.
[32]Xu J,Yang X H,Shao X X.A new medical image mosaic algorithm based on fuzzy sets recognition method[C].International Conference on Bioinformatics and Biomedical Technology,IEEE,2010:180-184.
[33]Chen G,Hu J,Li D,et al.Image recognition of maize diseases based on fuzzy clustering and support vector machine algorithm[J].NJAS-Wageningen Journal of Life Sciences,2012,10(1-2):433-438.
[34]汪东平,涂敏.基于深度学习的刑侦图像处理新方法[J].江西警察学院学报,2017(6):53-56.
[35]蒋子源.用深度学习技术解决图像语义分割问题[J].电子制作,2017(20):39-40.
[36]黄祥钧,邢武,李锋.基于句法模式识别的脉搏波特征信息研究[J].中国医疗器械杂志,2005,29(5):325-327.
[37]Zhou L,Wang L,Liu L,et al.Support vector machines for neuroimage analysis:Interpretation from discrimination[M].Springer International Publishing,2014:191-220.
[38]董超,田联房.最速上升关联向量机高光谱影像分类[J].光学精密工程,2012,20(6):1398-1405.
[39]Keller J M,Gray M R,Givens J A.A fuzzy K-nearest neighbor algorithm[J].IEEE Transactions on Systems Man&Cybernetics,2012,15(4):580-585.
[40]Lei Y,Zuo M J.Gear crack level identification based on weighted K,nearest neighbor classification algorithm[J].Mechanical Systems&Signal Processing,2009,23(5):1535-1547.
[41]张琳,陈燕,李桃迎,等.决策树分类算法研究[J].计算机工程,2011,37(13):66-67.
[42]史朝辉,王晓丹,赵士敏,等.改进的SVM决策树分类算法[J].空军工程大学学报:自然科学版,2006,7(2):32-35.