用户名: 密码: 验证码:
织物疵点检测的计算机图像分析和评定
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
本文借助MATLAB编程语言,利用数字图像处理技术和人工神经网络技术对织物疵点的自动识别进行了系统的研究,提出了一种基于图像处理的、以人工神经网络技术来实现分类的织物疵点计算机识别的新方法,并对这一方法的可行性进行了验证。
     借助于MATLAB的图像处理、小波分析、人工神经网络三大工具箱,通过大量的实验比较和验证,找到了有利于疵点分析的图像处理方法,最优的疵点特征参数的提取,高效而准确的疵点识别模式,将整个图像处理流程系统化,并使其能够有效地兼顾不同种类的疵点图像,形成了一套包括织物疵点图像的预处理、二值分割、分割后处理、疵点部分特征提取、神经网络识别这五个关键环节的、完整的织物疵点自动识别系统。并对其识别能力进行了实验评估,证明了所建立的识别系统,对于简单织物组织的坯布图像,在光影、底色相近的条件下,在经疵、纬疵、区域、破洞四类疵点分类上做到了识别快速、准确。
     图像处理程序实现过程中,舍弃了获得精确尺寸的意图,着眼于疵点类别的快速、准确分类,做了一些大胆假设。实验证明,所做的假设基本符合实际,可以大大改善识别效果、简化识别算法,且对疵点的个数确定、种类识别和定位无影响。
In this thesis, recurring to MATLAB, the detection of fabric defects using digital image processing and neural network technique is studied. A new way of detecting fabric detects which based on image processing and accomplish detect classification by means of neural network is put forward. Furthermore, the feasibility of this way is testified.Recurring to three MATLAB toolbox: image processing toolbox, wavelet toolbox, neural network toolbox, by a mass of experimental comparisons and validations, the image processing methods which applies to detect analysis, the best feature extraction of fabric detects and the efficient and exact detect recognition pattern are found; the systematization of the whole image processing flow is achieved for coping with the different kinds of detects in image processing, accordingly, a integrated system recognizing detects automatically which consists of five key steps: image preprocessing of fabric images with detects, two-value image segmentation, image processing after segmenting, feature extraction of fabric detects and the recognition and classification of fabric detects by means of neural network model is formed. The experimental evaluation of this system is also made and it is testified that this system can quickly and exactly recognize detects in in-gray images which have simple fabric weaves to one of four classes: warp direction detects, weft direction defects, regional defects and discrete defects when the lightness and grounding color are similar.In the process of achieving image processing, the intent of getting the exact sizes of detects is discarded and some important hypotheses are made to classify detects quickly and precisely. And it is testified that these hypotheses according with the fact basically can improve effect and simplify arithmetic greatly and do not counteract classifying , orientating and getting the number of detects.
引文
[1] 宋湛华.图像信息处理技术在纺织行业应用中的前景[J].纺织导报,2001,No.5:149-150.
    [2] 李立轻,黄秀宝.图像处理刚于织物疵点自动检测的研究进展[J].东华大学学报(自然科学版),2002,28(4):118-121.
    [3] 马昀,仲岑然.织物自动检验系统的发展与应用[J].南通纺织职业技术学院学报,2004,(1)
    [4] 王培峰.利用神经网络技术的验布系统[J].棉纺织技术,2004,32(1)
    [5] 何志贵.I-TEX2000型织物自动检验系统[J].国外纺织技术,2000,(12)
    [6] 王家文,曹宇.MATLAB6.5图形图像处理[M].北京:国防工业出版社,2004.
    [7] 飞思科技产品研发中心.MATLAB6.5辅助小波分析与应用[M].北京:电子工业出版社,2003.
    [8] 董长虹,高志,余啸海.Matlab小波分析工具箱原理与应用[M].北京:国防工业出版社,2004.
    [9] 余成波.数字图像处理及MATLAB实现[M].重庆大学出版社,2003.
    [10] 董长虹,赖志国,余啸海.Matlab图像处理与应用[M].北京:国防工业出版社,2004.
    [11] 阮秋琦等译.数字图像处理[M].北京:电子工业出版社,2005.
    [12] 陈传波,金先级.数字图像处理[M].北京:机械工业出版社,2004.
    [13] 李国勇.智能控制及其MATLAB实现[M].北京:电子工业出版社,2005.
    [14] 徐晓峰,段红,魏俊民.基于二维小波变换和BP神经网络的织物疵点检测方法.浙江工程学院学报.2004;21(1):15-19.
    [15] 张瑞林,徐秩峰.基于PCNN的织物疵点识别研究.纺织学报.2004,25(6):69-71.
    [16] 刘曙光,屈萍鸽.基于小波包的织物纹理分类.纺织学报.2004;25(4):47-48.
    [17] T.J.Kang等著,赵其明译.基于图像处理和神经网络的原棉杂质及颜色的客观评定.国外纺织技术.2003;1:37-42.
    [18] 成玲,万振凯,臧海英.基于神经网络的织物风格识别系统探讨.纺织学报.2002;23(3):69-70.
    [19] 杨晓波,黄秀宝.基于BP神经网络的织物折皱等级评定.东华大学学报.2003;29(4):68-71.
    [20] 梅兴波,顾伯洪.BP神经网络预测织物拉伸性能.东华大学学报.2001;27(3):64-67.
    [21] 景晓军,李剑锋等.图像智能化的目标检测技术(Ⅱ)——数据流程与背景感知.2003,6,17-26.
    [22] 王茜蓓,彭中,刘莉.一种基于自适应阈值的图像分割算法.背景理工大学学报.2003,23(4) 521:524.
    [23] 章毓晋.图像处理和分析[M].北京:清华大学出版社,1999
    [24] 龚炜等.数字空间中数学形态学——理论及应用[M].北京:科学出版社,1997
    [25] 贾永红.计算机图像处理与分析[M].武昌,武汉大学出版社,2001
    [26] 张爱华,余胜生,周敬利.一种基于边缘检测的局部阈值分割算法.小型微型计算机系统.2003,24(4)661,663.
    [27] 郭春秋,欧阳松.一种快速、准确的图像阈值分割新方法.湖南工业职业技术学院学报.2003,4(1)9-11.
    [28] 张文琴,狄红卫.一种基于小波和形态学的边缘检测方法.暨南大学学报.2004,25(5)585:589.
    [29] 李忠杰,杨关良,徐小杰.自动阈值选取与边缘检测相结合的图像分割算法.2002,14(4) 88:91.
    [30] Y. F. Zhang and R. R. Bresee, Fabric Defect Detection and Classification Using Image Analysis[J], Textile Res. J., 1995, 65(1): 1-9
    [31] I-Shou Tsai and Ming-Chuan Hu, Automatic Inspection of Fabric Defects Using an Artificial Neural Network Technique[J], Textile Res. J., 1996, 66(7): 174-182
    [32] Chang-Chiun Huang and I-Chun Chen. Neural-Fuzzy Classification for Fabric Defects[J]. Textile Res. J., 2001, 71(3):220-224
    [33] Brrhika Mallik-Goswami and Asit K. Datta, Detecting Defects Using in fabric with Laser-Based Morphological Image Processing[J],Textile Res. J., 2000, 70(9):758-762
    [34] M. C. Hu and I. S. Tsai. Fabric Inspection Based on Best Wavelet Packet Bases [J]. Textile Res. J., 2000, 70(8):662-670
    [35] Chung-Feng Jeffrey Kuo et al, A Back-Propagation Network for Recognizing Fabric Defects. Textile Research Journal. 2003; (2): 147-151.
    [36] Yau-Ren Shiau, I-Shou Tsai, and Chih-Shiang Lin. Classifying Web Defects with a Back-Propagation Neural Network by Color Image Processing[J] Textile Res. J., 2000, 70(7):633-640
    [37] Hyung Taek Choi, Sung Moon Jeong, etc. Detecting Fabric Defects with Computer Vision and Fuzzy Rule Generaton Part Ⅱ: Defect Identification by a Fuzzy Exper System[J]. Textile Res. J., 2001, 71(7):563-573
    [38] Rajasekaran S. Trainning-free counter propagation neural network for pattern recognition of fabric defects. Textile Research Journal, 1997; 67(6): 401-405
    [39] F.H.She,S. Chow, B. Wang, L.X. Kong. Identification and classification of animal fibres using artificial neural networks. Journal of the Textile Machinery Society of Japan. 2001; 47(2): 35-38.
    [40] CHUNG-FENG JEFFREY KUO, CHING-JENG LEE, CHENG-CHIH TSAI. Using a Neural Network to Identify Fabric Defects in Dynamic Cloth Inspection. TEXTILE RESEARCH JOURNAL. 2003; 73(3): 238-244.
    [41] 饶海涛,翁桂荣.基于数学形态学的图像边缘检测.苏州大学学报.2004,20(2)42:45.
    [42] 王乐佳,王欣.基于双Haar小波的边缘检测.山东大学学报.2004,34(2)35:37.
    [43] 努尔顿,左保齐.织物疵点检测与神经网络技术.江苏丝绸.2003;3:5-7.
    [44] 徐增波,贡玉南等.基于二维连续小波变换的织物疵点检测[J].中国纺织大学学报,2000,26(2)
    [45] 汪成龙,李晶,高晓丁.高效能的织物疵点识别算法及其实现棉纺织技术.2004;32(6)23-26.
    [46] 韩武鹏,陈文楷,刘正耀.纺织品检测中的模式识别应用.控制理论与应用.2003;20(3):391-393.
    [47] 余序芬,吴兆平.数学形态学边缘检测法将其对棉麻自动识别的应用[J].中国纺织大学学报,1996,22(5):66-72
    [48] 贡玉南,唐予远,张明.织物疵点的自动检测方法[J].郑州纺织工学院学报,1997,(6):21~24
    [49] 李立轻,黄秀宝.用于疵点检测的织物自适应正交小波的实现[J].东华大学学报.2002,28(2):77—81
    [50] 李立轻,王文淑.Wiener滤波器分解织物图像在织物疵点自动检测中的应用[J].河北科技大学学报,2002,23(1):32—37
    [51] 徐大诚.基于小波变换的图像处理技术的应用[J].苏州大学学报,2002,18(1):45—48
    [52] 费佩燕,刘曙光,屈平鸽.基于二进小波的图像去噪技术[J].纺织高校基础科学学报,2003,16(2):170-174
    [53] 徐晓峰,段红,魏俊民.基于二维小波变换和BP神经网络的织物疵点检测方法[J].浙江工程学院学报.2004,21(1):17—19
    [54] 纺织品机织物疵点术语.中华人民共和国纺织行业标准.FZ 01018—92

© 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