基于Matrox图像处理卡的帘子布疵点在线检测系统的研究与设计
|
摘要
本课题的研究目的是实现基于图像处理卡的帘子布疵点检测硬件平台,并探索快速、准确的在线帘子布疵点检测算法。帘子布具有幅宽大,运动速度快且变动剧烈的特点,因此对其进行清晰、稳定的图像采集难度较大,这也是该类机器视觉系统的一个关键问题。该系统的硬件设计分为三个部分:一、光学成像系统,包括线阵相机,镜头及光源。二、运动同步系统,包括编码器,分频器。该子系统要求能准确地检测帘子布的运动速度,精确控制线阵相机的同步采集。三,图像获取系统,包括图像采集卡及计算机。本文根据系统的设计要求,对该系统进行了硬件选型及参数计算,对运动同步系统进行了软硬件设计,并在VC平台下,利用MIL库编写了图像采集程序。该图像采集系统已在现场安装并完成调试。实验结果表明,该系统能够在工业现场进行高质量的,稳定的帘子布图像采集。
在快速判断帘子布有无疵点方面,本文比较了基于灰度直方图和基于灰度双阈值的判断方法。其中基于直方图检测的方法是比较基本的方法,由于其本身的缺陷,在误检率上还不太满足系统的要求;基于灰度双阈值的方法是根据帘子布的纹理结构特性,选取大量正常图像的最大灰度值和最小灰度值做为此方法的双阈值,通过区域对比和纵向结合的方法判断图像的灰度是否有异常。在最大灰度值和最小灰度值两个阈值的约束下,能准确快速检测出疵点,所以更加适合快速判断有无疵点的检测。
This study aims to build an online cord fabric’s defect detection hardware platform based on image processing board, and explore real time defect detection methods with high accuracy. The challenge of acquiring high quality images in this kind of system comes from the large width of the cord fabric and the movement velocity which is high and varies in a large extent. The hardware platform is subdivided into three parts: first, the optical imaging subsystem including the line camera, lens and lamp-house; second, motion synchronization subsystem composed of an encoder and the frequency division controller, in which accurate speed measurement of the cord fabric is implemented in order to synchronize the acquisition frequency of the line camera; third, the image acquisition subsystem composed of image processing board and PC. In this paper, hardware is elaborately selected and their parameters are calculated subsequently. Implementation of the motion synchronization subsystem, both hardware and software, is conducted. By aid of the MIL library, an image acquisition program is realized in Visual Studio. The whole image acquisition system has been installed and adjusted in the field. Experiments approve that our system can obtain images with high quality stably in practice.
For quickly judging whether the cord fabric has defects, methods based on histogram and two thresholds in grayscale are compared. Of which based on the histogram detection method is a more basic way, because of its own shortcomings, in the false detection rate is not yet meet the requirements of the system. According to the structural characteristics of texture cord fabric, the method based on grayscale double thresholds selects a large number of maximum grayscale values and minimum grayscale values in normal image as this method’s double thresholds, and then comparing with regional and longitudinal, to judge whether there is abnormity in grayscale. Under the constraints between maximum values and minimum values, it can accurately detect defects quickly, so it is more suitable for quick judgment.
在快速判断帘子布有无疵点方面,本文比较了基于灰度直方图和基于灰度双阈值的判断方法。其中基于直方图检测的方法是比较基本的方法,由于其本身的缺陷,在误检率上还不太满足系统的要求;基于灰度双阈值的方法是根据帘子布的纹理结构特性,选取大量正常图像的最大灰度值和最小灰度值做为此方法的双阈值,通过区域对比和纵向结合的方法判断图像的灰度是否有异常。在最大灰度值和最小灰度值两个阈值的约束下,能准确快速检测出疵点,所以更加适合快速判断有无疵点的检测。
This study aims to build an online cord fabric’s defect detection hardware platform based on image processing board, and explore real time defect detection methods with high accuracy. The challenge of acquiring high quality images in this kind of system comes from the large width of the cord fabric and the movement velocity which is high and varies in a large extent. The hardware platform is subdivided into three parts: first, the optical imaging subsystem including the line camera, lens and lamp-house; second, motion synchronization subsystem composed of an encoder and the frequency division controller, in which accurate speed measurement of the cord fabric is implemented in order to synchronize the acquisition frequency of the line camera; third, the image acquisition subsystem composed of image processing board and PC. In this paper, hardware is elaborately selected and their parameters are calculated subsequently. Implementation of the motion synchronization subsystem, both hardware and software, is conducted. By aid of the MIL library, an image acquisition program is realized in Visual Studio. The whole image acquisition system has been installed and adjusted in the field. Experiments approve that our system can obtain images with high quality stably in practice.
For quickly judging whether the cord fabric has defects, methods based on histogram and two thresholds in grayscale are compared. Of which based on the histogram detection method is a more basic way, because of its own shortcomings, in the false detection rate is not yet meet the requirements of the system. According to the structural characteristics of texture cord fabric, the method based on grayscale double thresholds selects a large number of maximum grayscale values and minimum grayscale values in normal image as this method’s double thresholds, and then comparing with regional and longitudinal, to judge whether there is abnormity in grayscale. Under the constraints between maximum values and minimum values, it can accurately detect defects quickly, so it is more suitable for quick judgment.
引文
[1]刘波,高强.我国锦纶帘子布市场现状及展望[J ].中国橡胶,2008,24(15):16-18.
[2] GB/T 9102-2002.锦纶66帘子布国家标准[S].北京:国家质量监督检验检疫总局,2002.
[3]黄彬.影响锦纶6浸胶帘子布加工性能的外观质量因素[J].合成纤维工业,1998,21(4):44-46.
[4] Hamed Sari-Sarraf, James S.Goddard.Vision System for On-Loom Fabric Inspection[J]. IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 1999,35(6):287-290.
[5]何志贵. I-TEX000型织物自动检验系统[J].国外纺织技术,2000, (12).
[6]马骏,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(综合版) 2004, (1).
[7]王培峰.利用神经网络技木的验布系统[J].棉纺织技术,2004,32(l).
[8]李立轻,黄秀宝.图像处理用于织物疵点自动检测的研究进展[J].东华大学学报, 2002.8, 28(4):118-122.
[9] www.evs-sm.com
[10] http://www.barco.com.
[11] II.Schmalfub, K.I-Schinner,俞雯译,自动在线织物检验[J],国际纺织导报,1999, 3:52-56.
[12]瑞士Zell weger Uster公司Rudof Meier,Rolf Leuenberger.Uster公司的织物质量自动检测检验系统[J].纺织导报,1999,(2):41-42.
[13]何志贵. EVS公司的I-T ex2000型织物自动检验系统[J].国外纺织技术,2001, (10):40-41.
[14] Conci A. Proenca C.B. A Fractal image analysis system for fabric inspection based on a box-counting method[J]. Computer Networks and ISDN Systems, 1998,30 (20-21):1887-1895.
[15] Sari-Sarmf H,GoddardC J S. Vision system for on-loom fabric inspection[J]. IEEE Trans Ind Applicat,1999,35:1252-1259.
[16]梁金祥编译,左保齐校.基于计算机视觉的织物疵点检测[J].国外丝绸,2009,(5):32-36.
[17]邹超,汪秉文,孙志刚.基于机器视觉的织物疵点检测方法综述[J].天津工业大学学报,2009,28(2):78-82.
[18] Balakrishnan H,Venkataraman S,Jayaraman& FDICS.A Vision-Based System for the Identification and Classification of Fabric Defects[J]. Journal of the Textile Institute,1998,89(2):365-380.
[19] Kuo Chung-Fetag Jerrrey. Gray relational analysis for recognizing fabric defects[J].Textile Research Journal,2003,73(5):461-465.
[20] Gareia M A,Puig D. Pixel clasification by divergence-based integration of multiple texture methods and its application to fabric defect detection[J]. Pattern Recognition, 25th DAGM Symposium,Magdeburg,Germany,Proceedings,2003,2781:132-139.
[21]高士忠,卢易枫,蔡振伟等.基于灰度共生矩阵的帘子布疵点检测研究[J].电子技术应用,2008,34(1):117-119.
[22] Stojanovic R,tropulos P,Koulamas C,eta1. Real-time visiorrbased system for textile fabric inspection[J]. Real-Time Imaging,2001,7(6):507-518.
[23] CEM Baykal I,JULLIEN G A.In-camera detection of fabric defects[C].International Symposium on circuits and systems.New York:IEEE Press,2004:933—936.
[24]王学文,邓中民,严平.基于小波分析与纹理能量变换的织物疵点检测[J].棉纺织技术,2007,35(10):9-12.
[25]卿湘运,段红,魏俊民,王璐娟.一种新的基于小波分析与神经网络的织物疵点检测与识别方法[J].仪器仪表学报,2006,26(6):618-622.
[26]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):15-19.
[27]严平,邓中民,刘童花.基于改进的小波分解织物疵点检测[J].2007,(4):46-47.
[28]李立轻,黄秀宝.基于织物自适应正交小波的疵点检测[J].东华大学学报自然科学版,2001, 27 (4):82-87.
[29]祝双武,郝重阳,齐华.织物疵点检测中自适应正交小波基的构造[J].西安工程可以学院学报,2007,21(2):212-215.
[30] CHETVERIKOV Dmitry.Pattern regularity as a visual key[J].Image and Vision Computing,2000,18(12):975-985.
[31] CHETVERIKOV Dmitry,HANBURY A.Finding defects in texture using regularity and local orientation[J].Pattern Recognition,2002,35:203-218.
[32] Hu M C, Tsai I S.Fabric Inspection Based on Best Wavelet Packet Bases[J].Textile Research Journal,2000,70(8):662-670.
[33] Kumar A,Pang Grantham K H.Identification of surface defects in textured materialsusing wavelet packets[J].Proc.36th IEEEIAS Annu.Meeting,vol.1 Chicago, IL, 2001: 247-251.
[34] Casasent D,Smokelin J S. Real,Imaginary,and Clutter. Gabor filter fusion for detection with reduced false alarms[J]. Opt Eng,1994,33(7):2255-2363.
[35] Kumar A, Pang G K H. Defect detection in textured materials using Gabor filters[J].IEEE Transactions on Industry Applications,2002,38(2):425-440.
[36] Kumar A,Pang G K H.Fabric defect segmenmtion using multichannel blob detectors[J].Optical Engineering, 2000,39(12):3176-3190.
[37]韩润萍,孙苏榕,姜玲.基于Gabor滤波器组的织物疵点检测方法[J].计算机工程与应用. 2007,43(7):211-214.
[38]宋寅卯,袁端磊.基于最优Gabor滤波器的织物缺陷检测[J].中国图象图形学报. 2006,11(7):954-958.
[39]屈博,卢朝阳,李静,崔玲玲,周峰江.一种改进的多通道Gabor滤波器布匹瑕疵检测方法[J].纺织学报.2009,30(12):37-40
[40] J.R.Coaton, A.M.Marsden.光源与照明[M].上海:复旦大学出版社,2000
[41]邵思杰.织物疵点的自动检测[D].上海:中国纺织大学,2000.
[42] YF3528 technical data[EB/OL], http://www.mvlz.com/.
[43] Basler L803K User’s Manual[EB/OL], http :/ /www. basler. com.
[44] Matrox Odyssey Installation and Hardware Reference [EB/OL], http: / /www. matrox.Com.
[45]陈迎娟,张之江,张智强.CCD像素响应不均匀性的校正方法[J].光学精密工程,2004,12(2):216-219.
[46]孟然,于德敏,王永强,许增朴.黑白CCD相机平场影响因素分析及校正方法研究[J].天津科技大学学报,2006,21(4):68-70,74.
[47]程万胜,赵杰,蔡鹤皋.CCD像素响应非均匀的校正方法[J].光学精密工程,2006,16(2):314-318.
[48]徐树兴,王宝光,郑义忠.线阵CCD平场校正及FPGA实现的研究[J].宇航计测技术,2007,27(6):24-37.
[49]张之江,邹宾,陈迎娟.CCD亚像素细分中的像素响应不均匀性补偿技术[J].传感技术学报,2005,18(1):57-62.
[50]严军,陈迎娟.基于光电响应模型的CCD像素响应不均匀性校正方法[J].宇航计测技术,2004,24(6):20-25.
[51]段文亮,朱瑞丽,常梅英.锦纶-66与锦纶-6帘子线应用于轮胎中特性体现[J].河南纺织高等专科学校学报,2001(1):6-8.
[52]郭怡,李辉,华演.对浸胶帘子布产生胶皮胶末问题的探讨[J]. 2003,21(6):30-32.
[53]潘清江.浸胶帘子布胶斑的产生原因及解决办法[J].中国橡胶,2009,25(14):35-37.
[54]朱泽贺,刘黎,王韦伟.锦纶6帘子布“泡泡纱”产生的原因及解决办法[J].中国橡胶,1999(14):25-26.
[55]徐莉芹,晋丽.帘子布缺纬疵点原因及预防探讨[J].江苏纺织,2009(6):47-48.
[56] M.Schael and H.Burkhard. Automatic detection of errors on textures using invariant grey scale features and polynomial classifiers [J]. Texture Analysis in Machine Vision, volume 40 of Machine Perception and Artificial Intelligence.World Scientific,2000:219-230.
[2] GB/T 9102-2002.锦纶66帘子布国家标准[S].北京:国家质量监督检验检疫总局,2002.
[3]黄彬.影响锦纶6浸胶帘子布加工性能的外观质量因素[J].合成纤维工业,1998,21(4):44-46.
[4] Hamed Sari-Sarraf, James S.Goddard.Vision System for On-Loom Fabric Inspection[J]. IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 1999,35(6):287-290.
[5]何志贵. I-TEX000型织物自动检验系统[J].国外纺织技术,2000, (12).
[6]马骏,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(综合版) 2004, (1).
[7]王培峰.利用神经网络技木的验布系统[J].棉纺织技术,2004,32(l).
[8]李立轻,黄秀宝.图像处理用于织物疵点自动检测的研究进展[J].东华大学学报, 2002.8, 28(4):118-122.
[9] www.evs-sm.com
[10] http://www.barco.com.
[11] II.Schmalfub, K.I-Schinner,俞雯译,自动在线织物检验[J],国际纺织导报,1999, 3:52-56.
[12]瑞士Zell weger Uster公司Rudof Meier,Rolf Leuenberger.Uster公司的织物质量自动检测检验系统[J].纺织导报,1999,(2):41-42.
[13]何志贵. EVS公司的I-T ex2000型织物自动检验系统[J].国外纺织技术,2001, (10):40-41.
[14] Conci A. Proenca C.B. A Fractal image analysis system for fabric inspection based on a box-counting method[J]. Computer Networks and ISDN Systems, 1998,30 (20-21):1887-1895.
[15] Sari-Sarmf H,GoddardC J S. Vision system for on-loom fabric inspection[J]. IEEE Trans Ind Applicat,1999,35:1252-1259.
[16]梁金祥编译,左保齐校.基于计算机视觉的织物疵点检测[J].国外丝绸,2009,(5):32-36.
[17]邹超,汪秉文,孙志刚.基于机器视觉的织物疵点检测方法综述[J].天津工业大学学报,2009,28(2):78-82.
[18] Balakrishnan H,Venkataraman S,Jayaraman& FDICS.A Vision-Based System for the Identification and Classification of Fabric Defects[J]. Journal of the Textile Institute,1998,89(2):365-380.
[19] Kuo Chung-Fetag Jerrrey. Gray relational analysis for recognizing fabric defects[J].Textile Research Journal,2003,73(5):461-465.
[20] Gareia M A,Puig D. Pixel clasification by divergence-based integration of multiple texture methods and its application to fabric defect detection[J]. Pattern Recognition, 25th DAGM Symposium,Magdeburg,Germany,Proceedings,2003,2781:132-139.
[21]高士忠,卢易枫,蔡振伟等.基于灰度共生矩阵的帘子布疵点检测研究[J].电子技术应用,2008,34(1):117-119.
[22] Stojanovic R,tropulos P,Koulamas C,eta1. Real-time visiorrbased system for textile fabric inspection[J]. Real-Time Imaging,2001,7(6):507-518.
[23] CEM Baykal I,JULLIEN G A.In-camera detection of fabric defects[C].International Symposium on circuits and systems.New York:IEEE Press,2004:933—936.
[24]王学文,邓中民,严平.基于小波分析与纹理能量变换的织物疵点检测[J].棉纺织技术,2007,35(10):9-12.
[25]卿湘运,段红,魏俊民,王璐娟.一种新的基于小波分析与神经网络的织物疵点检测与识别方法[J].仪器仪表学报,2006,26(6):618-622.
[26]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):15-19.
[27]严平,邓中民,刘童花.基于改进的小波分解织物疵点检测[J].2007,(4):46-47.
[28]李立轻,黄秀宝.基于织物自适应正交小波的疵点检测[J].东华大学学报自然科学版,2001, 27 (4):82-87.
[29]祝双武,郝重阳,齐华.织物疵点检测中自适应正交小波基的构造[J].西安工程可以学院学报,2007,21(2):212-215.
[30] CHETVERIKOV Dmitry.Pattern regularity as a visual key[J].Image and Vision Computing,2000,18(12):975-985.
[31] CHETVERIKOV Dmitry,HANBURY A.Finding defects in texture using regularity and local orientation[J].Pattern Recognition,2002,35:203-218.
[32] Hu M C, Tsai I S.Fabric Inspection Based on Best Wavelet Packet Bases[J].Textile Research Journal,2000,70(8):662-670.
[33] Kumar A,Pang Grantham K H.Identification of surface defects in textured materialsusing wavelet packets[J].Proc.36th IEEEIAS Annu.Meeting,vol.1 Chicago, IL, 2001: 247-251.
[34] Casasent D,Smokelin J S. Real,Imaginary,and Clutter. Gabor filter fusion for detection with reduced false alarms[J]. Opt Eng,1994,33(7):2255-2363.
[35] Kumar A, Pang G K H. Defect detection in textured materials using Gabor filters[J].IEEE Transactions on Industry Applications,2002,38(2):425-440.
[36] Kumar A,Pang G K H.Fabric defect segmenmtion using multichannel blob detectors[J].Optical Engineering, 2000,39(12):3176-3190.
[37]韩润萍,孙苏榕,姜玲.基于Gabor滤波器组的织物疵点检测方法[J].计算机工程与应用. 2007,43(7):211-214.
[38]宋寅卯,袁端磊.基于最优Gabor滤波器的织物缺陷检测[J].中国图象图形学报. 2006,11(7):954-958.
[39]屈博,卢朝阳,李静,崔玲玲,周峰江.一种改进的多通道Gabor滤波器布匹瑕疵检测方法[J].纺织学报.2009,30(12):37-40
[40] J.R.Coaton, A.M.Marsden.光源与照明[M].上海:复旦大学出版社,2000
[41]邵思杰.织物疵点的自动检测[D].上海:中国纺织大学,2000.
[42] YF3528 technical data[EB/OL], http://www.mvlz.com/.
[43] Basler L803K User’s Manual[EB/OL], http :/ /www. basler. com.
[44] Matrox Odyssey Installation and Hardware Reference [EB/OL], http: / /www. matrox.Com.
[45]陈迎娟,张之江,张智强.CCD像素响应不均匀性的校正方法[J].光学精密工程,2004,12(2):216-219.
[46]孟然,于德敏,王永强,许增朴.黑白CCD相机平场影响因素分析及校正方法研究[J].天津科技大学学报,2006,21(4):68-70,74.
[47]程万胜,赵杰,蔡鹤皋.CCD像素响应非均匀的校正方法[J].光学精密工程,2006,16(2):314-318.
[48]徐树兴,王宝光,郑义忠.线阵CCD平场校正及FPGA实现的研究[J].宇航计测技术,2007,27(6):24-37.
[49]张之江,邹宾,陈迎娟.CCD亚像素细分中的像素响应不均匀性补偿技术[J].传感技术学报,2005,18(1):57-62.
[50]严军,陈迎娟.基于光电响应模型的CCD像素响应不均匀性校正方法[J].宇航计测技术,2004,24(6):20-25.
[51]段文亮,朱瑞丽,常梅英.锦纶-66与锦纶-6帘子线应用于轮胎中特性体现[J].河南纺织高等专科学校学报,2001(1):6-8.
[52]郭怡,李辉,华演.对浸胶帘子布产生胶皮胶末问题的探讨[J]. 2003,21(6):30-32.
[53]潘清江.浸胶帘子布胶斑的产生原因及解决办法[J].中国橡胶,2009,25(14):35-37.
[54]朱泽贺,刘黎,王韦伟.锦纶6帘子布“泡泡纱”产生的原因及解决办法[J].中国橡胶,1999(14):25-26.
[55]徐莉芹,晋丽.帘子布缺纬疵点原因及预防探讨[J].江苏纺织,2009(6):47-48.
[56] M.Schael and H.Burkhard. Automatic detection of errors on textures using invariant grey scale features and polynomial classifiers [J]. Texture Analysis in Machine Vision, volume 40 of Machine Perception and Artificial Intelligence.World Scientific,2000:219-230.