织物纹理的表征和自动识别的研究
|
摘要
在织物生产过程中,织物的质量控制如疵点检测、起毛起球等级评定、织物褶皱评定等是非常重要的,然而传统的检测丰要依靠人工检测,由于受人为因素影响,误检率和漏检率较高。随着计算机技术的广泛应用,织物的纹理分析开始实现自动化、智能化,其理论基础是织物纹理的数字化表征。织物图像纹理表征分析直接决定了织物组织参数和疵点自动检测等研究的应用效果。在将计算机视觉应用于纺织品的外观分析和检测方面,织物纹理表征和分析在值得进行进一步深入的研究,对数字化纺织的应用具有重要应用价值。
织物纹理属于周期性纹理,小波变换是周期性纹理图像的特征表示方法中最主要的方法之一。本文正是基于自适应小波对纹理图像进行特征提取,改善了传统小波基非自适应的缺点,从织物图像的疵点检测的角度验证了该织物纹理表征算法的可行性和有效性。
本文采用自适应小波三层分解的方法来表征纹理。首先,本文简单介绍了小波分析在机织物纹理表征上的应用及其在疵点检测方面的验证,经过比较发现自适应小波分析适合织物纹理的表征。其次,对织物图像进行预处理后,通过逼近条件寻找与织物纹理相匹配的滤波器,提出两种新的约束条件即小波系数纹理方向的波动性和灰度共生矩阵,与常用的能量和小波系数差等逼近条件相比,本文方法效果更佳。接着,关于自适应小波分解层数的确定,突破以往自适应小波单层分解,采用熵值减小程度作为分解终止信号,确定分解层数为三层。在确定了表征纹理的方法为自适应小波三层分解,以织物疵点检测为例,判断该方法的有效性。最后,将这种纹理表征的方法运用于平纹和斜纹类织物的疵点检测,对织物图像进行分解后提取特征值,通过特征值判断疵点的存在性,根据比较几种阈值分割方法,找到适合疵点二值化的方法为一维最大熵值方法。运用椭圆的方法计算目标疵点部分面积、大小、与水平方向夹角和长短轴比值,据此分析该疵点类型及大小等特征。试验结果表明本文所运用的表征织物纹理的方法是可行的,有效的。
In the fabric production process, the fabric quality control is very important, such as defect detection, pilling rating, puckering assessment, and so on. However, the traditional fabric detection mainly relied on manual testing, due to human factors, whose miss rate and fall-alarm rate were high. With the extensive application of computer technology, it begins to realize the automation and intelligence in fabric texture analysis, which is based on the digital characterization theory of fabric texture. The application effect of the research on fabric parameters and defect study of auto-detection is directly determined by analysis on characterization of the fabric image texture. As to applying computer vision to the analysis and detection of the appearance of textiles, fabric texture characterization and analysis are worth further studying which is important to the application of digital textile.
Fabric texture is periodic. Wavelet transforming is one of the most important methods to describe the periodic features. In this paper it extracts the features of texture image using adaptive wavelet, which improves the traditional non-adaptive wavelet methods. This paper verifies the feasibility and effectiveness of the characterization algorithm of fabric texture in terms of fabric defect detection.
In the paper it describes the fabric features using adaptive wavelet with the three-ply resolution. Firstly it gives a brief introduction of the application of this method in characterization of woven fabric texture and its verification in defect detection. Adaptive wavelet decomposition can be proved to be a better method in describing the characterization of fabric texture, suitable for fabric defect detection. Secondly, after the image's pre-processing, we search for the filter to match fabric texture through the approximation conditions. This paper offers two new constraint conditions, the fluctuations in the direction and gray-scale of co-occurrence matrix of wavelet coefficient texture. The method in this paper is proved better than the approximation condition about energy and scope of the wavelet coefficient. Thirdly, Breaking through the single adaptive wavelet decomposition, it shows a stop signal is the extent of some of the decrease of entropy in Approximate Image. It applies the three-ply resolution method, which is more appropriate for fabric defect detection. In the paper the method to describe the periodic features is the adaptive wavelet with the three-ply resolution, which is shown effective using defect detection. At last, this texture characterization method is applied to the defect detection of the twill fabric and the plain fabric, it shows on how to decide if the defect exists by the characteristic value. According to comparing several thresholding methods, it finds a suitable method of binarization, which is one-dimension maximum entropy. It calculates the target's area, size, the angle between the long axis and horizontal and the long axis and short axis ratio, using ellipse method. And it gives an analysis of defect characteristics, such as size and type, and so on. The result is shown feasible and effective.
织物纹理属于周期性纹理,小波变换是周期性纹理图像的特征表示方法中最主要的方法之一。本文正是基于自适应小波对纹理图像进行特征提取,改善了传统小波基非自适应的缺点,从织物图像的疵点检测的角度验证了该织物纹理表征算法的可行性和有效性。
本文采用自适应小波三层分解的方法来表征纹理。首先,本文简单介绍了小波分析在机织物纹理表征上的应用及其在疵点检测方面的验证,经过比较发现自适应小波分析适合织物纹理的表征。其次,对织物图像进行预处理后,通过逼近条件寻找与织物纹理相匹配的滤波器,提出两种新的约束条件即小波系数纹理方向的波动性和灰度共生矩阵,与常用的能量和小波系数差等逼近条件相比,本文方法效果更佳。接着,关于自适应小波分解层数的确定,突破以往自适应小波单层分解,采用熵值减小程度作为分解终止信号,确定分解层数为三层。在确定了表征纹理的方法为自适应小波三层分解,以织物疵点检测为例,判断该方法的有效性。最后,将这种纹理表征的方法运用于平纹和斜纹类织物的疵点检测,对织物图像进行分解后提取特征值,通过特征值判断疵点的存在性,根据比较几种阈值分割方法,找到适合疵点二值化的方法为一维最大熵值方法。运用椭圆的方法计算目标疵点部分面积、大小、与水平方向夹角和长短轴比值,据此分析该疵点类型及大小等特征。试验结果表明本文所运用的表征织物纹理的方法是可行的,有效的。
In the fabric production process, the fabric quality control is very important, such as defect detection, pilling rating, puckering assessment, and so on. However, the traditional fabric detection mainly relied on manual testing, due to human factors, whose miss rate and fall-alarm rate were high. With the extensive application of computer technology, it begins to realize the automation and intelligence in fabric texture analysis, which is based on the digital characterization theory of fabric texture. The application effect of the research on fabric parameters and defect study of auto-detection is directly determined by analysis on characterization of the fabric image texture. As to applying computer vision to the analysis and detection of the appearance of textiles, fabric texture characterization and analysis are worth further studying which is important to the application of digital textile.
Fabric texture is periodic. Wavelet transforming is one of the most important methods to describe the periodic features. In this paper it extracts the features of texture image using adaptive wavelet, which improves the traditional non-adaptive wavelet methods. This paper verifies the feasibility and effectiveness of the characterization algorithm of fabric texture in terms of fabric defect detection.
In the paper it describes the fabric features using adaptive wavelet with the three-ply resolution. Firstly it gives a brief introduction of the application of this method in characterization of woven fabric texture and its verification in defect detection. Adaptive wavelet decomposition can be proved to be a better method in describing the characterization of fabric texture, suitable for fabric defect detection. Secondly, after the image's pre-processing, we search for the filter to match fabric texture through the approximation conditions. This paper offers two new constraint conditions, the fluctuations in the direction and gray-scale of co-occurrence matrix of wavelet coefficient texture. The method in this paper is proved better than the approximation condition about energy and scope of the wavelet coefficient. Thirdly, Breaking through the single adaptive wavelet decomposition, it shows a stop signal is the extent of some of the decrease of entropy in Approximate Image. It applies the three-ply resolution method, which is more appropriate for fabric defect detection. In the paper the method to describe the periodic features is the adaptive wavelet with the three-ply resolution, which is shown effective using defect detection. At last, this texture characterization method is applied to the defect detection of the twill fabric and the plain fabric, it shows on how to decide if the defect exists by the characteristic value. According to comparing several thresholding methods, it finds a suitable method of binarization, which is one-dimension maximum entropy. It calculates the target's area, size, the angle between the long axis and horizontal and the long axis and short axis ratio, using ellipse method. And it gives an analysis of defect characteristics, such as size and type, and so on. The result is shown feasible and effective.
引文
[1]徐造坤.基于小波分析的机织物识别研究[D].武汉理工人学硕士学位论文.2006
[2]庄国瑜,孙悦.织物纹理计算机图像处理的多频道分解方法[J].天津工业大学学报.2001,20(3):26-28
[3]吴小清,邓中民,王芳,徐造坤.基于MATLAB的机织物密度自动检测[J].纺织科技进展.2005(6):70-74
[4]王朝莉.织物疵点检测的计算机图像分析和评定[D].青岛大学硕士学位论文.2006
[5]徐造坤,邓中民,赵燕等.基于小波变换的机织物经纬密度测量[J].武汉科技学院学报.2006,19(2):30-33
[6]沈庭芝,方子文.数字图像处理及模式识别[M].北京:北京理工大学出版社,1998.46-49
[7]Ajay Kumar,Grantham Pang.dentification of surface defects in textured materials using wavelet packets[J].IEEE Industrial Automation Research.2001:247-251
[8]刘素一,刘晶璟,章乐多.基于小波包的织物疵点检测[J].广西轻工业.2008,110(1):73-74
[9]于晓峰.基于计算机视觉的织物疵点识别方法[D].武汉理工大学硕士学位论文.2007
[10]靳华,王晓丹,赵荣椿.树型小波变换在纹理分析中的应用[J].计算机应用研究.2001(3):91-93
[11]刘建立,左保齐.织物纹理分析中小波基的选择和分解级数的确定[J].丝网.2008:37-39
[12]贺福强,王文,陈子辰.基于小波重构的皮革表面检测方法[J].仪器仪表学报(增刊).2006,6(27):316-318
[13]W.K.Wong,C.W.M.Yuen,D.D.Fan,L.K.Chan,E.H.K.Fung.Stitching defect detection and classification using wavelet transform and BP nural network[J].Expert Systems with Applications.2008:1-12
[14]Du-Ming Tsai,Bo Hsiao.Automatic surface inspection using wavelet reconstruction[J].THE JOURNAL OF THE PATTERN RECOGNITION SOCIETY.2001:1285-1305
[15]Soo Chang Kim,Tae Jin Kang.Texture classification and segmentation using wavelet packet frame and Gaussian mixture model[J].THE JOURNAL OF THE PATTERN RECOGNITION SOCIETY.2007:1207-1221
[16]M C Hu,I S Tsai.The inspection of fabric defects by using wavelet transform[J].Journal of Textile Institute.2000,91(3):420-433
[17]M C Hu,I S Tsai.Fabric inspection based on best wavelet packet bases[J].Textile Research Journal,2000,70(8):662-670
[18]谢平,周志丰.基于小波变换和信息熵的掌纹特征提取方法[J].计算机系统应用.2008, (2):105-108
[19]石智,易亮,魏恒东.图像纹理识别中最优小波基的选择[J].纺织高校基础科学学报.2007,20(4):427-431
[20]陈立君,王克奇,王辉,随鑫.术材纹理分析中小波基的选择和分解级数的确定[J].林业机械与术工设备.2007,5(35):25-27
[21]冯毅力,李汝勤.用于小波变化法自动测量机织物经纬密度[J].纺织学报.2001,22(2):30-31
[22]刘建立,基于小波分析和BP神经网络的织物疵点识别[D].苏州大学硕士论文
[23]张锐,李笑颖,李天牧.基于小波分析的图像边缘提取[J].自动化理论、技术与应用.2005(5):246-249
[24]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):83-87
[25]王肖芬,徐科军.基于小波变换的基波提取和频率测量[J].仪器仪表学报.2005,26(2):146-151
[26]Du-Ming Tsai,Cheng-Huei Chiang.Automatic band selection for wavelet reconstruction in the application of defect detection[J].Image and Vision Computing.2003:413-431
[27]樊计昌,刘明军,王夫运等.浅析小波最大分解层[J].科技导报.2008,26(10):40-42
[28]Jing Zhang,Shunichiro Oe.Method Based on Wavelet Transform and Neural Networks[J].IEEE Industrial Automation Research.1998:4595-4600
[29]Stephane G Mallat.A theory for multiresotution signal decomposition:The wavelet representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7):674-693
[30]K R Castleman.Digital image processing[J].Englewood Cliffs:Prentice Hall,1988
[31]程正兴.小波分析算法与应用[M].西安:西安交通大学出版社,1998.78-96
[32]Tianhorng C,Kuo C..Texture analysis and classification with tree-structured wavelettransform[J].IEEE Transactions on Image Processing,1993,2(4):429-441
[33]Hu M.,Tsai I..Fabric Inspection Based on Best Wavelet Packet Bases[J],Textile Res.J,2000,70(8):662-670
[34]Palmer S.,Wang X.objective Classification with of Fabric Pilling Based on the Two-Dimensional Discrete Wavelet Transform[J].Textile Res.J,2003,73(8):713-720
[35]Palmer S.,Wang X..Evaluation the Robustness of Objective Pilling Classification with Two-Dimensional Discrete Wavelet Transform[J].Textile Res.J,2004,74(2):140-145
[36]彭玉华.小波变换与工程应用[M].北京:科学出版社,2000.13-78
[37]Albert Boggess,Narcowich J..小波与傅立叶分析基础[M].北京:电子工业出版社
[38]秦前清,杨宗凯.实用小波分析[M].西安:西安电子科技大学出版社,1998.29-53
[39]刘贵忠,邸双亮小波分析及其应用[M].西安:西安电子科技大学出版社,1992.17-90
[40]Hamed Sari-Sarraf,James S Goddard Jr.Vision system for on-loom fabric inspection[J].IEEE Transactions on Industry Applications,1999,35(6):1252-1259
[41]Tianhorng C,C-C Jay Kuo.Texture analysis and classification with tree-structured wavelet transform[J].IEEE Transactions on Image Processing,1993,2(4):429-441
[42]Chang S L,Chong-Ho C,Jin Y C,et al.surface defect inspection of cold rolled strips with features based on adaptive wavelet packets[J].IEICE Transactions on Information and System,1997,E80-D(5):594-604
[43]Warren J Jasper,Stephen J Gamier,Harsh Potlapalli.Texture characterization and defect detection using adaptive wavelets[J].Optical Engineering,1996,36(11):3140-3149
[44]李立轻.基于计算机视觉的织物疵点检测自动检测研究[D].东华大学博士学位论文.2003
[45]何东健.数字图像处理[M].西安电子科技大学出版社2003.54-62
[46]孙兆林.MATLAB 6.X图像处理[M].清华大学出版社.2002.40-46
[47]张强,王正林.精通MATLAB图像处理[M].电子工业出版社.2009.51-53
[48]张德丰.MATLAB数字图像处理[M].机械工业出版社.2009.71-72
[49]Chang S L,Chong-Ho C,Jin Y C,et al.Surface defect inspection of cold rolled strips with features based on adaptive wavelet packets[J].IEICE.Transaction and System,1997,E80-D(5):594-604
[50]W J Jasper,S J Garnier,H Potlapalli.Texture characterization and defect detection using adaptive wavelets[J].Optical Engineering,1996,35(11):3140-3149
[51]乔万顺.基于时频变换的机纺织物结构分析和疵点检测[M].大连理工大学硕士学位论文.2007
[52]温智婕.图像纹理特征表示方法研究与应用[D].大连理工大学博士学位论文.2008
[53]何峰.基于自适应小波变换的机织物织物结构参数自动识别.东华大学硕士学位论文.2006
[54]苑丽红,付丽等.灰度共生矩阵提取纹理特征的实验结果分析[J].计算机应用.2009.4(29)4:19-22
[55]侯海苗,冀小平.基于灰度共生矩阵的纹理特征[J].长治学院学报.2008.10.(25)5:31-32
[56]M C Hu,I S Tsai.Fabric inspection based on best wavelet packet bases[J].Textile Research Journal,2000,70(8):662-670
[57]李强.图像分割中的阈值法研究[J].铜仁职业技术学院学报(自然科学版).2008.12.6(6):10-13
[58]肖超云,朱伟兴.基于Otsu准则及图像熵的阈值分割算法[J].计算机工程.2007.7.33(14):188-209
[59]吴谨,李娟等.基于最大熵的灰度阈值选取方法[J].武汉科技大学学报(自然科学版).2004.3.27(1):20-25
[2]庄国瑜,孙悦.织物纹理计算机图像处理的多频道分解方法[J].天津工业大学学报.2001,20(3):26-28
[3]吴小清,邓中民,王芳,徐造坤.基于MATLAB的机织物密度自动检测[J].纺织科技进展.2005(6):70-74
[4]王朝莉.织物疵点检测的计算机图像分析和评定[D].青岛大学硕士学位论文.2006
[5]徐造坤,邓中民,赵燕等.基于小波变换的机织物经纬密度测量[J].武汉科技学院学报.2006,19(2):30-33
[6]沈庭芝,方子文.数字图像处理及模式识别[M].北京:北京理工大学出版社,1998.46-49
[7]Ajay Kumar,Grantham Pang.dentification of surface defects in textured materials using wavelet packets[J].IEEE Industrial Automation Research.2001:247-251
[8]刘素一,刘晶璟,章乐多.基于小波包的织物疵点检测[J].广西轻工业.2008,110(1):73-74
[9]于晓峰.基于计算机视觉的织物疵点识别方法[D].武汉理工大学硕士学位论文.2007
[10]靳华,王晓丹,赵荣椿.树型小波变换在纹理分析中的应用[J].计算机应用研究.2001(3):91-93
[11]刘建立,左保齐.织物纹理分析中小波基的选择和分解级数的确定[J].丝网.2008:37-39
[12]贺福强,王文,陈子辰.基于小波重构的皮革表面检测方法[J].仪器仪表学报(增刊).2006,6(27):316-318
[13]W.K.Wong,C.W.M.Yuen,D.D.Fan,L.K.Chan,E.H.K.Fung.Stitching defect detection and classification using wavelet transform and BP nural network[J].Expert Systems with Applications.2008:1-12
[14]Du-Ming Tsai,Bo Hsiao.Automatic surface inspection using wavelet reconstruction[J].THE JOURNAL OF THE PATTERN RECOGNITION SOCIETY.2001:1285-1305
[15]Soo Chang Kim,Tae Jin Kang.Texture classification and segmentation using wavelet packet frame and Gaussian mixture model[J].THE JOURNAL OF THE PATTERN RECOGNITION SOCIETY.2007:1207-1221
[16]M C Hu,I S Tsai.The inspection of fabric defects by using wavelet transform[J].Journal of Textile Institute.2000,91(3):420-433
[17]M C Hu,I S Tsai.Fabric inspection based on best wavelet packet bases[J].Textile Research Journal,2000,70(8):662-670
[18]谢平,周志丰.基于小波变换和信息熵的掌纹特征提取方法[J].计算机系统应用.2008, (2):105-108
[19]石智,易亮,魏恒东.图像纹理识别中最优小波基的选择[J].纺织高校基础科学学报.2007,20(4):427-431
[20]陈立君,王克奇,王辉,随鑫.术材纹理分析中小波基的选择和分解级数的确定[J].林业机械与术工设备.2007,5(35):25-27
[21]冯毅力,李汝勤.用于小波变化法自动测量机织物经纬密度[J].纺织学报.2001,22(2):30-31
[22]刘建立,基于小波分析和BP神经网络的织物疵点识别[D].苏州大学硕士论文
[23]张锐,李笑颖,李天牧.基于小波分析的图像边缘提取[J].自动化理论、技术与应用.2005(5):246-249
[24]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):83-87
[25]王肖芬,徐科军.基于小波变换的基波提取和频率测量[J].仪器仪表学报.2005,26(2):146-151
[26]Du-Ming Tsai,Cheng-Huei Chiang.Automatic band selection for wavelet reconstruction in the application of defect detection[J].Image and Vision Computing.2003:413-431
[27]樊计昌,刘明军,王夫运等.浅析小波最大分解层[J].科技导报.2008,26(10):40-42
[28]Jing Zhang,Shunichiro Oe.Method Based on Wavelet Transform and Neural Networks[J].IEEE Industrial Automation Research.1998:4595-4600
[29]Stephane G Mallat.A theory for multiresotution signal decomposition:The wavelet representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7):674-693
[30]K R Castleman.Digital image processing[J].Englewood Cliffs:Prentice Hall,1988
[31]程正兴.小波分析算法与应用[M].西安:西安交通大学出版社,1998.78-96
[32]Tianhorng C,Kuo C..Texture analysis and classification with tree-structured wavelettransform[J].IEEE Transactions on Image Processing,1993,2(4):429-441
[33]Hu M.,Tsai I..Fabric Inspection Based on Best Wavelet Packet Bases[J],Textile Res.J,2000,70(8):662-670
[34]Palmer S.,Wang X.objective Classification with of Fabric Pilling Based on the Two-Dimensional Discrete Wavelet Transform[J].Textile Res.J,2003,73(8):713-720
[35]Palmer S.,Wang X..Evaluation the Robustness of Objective Pilling Classification with Two-Dimensional Discrete Wavelet Transform[J].Textile Res.J,2004,74(2):140-145
[36]彭玉华.小波变换与工程应用[M].北京:科学出版社,2000.13-78
[37]Albert Boggess,Narcowich J..小波与傅立叶分析基础[M].北京:电子工业出版社
[38]秦前清,杨宗凯.实用小波分析[M].西安:西安电子科技大学出版社,1998.29-53
[39]刘贵忠,邸双亮小波分析及其应用[M].西安:西安电子科技大学出版社,1992.17-90
[40]Hamed Sari-Sarraf,James S Goddard Jr.Vision system for on-loom fabric inspection[J].IEEE Transactions on Industry Applications,1999,35(6):1252-1259
[41]Tianhorng C,C-C Jay Kuo.Texture analysis and classification with tree-structured wavelet transform[J].IEEE Transactions on Image Processing,1993,2(4):429-441
[42]Chang S L,Chong-Ho C,Jin Y C,et al.surface defect inspection of cold rolled strips with features based on adaptive wavelet packets[J].IEICE Transactions on Information and System,1997,E80-D(5):594-604
[43]Warren J Jasper,Stephen J Gamier,Harsh Potlapalli.Texture characterization and defect detection using adaptive wavelets[J].Optical Engineering,1996,36(11):3140-3149
[44]李立轻.基于计算机视觉的织物疵点检测自动检测研究[D].东华大学博士学位论文.2003
[45]何东健.数字图像处理[M].西安电子科技大学出版社2003.54-62
[46]孙兆林.MATLAB 6.X图像处理[M].清华大学出版社.2002.40-46
[47]张强,王正林.精通MATLAB图像处理[M].电子工业出版社.2009.51-53
[48]张德丰.MATLAB数字图像处理[M].机械工业出版社.2009.71-72
[49]Chang S L,Chong-Ho C,Jin Y C,et al.Surface defect inspection of cold rolled strips with features based on adaptive wavelet packets[J].IEICE.Transaction and System,1997,E80-D(5):594-604
[50]W J Jasper,S J Garnier,H Potlapalli.Texture characterization and defect detection using adaptive wavelets[J].Optical Engineering,1996,35(11):3140-3149
[51]乔万顺.基于时频变换的机纺织物结构分析和疵点检测[M].大连理工大学硕士学位论文.2007
[52]温智婕.图像纹理特征表示方法研究与应用[D].大连理工大学博士学位论文.2008
[53]何峰.基于自适应小波变换的机织物织物结构参数自动识别.东华大学硕士学位论文.2006
[54]苑丽红,付丽等.灰度共生矩阵提取纹理特征的实验结果分析[J].计算机应用.2009.4(29)4:19-22
[55]侯海苗,冀小平.基于灰度共生矩阵的纹理特征[J].长治学院学报.2008.10.(25)5:31-32
[56]M C Hu,I S Tsai.Fabric inspection based on best wavelet packet bases[J].Textile Research Journal,2000,70(8):662-670
[57]李强.图像分割中的阈值法研究[J].铜仁职业技术学院学报(自然科学版).2008.12.6(6):10-13
[58]肖超云,朱伟兴.基于Otsu准则及图像熵的阈值分割算法[J].计算机工程.2007.7.33(14):188-209
[59]吴谨,李娟等.基于最大熵的灰度阈值选取方法[J].武汉科技大学学报(自然科学版).2004.3.27(1):20-25