几种织物疵点检测算法的设计与比较
|
摘要
在研究相关文献内容的基础上,选取目前织物疵点自动检测中3种常用的特征提取算法,基于Hough变换和Gabor滤波的检测算法、基于频域筛状滤波器的检测算法和基于灰度共生矩阵法的检测算法,简要介绍了3种检测算法的设计原理和实现步骤。基于相同的硬件、软件环境,分别使用3种检测算法对几种常见的织物疵点进行测试。最后通过对时效性、检测效果等进行比较分析,3种检测算法对于纹理性、非纹理性等不同的疵点具有不同的优缺点。
Based on the research of related literatures, this paper analyzes three commonly used feature extraction algorithms in automatic fabric defect detection in the current research. The detection algorithms include Hough transformation and Gabor filter, the frequency domain sieve-like filter and gray level co-occurrence matrix. Firstly, the design principles and the implementation steps of the three algorithms are briefly introduced. Then, based on the same hardware and software environment, the three detection algorithms are used for several common defects respectively. Finally, this paper analyzes the comparative results of the three algorithms in terms of timeliness and detection effects. Three algorithms have different advantages and disadvantages for texture, non-textured of different defects.
Based on the research of related literatures, this paper analyzes three commonly used feature extraction algorithms in automatic fabric defect detection in the current research. The detection algorithms include Hough transformation and Gabor filter, the frequency domain sieve-like filter and gray level co-occurrence matrix. Firstly, the design principles and the implementation steps of the three algorithms are briefly introduced. Then, based on the same hardware and software environment, the three detection algorithms are used for several common defects respectively. Finally, this paper analyzes the comparative results of the three algorithms in terms of timeliness and detection effects. Three algorithms have different advantages and disadvantages for texture, non-textured of different defects.
引文
[1]Anagnostopoulos C,Vergados D,Kayafas E,et al.A computer vision approach for textile quality control[J].The Journal of Visualization and Computer Animation,2001,12(1):31-44.
[2]Rohrmus D R.Invariant and adaptive geometrical texture features for defect detection and classification[J].Pattern Recognition,2005,38:1546-1559.
[3]李冠志,万贤福,汪军,等.基于机器视觉的坯布疵点实时自动检测平台[J].东华大学学报(自然科学版),2014,40(1):11-16.Li G Z,Wang X F,Wang J,et al.The machine vision-based platform for real-time grey fabric defect detection[J].Journal of Donghua University(Natural Science),2014,40(1):11-16.
[4]袁端磊,路立平,宋寅卯.织物疵点自动检测技术的研究进展[J].郑州轻工业学院学报,2005,20(3):69-73.Yuan D L,Lu L P,Song Y M.Recent studies on automatic fabric defect detection technique[J].Journal of Zhengzhou Institute of Light Industry,2005,20(3):69-73.
[5]王惠明,史萍.图像纹理特征的提取方法[J].中国传媒大学学报(自然科学版),2006,13(1);49-50.Wang H M,Shi P.Methods to extract images texture features[j].journal of communication university of china(Science and Technology),2006,13(1);49-50.
[6]黎丹,刘哲.织物疵点特征提取主要算法比较[J].毛纺科技,2011,39(1):57-62.Li D,Liu Z.Comparison of algorithms to extract features used in fabric defects detection[J].Wool Textile Journal,2011,39(1):57-62.
[7]刘伟斌,郑力新,周凯汀.一种方向性纹理织物疵点的检测方法[J].华侨大学学报(自然科学版),2014,11(6):642-647.Liu W b,Zheng L X,Zhou K T.A detection method of directional texture fabric defects[J].Journal of Huaqiao University(Natural Science),2014,11(6):642-647.
[8]Tsai I S,Hu M C.Automatic inspection of fabric defects using an artificial neural network technique[J].Textile Research Journal,1996,66(7):474-482.
[9]Haralick R M.Statistical and structural approaches to texture[J].Proceedings of the IEEE,1979,67(5):786-804.
[10]杨晓波.基于Gabor滤波器的织物疵点检测[J].纺织学报,2010,31(4):55-58.Yang X B.Detection of fabric defects based on Gabor filter[J].Journal of Textile Research,2010,31(4):55-58.
[11]卢亮,赵静.基于小波变换和图像最大熵的织物疵点检测[J].科学技术与工程,2011,11(22):5446-5450.Lu L,Lin J.Fabric defect detection based on wavelet transform and the maximum entropy of images[J].Science Technology and Engineering,2011,11(22):5446-5450.
[12]OTSU N.A threshold selection method from gray-level histogram[J].IEEE Trans System Man and Cybernetics,1979,9(01):62-66.
[13]管声启,石秀华.基于频域滤波的织物疵点检测[J].计算机应用,2008,28(10):2673-2675.Guan S Q,Shi X H.Fabric defects detection based on frequency domain filtering[J].Journal of Computer Applications,2008,28(10):2673-2675.
[14]杜磊,李立轻,汪军,万贤福,等.几种基于图像自适应阈值分割的织物疵点检测方法比较[J].纺织学报,2014,35(6):56-61.Du L,Li L Q,Wang J,Wan X F,et al.Comparison of several fabric defect detection methods based on image self-adaptive threshold segmentation[J].Journal of Textile Research,2014,35(6):56-61.
[15]Lin P L,Hsu H C,Huang P Y,et al.Alveolar bone-loss area localization in periapical radiographs by texture analysis based on f Bm model and GLC matrix[C].Bioelectronics and Bioinformatics(ISBB),2014 IEEE International Symposium on.IEEE,2014:1-4.
[16]Chen M,Dai S.Analysis on Image texture based on gray-level co-occurrence matrix[J].Communications Technology,2012,2:108-111.
[17]赵波,郑力新,潘旭玲,等.新的基于图像显著性区域特征的织物疵点检测算法[J].计算机应用,2012,32(6):1574-1577.Zhao B,Zheng L X,Pan X L,et al.New approach of fabric defects detection based on saliency region feature[J].Journal of Computer Applications,2012,32(6):1574-1577.
[18]白宗文.基于Besov和Hilbert-Sobolev空间的图像分解与修复算法[J].控制工程,2013,20(4):730-733.Bai Z W.Image decomposition and inpainting based on besov and hilbert-sobolev space[J].Control Engineering of China,2013,20(4):730-733.
[19]张锦华,孙挺.基于倍频信号滤波的非规则图像动态特征提取[J].控制工程,2015,22(2):301-305.Zhang J H,Sun T.Extraction of non-regular image dynamic characteristics based on frequency doubling signal filtering[J].Control Engineering of China,2015,22(2):301-305.
[2]Rohrmus D R.Invariant and adaptive geometrical texture features for defect detection and classification[J].Pattern Recognition,2005,38:1546-1559.
[3]李冠志,万贤福,汪军,等.基于机器视觉的坯布疵点实时自动检测平台[J].东华大学学报(自然科学版),2014,40(1):11-16.Li G Z,Wang X F,Wang J,et al.The machine vision-based platform for real-time grey fabric defect detection[J].Journal of Donghua University(Natural Science),2014,40(1):11-16.
[4]袁端磊,路立平,宋寅卯.织物疵点自动检测技术的研究进展[J].郑州轻工业学院学报,2005,20(3):69-73.Yuan D L,Lu L P,Song Y M.Recent studies on automatic fabric defect detection technique[J].Journal of Zhengzhou Institute of Light Industry,2005,20(3):69-73.
[5]王惠明,史萍.图像纹理特征的提取方法[J].中国传媒大学学报(自然科学版),2006,13(1);49-50.Wang H M,Shi P.Methods to extract images texture features[j].journal of communication university of china(Science and Technology),2006,13(1);49-50.
[6]黎丹,刘哲.织物疵点特征提取主要算法比较[J].毛纺科技,2011,39(1):57-62.Li D,Liu Z.Comparison of algorithms to extract features used in fabric defects detection[J].Wool Textile Journal,2011,39(1):57-62.
[7]刘伟斌,郑力新,周凯汀.一种方向性纹理织物疵点的检测方法[J].华侨大学学报(自然科学版),2014,11(6):642-647.Liu W b,Zheng L X,Zhou K T.A detection method of directional texture fabric defects[J].Journal of Huaqiao University(Natural Science),2014,11(6):642-647.
[8]Tsai I S,Hu M C.Automatic inspection of fabric defects using an artificial neural network technique[J].Textile Research Journal,1996,66(7):474-482.
[9]Haralick R M.Statistical and structural approaches to texture[J].Proceedings of the IEEE,1979,67(5):786-804.
[10]杨晓波.基于Gabor滤波器的织物疵点检测[J].纺织学报,2010,31(4):55-58.Yang X B.Detection of fabric defects based on Gabor filter[J].Journal of Textile Research,2010,31(4):55-58.
[11]卢亮,赵静.基于小波变换和图像最大熵的织物疵点检测[J].科学技术与工程,2011,11(22):5446-5450.Lu L,Lin J.Fabric defect detection based on wavelet transform and the maximum entropy of images[J].Science Technology and Engineering,2011,11(22):5446-5450.
[12]OTSU N.A threshold selection method from gray-level histogram[J].IEEE Trans System Man and Cybernetics,1979,9(01):62-66.
[13]管声启,石秀华.基于频域滤波的织物疵点检测[J].计算机应用,2008,28(10):2673-2675.Guan S Q,Shi X H.Fabric defects detection based on frequency domain filtering[J].Journal of Computer Applications,2008,28(10):2673-2675.
[14]杜磊,李立轻,汪军,万贤福,等.几种基于图像自适应阈值分割的织物疵点检测方法比较[J].纺织学报,2014,35(6):56-61.Du L,Li L Q,Wang J,Wan X F,et al.Comparison of several fabric defect detection methods based on image self-adaptive threshold segmentation[J].Journal of Textile Research,2014,35(6):56-61.
[15]Lin P L,Hsu H C,Huang P Y,et al.Alveolar bone-loss area localization in periapical radiographs by texture analysis based on f Bm model and GLC matrix[C].Bioelectronics and Bioinformatics(ISBB),2014 IEEE International Symposium on.IEEE,2014:1-4.
[16]Chen M,Dai S.Analysis on Image texture based on gray-level co-occurrence matrix[J].Communications Technology,2012,2:108-111.
[17]赵波,郑力新,潘旭玲,等.新的基于图像显著性区域特征的织物疵点检测算法[J].计算机应用,2012,32(6):1574-1577.Zhao B,Zheng L X,Pan X L,et al.New approach of fabric defects detection based on saliency region feature[J].Journal of Computer Applications,2012,32(6):1574-1577.
[18]白宗文.基于Besov和Hilbert-Sobolev空间的图像分解与修复算法[J].控制工程,2013,20(4):730-733.Bai Z W.Image decomposition and inpainting based on besov and hilbert-sobolev space[J].Control Engineering of China,2013,20(4):730-733.
[19]张锦华,孙挺.基于倍频信号滤波的非规则图像动态特征提取[J].控制工程,2015,22(2):301-305.Zhang J H,Sun T.Extraction of non-regular image dynamic characteristics based on frequency doubling signal filtering[J].Control Engineering of China,2015,22(2):301-305.