全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于最小分类误差小波特征的纺织品缺陷分类方法研究

DOI: 10.11834/jig.20090218

Keywords: 纺织品自动检测,纺织品缺陷分类,小波框架,最小分类误差训练

Full-Text   Cite this paper   Add to My Lib

Abstract:

纺织品缺陷分类是利用计算机视觉技术检测纺织品品质的一个关键环节。提出了一种基于小波框架的纺织品缺陷分类新方法。该方法使用纺织品图像的小波框架来描述缺陷的纹理特征。在最小分类误差训练框架下,通过联合设计一个基于线性变换矩阵的特征提取器和一个分类器,来获取面向缺陷分类的小波框架特征,并最小化分类器的错误概率。该方法对包含9类纺织品缺陷的329个样本,以及328个无缺陷样本进行了分类实验评估,获得了93?1%的分类准确率,相比传统的基于小波变换的分类方法提高了27?2%。

References

[1]  Brzakovic D, Vujovic N. Designing a defect classification system: a case study [J]. Pattern Recognition, 1996, 29 ( 8 ) : 1401 - 1419.
[2]  Tolba A S, Abu-Rezeq A N. A self-organizing feature map for automated visual inspection of textile products [J]. Computers in Industry, 1997, 32(3) : 319-333.
[3]  Karayiannis Y A. Defect detection and classification on web textile fabric using muhiresolution decomposition and neural networks [ A ]. In: Proceedings of IEEE International Conference on Electronics, Circuits and Systems [C] , Blacksburg, Virginia, USA, 1999: 765 -768.
[4]  Cvetkovic Z, Vetterli M. Oversampled filter banks[J]. IEEE Transactions on Signal Processing, 1998, 45 ( 5 ) : 1245-1255.
[5]  Juang B H, Katagiri S. Discriminant learning for minimum error classification[J] . IEEE Transactions on Signal Processing, 1992, 40(12) : 3043-3054.
[6]  Watanabe H, Yamaguchi T, Katagiri S. Discriminant metric design for robust pattern recognition [J]. IEEE Transactions on Signal Processing, 1997, 45( 11 ) : 2655-2662.
[7]  Huo Q, Gc Y, Feng Z. High performance chinese OCR based on Gabor features, discriminative feature extraction and model training [ A ]. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing[C], Salt Lake City, Utah, USA,2001 : 1517-1520.
[8]  Laine A, Fan J. Frame representations for texture segmentation [J]. IEEE Transactions on Image Processing, 1996, 5 (5) : 771-780.
[9]  Srinivasan K, Dastor P H, Radhakrishnaihan P, et al. FDAS: A knowledge-based frame detection work for analysis of defects in woven textile structures [J] . Journal of Textile Institute, 1992, 83(3) : 431-447. ~
[10]  Bradshaw M. The application of machine vision to the automated inspection of knitted fabrics [J] . Mechatronics, 1995, 29 ( 8 ) : 233-243.
[11]  Rohrmus D. Invariant web defect detection and classification system [ A]. In:Proceedings of IEEE International Conference on CVPR [C], Hilton Head, SC, USA,2000: 794-795.
[12]  Unser M. Texture classification and segmentation using wavelet frames [J]. IEEE Transactions on Image Processing, 1995, 4 (11 ) : 1549-1560.
[13]  Katagiri S, Juang B H, Lee C H. Pattern recognition using a family of design algorithms based upon the generalized probabilistic descent method [J]. Proceedings of the IEEE, 1998, 86 ( 11 ) : 2345-2373.
[14]  Biem A, Katagiri S, Juang B H. Pattern recognition based on discriminative feature extraction [J]. IEEE Transactions on Signal Processing, 1997, 45(2) : 500-504.
[15]  Paliwal K K, Bacehiani M, Sagisaka Y. Simultaneous design of feature extractor and pattern classifier using the minimum classification error training algorithm [ A ]. In : Proceedings of IEEE Workshop on Neural Networks for Signal Processing [C] , Cambridge, MA, USA, 1995 : 67 -76.
[16]  Tasy K M, Shyu H K, Chang H P. Feature transformation with generalized learning vector quantization for handwritten Chinese character recognition [J] . IEICE Transactions on Information and Systems, 1999, E82-D (3) : 687-692.
[17]  Fletcher R. Practical Methods of Optimization [M]. New York, USA: Wily, 1987:35-40.
[18]  Yang X, Pang G, Yung N. Discriminative fabric defect detection using adaptive wavelet [J]. Optical Engineering, 2002, 41 ( 12 ) : 3116-3126.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133