一种提取局部区域共同向量的瑕疵分类算法

doi:10.3969/j.issn.1001-2400.2011.05.010

Abstract

Abstract:

The large differences in texture and shape of the same type cloth and certain similarities between heterogeneous types result in the difficult classification of fabric defects. In this paper, it is proposed to select the fabric defect local region features and use the common vector method to extract features and to do classification. The defect local region features refer to the fabric defect local region gray histogram and geometrical features. First, we detect the fabric defect region by the optimal multiple-channels 2D Gabor wavelet| then select the features of the fabric defect local region gray histogram and geometrical feature (the rate of defect length and width, and the direction feature), and extract the common vector by the common vector algorithm| and finally, use the minimum distance method for defect classification. The algorithm is of small-sample learning, less computational load and high recognition rate.

Key words: fabric defect, histogram, geometrical feature, common vector, defect classification

CLC Number:

TP391

References

［1］ Sari-Sarraf H, Goddard J S. Vision Systems for On-loom Fabric Inspection［J］. IEEE Trans on Ind Appl, 1999(35): 1252-1259.
［2］ Kumar A. Neural Network Based Detection of Local Textile Defect［J］. Pattern Recognition, 2003(36): 1645-1659.
［3］ Brzakovic D, Vujovic N. Designing a Defect Classification Systems: a Case Study ［J］. Pattern Recognition,1996, 29(8): 1041-1419.
［4］ Cicirelli G, Stella E, Nitti M, et al. Neural Network Based Defect Inspection from Images［C］//Proceeding of the Fourth IASRED International Conference Signal Processing, Pattern Recognition, and Applications. Innsbruck: ACTA: 2007: 185-190.
［5］刘万春, 罗双华, 朱玉文, 等. 基于聚类分析和支持向量机的布匹瑕疵分类方法［J］. 北京理工大学学报, 2004, 24(8): 687-690.
Liu Wanchun, Luo Shuanghua, Zhu Yuwen, et al. Fabric Defect Classification Based on Cluster Analysis and Support Vector Machine［J］. Transactions of Beijing Institute of Technology, 2004, 24(8): 687-690.
［6］郝淑丽, 赵宇明. 基于支持向量机的瑕疵检测算法［J］. 微计算机信息, 2008, 24(3): 191-192.
Hao Shuli, Zhao Yuming. Flaw Detection Based on Support Vector Machine［J］. Microcomputer Information, 2008, 24(3): 191-192.
［7］ Shen Linlin, Ji Zhen. Gabor Wavelet Selection and SVM Classification for Object Recognition［J］. Acta Automatica Sinica, 2009, 35(4): 350-355.
［8］杨晓元, 王志刚, 王育民. 支持向量机在图像隐秘检测中的应用［J］. 西安电子科技大学学报, 2005, 32(3): 457-459.
Yang Xiaoyuan, Wang Zhigang, Wang Yumin. The Application of Support Vector Machines in Detection of Images Steganography［J］. Journal of Xidian University, 2005, 32(3): 457-459.
［9］丁爱玲, 刘芳, 姚霞. 基于支撑矢量机的智能目标识别方法［J］. 西安电子科技大学学报, 2001, 28(6): 743-746.
Ding Ailing, Liu Fang, Yao Xia. Intelligent Target Recognition Based on the Support Vector Machine［J］. Journal of Xidian University, 2001, 28(6): 743-746.
［10］温浩, 卢朝阳, 高全学. 融合小波变换和张量PCA 的人脸识别算法［J］. 西安电子科技大学学报, 2009, 36(4): 602-607.
Wen Hao, Lu Zhaoyang, Gao Quanxue. Face Recognition Algorithm Based on Wavelet Preprocessing and Tensor PCA［J］. Journal of Xidian University, 2009, 36(4): 602-607.
［11］温浩, 孙蕾. 基于张量局部和全局信息的人脸识别算法［J］. 西安电子科技大学学报, 2010, 37(3): 429-435.
Wen Hao, Sun Lei. New Face Recognition Algorithm Using Tensor Local and Global Information［J］. Journal of Xidian University, 2010, 37(3): 429-435.
［12］火元莲, 齐永锋. 基于Gabor小波与共同向量的人脸识别方法［J］. 计算机应用, 2009, 29(9): 2383-2385.
Huo Yuanlian, QI Yongfeng. Face Recognition Method Based on Gabor Wavelet and Common Vector［J］. Journal of Computer Applications, 2009, 29(9): 2383-2385.
［13］ Mark K L, Peng P. An Automated Inspection System for Textile Fabric Based on Gabor Filters［J］. Robotics and Computer-Integrated Manufacturing, 2008(24): 359-369.
［14］ Chen Shuyue, Feng Jun, Zou Ling. Study of Fabric Defects Detection through Gabor Filter Based on Scale Transformation［C］//Image Analysis and Signal Processing (IASP), 2010 International Conference in Zhejiang. Hangzhou: IASP, 2010: 97-99.
［15］ Cho I K J, Ko H S. Extending the Immediate Bucking Model to Triangular Meshes for Simulating Complex Clothes ［C］//Proceedings of Euro Graphics 2003 Short Presentations. Granada: The Earographice Association, 2003: 187-191.

[1]	KONG Yueping,LIU Chu,ZHU Xudong. Faceanti-spoofing method using the optical flow features of back ground [J]. Journal of Xidian University, 2021, 48(5): 86-91.
[2]	LIANG Fuxin;LIU Hongbin;CHANG Faliang. Multi-target tracking algorithm based on the multi-feature fusion matching and Hough forest [J]. Journal of Xidian University, 2018, 45(1): 129-134+161.
[3]	BIE Xiude;LIU Hongbin;CHANG Faliang;PENG Zhiyong. Multi-target tracking method based on the adaptive fragment and multi-feature fusion [J]. Journal of Xidian University, 2017, 44(2): 151-157.
[4]	YU Wangsheng;TIAN Xiaohua;HOU Zhiqiang;LIU Bin. Improved quadratic-form metric for histogram distance measurement [J]. J4, 2015, 42(3): 161-167+172.
[5]	LI Jin;WANG Junping;WAN Guoting;LI Ziyang;XU Dan;CAO Honghua;ZHANG Guangyan. Novel algorithm for image enhancement with histogram equalization and MSRCR [J]. J4, 2014, 41(3): 103-109.
[6]	WANG Xiang;LI Ke;FU Kaiyuan;LUO Fan. Histogram shifting based adaptive reversible watermarking algorithm with a high capacity [J]. J4, 2014, 41(1): 124-129.
[7]	CHEN Bing;ZHAO Yigong;LI Xin. Wide baseline image matching based on a new local descriptor [J]. J4, 2011, 38(2): 116-123.
[8]	TIAN Yu-min;ZHAO Jin;WU Zi-li. Shot boundary detection algorithm based on co-histogram [J]. J4, 2008, 35(2): 288-292.
[9]	WANG Shu-peng1.2;JI Hong-bing1. Object tracking based on the spatial color model [J]. J4, 2007, 34(7): 76-79.
[10]	JIAN Jian-feng(1;2);YIN Zhong-hai(1);ZHOU Li-hua(1);WANG Ren-xiang(2). Target’s matching method for the remote sensing image based on the histogram invariant moments [J]. J4, 2006, 33(4): 584-587.
[11]	MENG Fan-jie; GUO Bao-long. A novel image retrieval algorithm based on the color and distribution of interest points [J]. J4, 2005, 32(2): 256-259.

Algorithm for extraction of the local region common vector for defect classification

PDF (PC)

Like

Knowledge

Cited

Abstract

Cite this article

share this article

References

Related Articles 11

Metrics

Comments

Recommended 0