一种新的布匹瑕疵图像自动检测算法

doi:10.3969/j.issn.1001-2400.2011.05.011

J4 ›› 2011, Vol. 38 ›› Issue (5): 65-72.doi: 10.3969/j.issn.1001-2400.2011.05.011

一种新的布匹瑕疵图像自动检测算法

崔玲玲;卢朝阳;李静;李益红

(西安电子科技大学综合业务网理论及关键技术国家重点实验室，陕西西安 710071)

收稿日期:2011-01-19 出版日期:2011-10-20 发布日期:2012-01-14
通讯作者: 崔玲玲
作者简介:崔玲玲(1982-)，女，西安电子科技大学博士研究生，E-mail: llcuisx@gmail.com
基金资助:
国家自然科学基金资助项目(60872141);陕西省自然科学基础研究计划资助项目(2009JQ8019);综合业务网理论及关键技术国家重点实验室基金资助项目(ISN090302);西安电子科技大学基础科研业务费资助项目(K50510010007)

Novel algorithm for automated detection of fabric defect images

CUI Lingling;LU Zhaoyang;LI Jing;LI Yihong

(State Key Lab. of Integrated Service Networks, Xidian Univ., Xi'an 710071， China)

Received:2011-01-19 Online:2011-10-20 Published:2012-01-14
Contact: CUI Lingling

摘要/Abstract

摘要：

针对布匹图像非下采样Contourlet分解系数能更好地描述瑕疵图像的轮廓特性，同时具有平移不变性和多方向性等优点，提出一种新的瑕疵自动检测算法．该算法通过非下采样Contourlet变换得到图像的多尺度、多方向稀疏表示|在此基础上，通过代价函数选择最优子带，得到较鲁棒性的描述| 最后实时地估计瑕疵和非瑕疵图像的混合高斯模型参数，有效地避免了对每一类瑕疵的估计，显著地降低了计算量．实验结果表明，与现有经典算法相比，该算法的主观效果和客观评价性能都有明显改进．

关键词: 瑕疵检测, 非下采样Contourlet变换, 混合高斯模型, 小波变换

Abstract:

Considering the advantages that decomposition coefficients in the non subsampled Contourlet of fabric images can describe the contour characteristics in a better way, and that they have shift-invariant and multidirection, a novel algorithm for automated detection of fabric defect images is presented. Firstly, the nonsubsampled Contourlet transform (NSCT) is used to perform the sparse representations in multi-scales and multi-directions. On this basis, the optimal sub-bands of NSCT are selected by the cost function, and then the robust descriptions are obtained. Finally, the parameters of defect and nondefect images are timely estimated separately by the Mixture Gaussian Model(MGM), which effectively avoids estimating each defect and reduces the computational complexity evidently. Experimental results show that the proposed algorithm can lead to a better performance than the traditional algorithms in subjective effects and objective evaluation.

Key words: defect detection, nonsubsampled Contourlet transform(NSCT), mixture gaussian model(MGM), wavelet transforms

中图分类号:

TN911.73

崔玲玲;卢朝阳;李静;李益红. 一种新的布匹瑕疵图像自动检测算法[J]. J4, 2011, 38(5): 65-72.

CUI Lingling;LU Zhaoyang;LI Jing;LI Yihong. Novel algorithm for automated detection of fabric defect images[J]. J4, 2011, 38(5): 65-72.

参考文献

［1］ Kumar A. Computer-Vision-Based Fabric Defect Detection: A Survey ［J］. IEEE Trans on Industrial Electronics, 2008, 55(1): 348-363.
［2］ Kumar A, Pang G K H. Defect Detection in Textured Materials Using Gabor Filters ［J］. IEEE Trans on Industry Applications. 2002, 38(2): 425-440.
［3］ Zeng Peifeng, Hirata T. On-Loom Fabric Inspection Using Multi-Scale Differentiation Filtering ［C］//Proc of IEEE Industry Application Conference. Pittsburgh: IEEE, 2002: 320-326.
［4］ Chen Shuyue, Feng Jun, Zou Ling. Study of Fabric Defects Detection Through Gabor Filter Based on Scale Transformation ［C］//Proc of International Conference on Image Analysis and Signal Processing. Xiamen: IEEE, 2010: 97-99.
［5］ Cohen F S, Fan Z, Attali S. Automated Inspection of Textile Fabrics Using Textural Models ［J］. IEEE Trans on Pattern Analysis and Machine Intelligence, 1991, 13(8): 803-808.
［6］ Pennec E L, Mallat S. Image Compression with Geometrical Wavelets ［C］//Proc of International Conference on Image Processing. Vancouver: IEEE, 2000: 661-664.
［7］ Cunha A L, Zhou Jianping, Do M N. The Nonsubsampled Contourlet Transform: Theory, Design, and Application ［J］. IEEE Trans on Image Processing, 2006, 15 (10): 3089-3101.
［8］贾建, 焦李成. 利用方向特性实现非下采样Contourlet变换阈值去噪［J］. 西安电子科技大学学报, 2009, 36(2): 269-273.
Jia Jian, Jiao Licheng. Image Denoising Using the Directional Property in the NSCT Domain ［J］. Journal of Xidian University, 2009, 36(2): 269-273.
［9］常霞, 焦李成, 刘芳, 等. 基于斑点方差估计的非下采样Contourlet域SAR图像去噪［J］. 电子学报, 2010, 38(6): 1328-1333.
Chang Xia, Jiao Licheng, Liu Fang, et al. SAR Image Despeckling Based on the Estimation of Speckle Variance in Nonsubsampled Contourlet Domain ［J］. Acta Electronica Sinica, 2010, 38(6): 1328-1333.
［10］ Shensa M J. The Discrete Wavelet Transform: Wedding the àtrous and Mallat Algorithms ［J］. IEEE Trans on Signal Processing, 1992, 40(10): 2464-2482.
［11］ Burt P J, Adelson E H. The Laplacian Pyramid as a Compact Image Code ［J］. IEEE Trans on Communication, 1983, 31(4): 532-540.
［12］ Bamberger R H, Smith M J T. A Filter Bank for the Directional Decomposition of Image: Theory and Design ［J］. IEEE Trans on Signal Process, 1992, 40(4): 882-893.
［13］ MacQueen J B. Some Methods for Classification and Analysis of Multivariate Observations ［C］//Proc of 5th Berkeley Symposium on Mathematical Statistics and Probability. Berkeley: University of California, 1967: 281-297.
［14］ Dempster A, Laird N, Rubin D. Maximum Likehood Estimation from Incomplete Data Via the EM Algorithm ［J］. Journal of the Royal Statistical Society: Series B, 1977, 39(1): 1-38.

[1]	李坤伦,张鲁,许宏科,宋焕生. 小波域扩张网络用于低剂量CT图像快速重建[J]. 西安电子科技大学学报, 2020, 47(4): 86-93.
[2]	高家明;梁煜;张为;刘艳艳. 一种新型低存储二维离散小波变换架构[J]. 西安电子科技大学学报, 2018, 45(2): 110-115.
[3]	贾琦;梁煜;张为. 一种无片外存储的高性能二维DWT架构[J]. 西安电子科技大学学报, 2017, 44(4): 138-143.
[4]	董明岩;雷杰;王柯俨;李云松. 高效低存储DWT的VLSI结构设计[J]. 西安电子科技大学学报, 2016, 43(2): 35-40.
[5]	周航;蔡志明;王希敏. 宽带信号匹配滤波的GPU实现及性能优化[J]. J4, 2015, 42(3): 135-140+191.
[6]	闫允一;姜帅;郭宝龙. 结合稳定兴趣点和Gabor小波的图像检索[J]. J4, 2014, 41(5): 118-123.
[7]	吕政良;龚书喜;张鹏飞;赵博;王夫蔚. 快速分析线面结构天线宽带特性的扫频方法[J]. J4, 2014, 41(1): 87-91.
[8]	王凌霞;焦李成;颜学颖;辛芳芳. 利用免疫克隆进行小波域遥感图像变化检测[J]. J4, 2013, 40(4): 108-113.
[9]	辛芳芳;焦李成;王桂婷;万红林. 利用小波域HMC模型进行遥感图像变化检测[J]. J4, 2012, 39(3): 43-49.
[10]	徐亚兰;马娟;陈建军;刘珍. EMD和小波变换在结构模态参数辨识中的应用[J]. J4, 2012, 39(2): 186-191.
[11]	杨贞萍;牛海军;丁磊. 一种新的NSCT超分辨率图像复原技术[J]. J4, 2012, 39(1): 34-37+85.
[12]	张双喜;张磊;郭睿;周鹏;邢孟道. 利用小波变换进行合成孔径雷达窄带干扰抑制算法[J]. J4, 2011, 38(5): 108-114.
[13]	李艳玲;李兵兵;殷昌义;刘明骞. 多径信道下调制信号识别新方法[J]. J4, 2011, 38(5): 13-19.
[14]	马苗;焦莉莉. 结构相似性灰关联在强噪声图像增强中的应用[J]. J4, 2010, 37(2): 346-352+365.
[15]	宋宜美;宋国乡. 结合波原子和Cycle Spinning的图像去噪[J]. J4, 2010, 37(2): 300-304.

一种新的布匹瑕疵图像自动检测算法

Novel algorithm for automated detection of fabric defect images

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0