期刊
OPTICAL ENGINEERING
卷 55, 期 5, 页码 -出版社
SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS
DOI: 10.1117/1.OE.55.5.053109
关键词
defect detection; sparse encoding; convolutional matching pursuit; K-singular value decomposition; dual-dictionary
类别
资金
- National Natural Science Foundation of China [61301276]
- Discipline Construction Funds of Xi'an Polytechnic University [107090811]
- Xi'an Polytechnic University Scientific Research Foundation for doctors [BS1416]
- color printing fabric defect detection based on ADMG image decomposition [CX201602]
- Xi'an Polytechnic University Young Scholar Backbone Supporting Plan
Automatic patterned fabric defect detection is a promising technique for textile manufacturing due to its low cost and high efficiency. The applicability of most existing algorithms, however, is limited by their intensive computation. To overcome or alleviate the problem, this paper presents a convolutional matching pursuit (CMP) dual-dictionary algorithm for patterned fabric defect detection. A preprocessing with mean sampling is performed to eliminate the influence of background texture of fabric defects. Subsequently, a set of defect-free image blocks are selected as a sample set by sliding window. Dual-dictionary and sparse coefficiencies of the defect-free sample set are obtained via CMP and the K-singular value decomposition (K-SVD) based on a Gabor filter. Then we employ the defect-free and defective fabric image's projections onto the dual-dictionary as features for defect detection. Finally, the test results are determined by comparing the distance between the features to be measured. Experimental results reveal that the proposed algorithm is effective for patterned fabric defect detection and an acceptable average detection rate reaches by 94.2%. (C) 2016 Society of Photo-Optical Instrumentation Engineers (SPIE)
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据