Title :
Fabric Defect Detection Based on Wavelet Characteristics
Author :
Guan, Shengqi ; Shi, Xiuhua ; Cui, Haiying ; Song, Yuqin
Author_Institution :
Coll. of Marine Eng., Northwestern Polytech. Univ., Xi´´an
Abstract :
On the basis of wavelet and singular signal characteristic analysis, a new defect detection method based on wavelet characteristics is presented. Firstly, to select wavelet filters of compact support and high vanishing moment properties are regarded as finite biorthogonal filters. Secondly, the new wavelet with concussive and filters coefficients of centralized distribution is constructed by lifting scheme, which is matching with test fabric texture properties. Lastly, the detail signal feature after wavelet decomposition of fabric image is extracted, and it is compared with the detail signal feature of normal fabric image decomposition to determine whether there exists defect. The experimental result confirms that the proposed method is validity and the detection accuracy is over 92.5%.
Keywords :
automatic optical inspection; fabrics; feature extraction; filtering theory; flaw detection; image matching; image texture; textile industry; wavelet transforms; fabric defect detection; feature extraction; finite biorthogonal filter; high vanishing moment property; image matching; lifting scheme; singular signal characteristics; test fabric texture property; textile industry; wavelet characteristics; wavelet decomposition; wavelet filter selection; Fabrics; Feature extraction; Filters; Image decomposition; Polynomials; Signal analysis; Testing; Textile industry; Wavelet analysis; Wavelet transforms; Defect Detection; Feature extraction; Lifting Sheme; Wavelet characteristics;
Conference_Titel :
Computational Intelligence and Industrial Application, 2008. PACIIA '08. Pacific-Asia Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-3490-9
DOI :
10.1109/PACIIA.2008.179
