Title :
Fabric defect detection based on wavelet reconstruction
Author :
Guan, Shengqi ; Yuan, Jianchang ; Ma, Ke
Author_Institution :
Coll. of Mech. & Electron. Eng., Xi´´an Polytech. Univ., Xi´´an, China
Abstract :
Fabric defect detection is an important part of quality inspection of textiles. Through the relevant theoretical analysis, the fabric image is decomposed by the use of DB wavelet. Then, sub-graphs of wavelet decomposition are selected reconstruction, which effectively inhibit the normal texture information. On this basis, the reconstructed image is morphological filtering to determine the location and area of defect. Experimental results show that the detection method is effectiveness to most defects.
Keywords :
image texture; inspection; production engineering computing; quality management; textiles; wavelet transforms; DB wavelet; fabric defect detection; fabric image; morphological filtering; normal texture information; quality inspection; textiles; wavelet decomposition; wavelet reconstruction; Corrosion; Fabrics; Filter banks; Filtering theory; Image reconstruction; Wavelet transforms; Defect detection; Fabric defect; Morphological filter; Wavelet decomposition; Wavelet reconstruction;
Conference_Titel :
Multimedia Technology (ICMT), 2011 International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-61284-771-9
DOI :
10.1109/ICMT.2011.6001901
