DocumentCode :
1726128
Title :
Feature Extraction of the Fabric Defects Image
Author :
Jianxia, Wang ; Guang, Zheng ; Hongxia, Ma ; Min, Qin
Author_Institution :
Hebei Univ. of Sci. Technol., Shijiazhuang
fYear :
2007
Abstract :
The feature extraction of the fabric defects image is an important basis in the fabric defect identification. It affects directly the efficiency and accuracy of the fabric defects identification. The feature parameter should have high sensitivity, independency and rapid operation, based on this principle, the feature parameters of fabric defects are extracted, which include the area of fabric defects, the boundary perimeter, the center coordinate, the length of the long and short axes, the shape parameter F and eccentricity E. The experiment proved that the size and shape of fabric defects can be identified and the position can be confirmed based on these feature parameters.
Keywords :
fabrics; feature extraction; production engineering computing; boundary perimeter; center coordinate; eccentricity E; fabric defect identification; fabric defects image; feature extraction; feature parameter; shape parameter F; Covariance matrix; Digital images; Educational institutions; Eigenvalues and eigenfunctions; Fabrics; Feature extraction; Information science; Instruments; Pixel; Shape; Fabric defects identification; fabric defects; feature extraction; image processing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electronic Measurement and Instruments, 2007. ICEMI '07. 8th International Conference on
Conference_Location :
Xi´an
Print_ISBN :
978-1-4244-1136-8
Electronic_ISBN :
978-1-4244-1136-8
Type :
conf
DOI :
10.1109/ICEMI.2007.4350781
Filename :
4350781
Link To Document :
بازگشت