Title :
Texture feature extraction of steel strip surface defect based on gray level co-occurrence matrix
Author :
Ying-Jun Guo;Zi-Jun Sun;He-Xu Sun;Xue-Ling Song
Author_Institution :
School of Electrical Engineering, Hebei University of Science and Technology, Shijiazhuang 050054, China
fDate :
7/1/2015 12:00:00 AM
Abstract :
To extract the texture features of forehead wrinkles, edge crack and other four kinds of typical defects of steel strip, we propose a feature extraction method based on gray level co-occurrence matrix(GLCM). Matlab simulation achieved that using four-dimensional parameters characteristic to describe the texture feature of steel strip defects. The results show that feature parameters of GLCM can describe the texture information of strip image effectively and can classify these four kinds of defects.
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2015 International Conference on
DOI :
10.1109/ICMLC.2015.7340925