Title :
A new method for leather texture image classification
Author :
Wang, Qingyuan ; Liu, Hong ; Liu, Jianqin ; Wu, Tian
Author_Institution :
Inst. of Artificial Intelligence & Robotics, Xi´´an Jiaotong Univ., China
Abstract :
A new texture classification method intended for classifying leathers made of the same materials is presented. Unlike the conventional methods which mainly use global features, the authors use both global features extracted from the two dimensional power spectrum of enhanced leather trench image and the local features based on mathematical morphology operation of a segmented leather image. The experiment is conducted on a group of sample leathers and the results are satisfactory
Keywords :
feature extraction; image texture; enhanced leather trench image; leather texture image classification; mathematical morphology operation; two dimensional power spectrum; Artificial intelligence; Conducting materials; Feature extraction; Histograms; Image analysis; Image classification; Image texture analysis; Intelligent robots; Morphology; Shape measurement;
Conference_Titel :
Industrial Electronics, 1992., Proceedings of the IEEE International Symposium on
Conference_Location :
Xian
Print_ISBN :
0-7803-0042-4
DOI :
10.1109/ISIE.1992.279565
