Title :
Markov random fields and Karhunen-Loeve transforms for defect inspection of textile products
Author :
Özdemir, Serhat ; Ercil, Aytül
Author_Institution :
Dept. of Comput. Eng., Bogazici Univ., Istanbul, Turkey
Abstract :
In this paper the problem of using machine vision in quality inspection of textile fabrics is considered. A model based approach with Markov random fields (MRF) as the texture model and a new method based on Karhunen-Loeve transforms is studied for the defect inspection of textile fabrics. The results are illustrated on real fabric images, and the real time implementation of the MRF approach on a two TMS320C40 based parallel processing system is given
Keywords :
Markov processes; automatic optical inspection; computer vision; image texture; parallel processing; quality control; real-time systems; textile industry; transforms; Karhunen-Loeve transforms; Markov random fields; defect inspection; machine vision; parallel processing; real time systems; textile fabrics; texture analysis; Brightness; Fabrics; Humans; Image texture analysis; Inspection; Karhunen-Loeve transforms; Markov random fields; Parallel processing; Real time systems; Textile products;
Conference_Titel :
Emerging Technologies and Factory Automation, 1996. EFTA '96. Proceedings., 1996 IEEE Conference on
Conference_Location :
Kauai, HI
Print_ISBN :
0-7803-3685-2
DOI :
10.1109/ETFA.1996.573989
