Title :
Image segmentation algorithm for cord fabric defects inspection based on machine vision
Author :
Wang, Dongyun ; Hu, Rong ; Niu, Zhengguang
Author_Institution :
Sch. of Electr. & Inf. Eng., Zhongyuan Univ. of Technol., Zhengzhou, China
Abstract :
In an online defects inspection system for cord fabric based on machine vision, Image segmentation for cord fabric defects has been the hot and difficult problem. An adaptive segmentation algorithm using threshold surface is presented in this paper. And this method which is a fast adaptive threshold surface constructing method based on column statistic is proposed. This method inspects defects through detecting the change of image gray levels caused by the difference in optic character between cord fabric and defects. And it is set up around the analysis of for cord image and the requirements of online inspection system such as reliability, real-time, and veracity. The experiment results indicate that the proposed method has low computation cost, fast speed and good segmentation performance. It is in accord with the requirements of online inspection system.
Keywords :
computer vision; fabrics; image segmentation; production engineering computing; adaptive segmentation algorithm; adaptive threshold surface constructing method; column statistic; cord fabric defects inspection; image gray levels; image segmentation algorithm; machine vision; online inspection system; Change detection algorithms; Fabrics; Image analysis; Image segmentation; Information science; Inspection; Machine vision; Pixel; Surface morphology; Yarn;
Conference_Titel :
Information Science and Engineering (ICISE), 2009 1st International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-4909-5
DOI :
10.1109/ICISE.2009.653
