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.
展开▼
