Study and Realization of Image Segmentation on the Cotton Foreign Fibers

A method of foreign fibers image segmentation based on Mean shift、dilation and filtering algorithm is presented. For the representative gray images of hair、chicken feather and mixed foreign fibers, the Mean shift algorithm is used to carry on image segmentation; then dilation and filtering process is carried on to the divided image element. In this way the precise image segmentation of foreign fibers is realized. It’s proved by experiments that the image segmentation method proposed by this article can suppress the noise well, and the segmentation results are satisfied for all kinds of foreign fibers image.