The Research of Leather Image Segmentation Using Texture Analysis Techniques

The leather productions are produced rapidly in people’s living, the productions’ quality is required stricter. Leather must be detected include leather plainness; leather surface defects and the density of leather before they are produced to be productions.. The most important aspect is the surface defects; the defects’ location, size and quantity should be confirmed. One of the most important steps of leather defects detection is leather image segmentation so as to extract leather defects. Gray level co-occurrence matrix is used to extract a lot of leather surface texture feature, the method of optimized Fuzzy C-means is used to segment leather image in the article. The optimized Fuzzy C-means add the spatial information; the precision of segmentation is improved. The image needs to be treated use morphological approach after it is segmented. As a result, the defective areas are separated from non-defective areas successfully.