Color fabric image segmentation based on texture features

A new automatic segmentation algorithm based on texture features for color fabric images is described in this paper. This algorithm firstly according to the characteristics of the fabric image, counting the colors of pixels in horizontal and vertical direction to find out the gathering areas with different colors, and get the number of segmentation regions(namely clusters). Then use Difference of Gaussian (DOG) filters and Difference of Offset Gaussian (DOOG) filters to extract texture features. A feature set which consists of texture information and color information is created. Lastly, segment the fabric image by using a variation of the k-means clustering algorithm that can largely reduce the computing time. Experiments show that this segmentation algorithm is feasible and effective.