TEXTURE EDGE-DETECTION BY MODELING VISUAL CORTICAL CHANNELS

A simple and fast multi-channel filtering algorithm is presented in this paper for texture edge detection. The algorithm requires only a small number of channels and automatically determines the important channel parameters. It does not assume a priori knowledge about the type and number of textures occurring in the input image. It operates in an essentially unsupervised mode and involves only limited human intervention. The algorithm is tested extensively with a variety of synthetic and natural textures. Despite the simplicity of the overall algorithm, the segmentation results obtained are encouraging.