A segmentation method of texture image by using pyramid linking and neural networks

We introduce a segmentation method by using pyramid linking with band-pass neural networks. This approach is applied to segment an image composed of some types of texture to several homogeneous areas. The texture properties of the image are extracted by using a two-dimensional autoregressive method and fractal dimension, and then feature vector pyramids are built of reduced-resolution versions of these arrays. By using band-pass neural networks, the pyramid node linking process is applied. The resulting trees define the segmentation of the original image. The validity of this method is verified by several numerical examples