A segmentation method of textured image by using neural network

This paper deals with a segmentation method of an image composed of some kinds of textures with randomness using a neural network. After a texture image is divided into a number of small windows with the same size, the feature vector in those windows is extracted by using a two-dimensional autoregressive model and fractal dimension. The clustering of feature vectors is performed by applying the self-organization algorithm developed by Kohonen, and the result of clustering is mapped onto the original image. Furthermore, a method which applies the backpropagation algorithm to the result of clustering is proposed to improve the accuracy of segmentation.