Texture segmentation based on an adaptively fuzzy clustering neural network
Chengbo Wang, Hongbin Wang, Qi-Bin Mei · 2005
This work presents a novel approach to the segmentation of a textured image. We give a new validity function to check the validity of cluster number, it ensures the clustering results being fit for the real data structure by the aid of training of neural network. Then we synthesize traditional fuzzy clustering approaches and neural network to research the texture segmentation. The adaptive algorithm mainly includes three process: (1) feature extraction, extracting the texture features; (2) feature classification, using adaptively neural network to determine the clusters number; (3) fuzzy clustering, getting the results of classification and segmentation. Our experiments have proved the effectiveness of this method.