Parallel adaptive hierarchical network model for image segmentation

This paper described a new parallel adaptive hierarchical network model for image segmentation. The model consists of a layer for extracting local features and forming region in a parallel recursive way, a layer for adaptive statistical clustering, and a layer for making decision under the guidance of global distribution features. The communication between these layers is realized by means of cooperation mechanism. With the automatic non-parameter clustering method, the un-supervised image segmentation is completed by integrating the local gray feature with the global random distribution feature. The model has been applied to the adaptive segmentation of outdoor natural scene image. The experiments show that even though the environment of natural scene varies, accurate image segmentation still can be obtained.