Xiao Yan DAI and Junji MAEDA^*

Department of Computer Science and Systems Engineering, Muroran Institute of Technology, 27-1 Mizumoto, Muroran 050-8585, Japan

(Received October 15, 2001; Accepted June 26, 2002)

This paper presents an unsupervised segmentation method of natural images that uses Statistical Geometrical Features as texture descriptors and a hierarchical segmentation algorithm. We propose an extraction of texture features to obtain good boundary features and uniform texture features by incorporating an anisotropic diffusion preprocess. The proposed unsupervised hierarchical segmentation algorithm is performed in four stages: hierarchical splitting, local agglomerative merging, global agglomerative merging and pixelwise classification. We make some experiments to demonstrate the effectiveness of the proposed technique for segmentation of different natural images.

Key words: unsupervised segmentation, texture segmentation, statistical geometrical features, anisotropic diffusion, natural images