Image segmentation plays an important role in computer vision and
image analysis. In this paper, we cast natural image segmentation into a
problem of feature clustering. We extract local homogeneity, textures and
color features from images and describe them with Gaussian Mixture Models.
Unlike most existing clustering based segmentation methods, our method is
capable of model selection automatically by de-learning redundant segments
(clusters) during the clustering process. Thus, our method does not need to
specify the exact number of segments in advance. Comprehensive experiments
are conducted to measure the performance of the proposed algorithm in terms
of visual evaluation and a variety of quantitative indices for image
segmentation. The proposed algorithm compares favorably against other
well-known image segmentation methods on the BSDS500 image database.