Image Segmentation

CVGResearch Home 3D Reconstruction Texture Analysis Shape Analysis Segmentation Recognition Fractal Graphics Members				Segmentation Natural and man-made scenes are often made up of components, and some components can further be divided into smaller constituent elements, and so on. This hierarchical organization naturally motivates the study of segmentation, that is, an image of scenes and objects (as well as their 3D reconstructed models) can be beneficially segmented into meaningful parts. Automatic segmentation using the computer is useful in itself, and is also (debatably) widely considered as an important intermediate step for scene analysis and recognition.
				Adaptive Image Segmentation Using Artificial Co-evolving Tribes. Yun Wen Chen, Yan Qiu Chen. International Journal of Pattern Recognition and Artificial Intelligence, Vol. 21, Issue 7, Pages 1171-1193, 2007
				Abstract. Deriving from the artificial life theory, this paper proposes an artificial co-evolving tribes model and applies it to solve the image segmentation problem. During the evolution process, the individuals in this model making up the tribes effect communication cooperatively from one agent to the other in order to increase the homogeneity of the ensemble of the image regions they represent. Two remarkable properties, that is, the monotone contraction and the conservation of the system are proved. Stability and scale control of the proposed method are carefully analyzed. Experimental results are presented and compared with two latest segmentation methods, both quantitatively and visually. We also discuss the results matching with human visual perception.

				Artificial Life for Image Segmentation. Hao He, Yan Qiu Chen. International Journal of Pattern Recognition and Artificial Intelligence, Vol. 15, Issue 6, Pages 989-1003, 2001
				Abstract. Artificial life has been successfully used for understanding biological systems and in many applications in robotics, computer graphics, etc. In this paper, we pioneer the use of artificial life for image segmentation, a challenging area in image processing. Our method associates each pixel in an image with a life and it evolves according to a system of rules. The segmented partitions emerge when the state of the lives reaches an equilibrium. The artificial life approach is promising in image processing because it is inherently parallel and coincides with the self-governing biological process. In addition, it has the advantage of the integration of both detail preservation and noise removal. The experiments demonstrate the feasibility of the artificial life approach on both intensity images and color images. We also compared the approach with other four commonly used methods for three different kinds of noise corrupted images.

				Unsupervised texture segmentation using resonance algorithm for natural scenes. Hao He, Yan Qiu Chen. Pattern Recognition Letters, Volume 21, Issue 8, Pages 741-757, 2000
				Abstract. Many texture segmentation methods in the literature assume that the changes of intensity can be ascribed to the texture themselves. However, the real-world images may contain wide-ranged gradations in intensity which have nothing to do with local texture, such as those caused by the environment illuminations and cameras. To overcome the problem, an unsupervised texture segmentation method is proposed in this paper. Emphasizing the spatial relations between the adjacent texture pixels, the algorithm begins from a set of seed pixels and the texture region is generated by including those similar pixels. To suppress the noise influence, special attention is paid to the similarity criterion. Furthermore, to meet the requirement of unsupervised segmentation, the threshold in the similarity checking is automatically determined via iteratively applying the algorithm. The experimental results on Brodatz texture images and real-world images are presented.