Comparison of several approaches for the segmentation of texture images

Abstract In this paper, several approaches including K-Means, Fuzzy K-Means (FKM), Fuzzy Adaptive Resonance Theory (ART2) and Fuzzy Kohonen Self-Organizing Feature Mapping (SOFM) are adapted to segment the texture image. In our tests, five features, energy, entropy, correlation, homogeneity, and inertia, are used in texture analysis. The K-Means algorithm has the following disadvantages: (i) slow real-time ability, (ii) unstability. The FKM algorithm has improved the performance of the unstability by means of the introduction of fuzzy distribution functions. The Fuzzy ART2 has advantages, such as unsupervised training, low computation, and great degree of fault tolerance (stability/plasticity). Fuzzy operator and mapping functions are added into the network to improve the generality. The Fuzzy SOFM integrates the FKM algorithm into fuzzy membership value as learning rate and updating strategies of the Kohonen network. This yields automatic adjustment of both the learning rate distribution and update neighborhood, and has an optimization problem related to FKM. Therefore, the Fuzzy SOFM is independent of the sequence of feed of input patterns whereas final weight vectors by the Kohonen method depend on the sequence. The Fuzzy SOFM is “self-organizing” since the “size” of the update neighborhood and learning rate are automatically adjusted during learning. Clustering errors are reduced by Fuzzy SOFM as well as better convergence. The numerical results show that Fuzzy ART2 and Fuzzy SOFM are better than the K-Means algorithms. The images segmented by the algorithms are given to prove their performances.

[1]  C. Gareyte,et al.  Neural network segmentation and recognition of text data on engineering documents , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[2]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[3]  Nikhil R. Pal,et al.  Fuzzy divergence, probability measure of fuzzy events and image thresholding , 1992, Pattern Recognit. Lett..

[4]  Azriel Rosenfeld,et al.  A Comparative Study of Texture Measures for Terrain Classification , 1975, IEEE Transactions on Systems, Man, and Cybernetics.

[5]  Leif H. Finkel,et al.  Texture discrimination and binding by a modified energy model , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[6]  F. R. Hansen,et al.  Image segmentation using simple markov field models , 1982, Computer Graphics and Image Processing.

[7]  James C. Bezdek,et al.  Fuzzy Kohonen clustering networks , 1994, Pattern Recognit..

[8]  Sankar K. Pal,et al.  A review on image segmentation techniques , 1993, Pattern Recognit..

[9]  T. Y. Young,et al.  A multiresolution approach to texture segmentation using neural networks , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[10]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[11]  A. Kandel.  Fuzzy Mathematical Techniques With Applications , 1986 .

[12]  Alexander A. Sawchuk,et al.  Unsupervised textured image segmentation using feature smoothing and probabilistic relaxation techniques , 1989, Comput. Vis. Graph. Image Process..

[13]  Zhiling Wang,et al.  Unsupervised texture image segmentation by improved neural network ART2 , 1994 .

[14]  James M. Keller,et al.  Fuzzy Segmentation Of Natural Scenes Using Fractal Geometry , 1989, Other Conferences.

[15]  Changjing Shang,et al.  Principal features-based texture classification with neural networks , 1994, Pattern Recognit..