A multi-layer Kohonen's self-organizing feature map for range image segmentation

A self-organizing neural network for range image segmentation is proposed and described. The multi-layer Kohonen's self-organizing feature map (MLKSFM), which is an extension of the traditional single-layer Kohonen's self-organizing feature map (KSFM), is seen to alleviate the shortcomings of the latter in the context of range image segmentation. The problem of range image segmentation is formulated as one of vector quantization and is mapped onto the MLKSFM. The MLKSFM is currently implemented on the Connection Machine CM-2, which is a fine-grained single instruction multiple data (SIMD) computer. Experimental results using both synthetic and real range images are presented.<<ETX>>

[1]  Jack Bryant,et al.  On the clustering of multidimensional pictorial data , 1979, Pattern Recognit..

[2]  Ramesh C. Jain,et al.  Segmentation through Variable-Order Surface Fitting , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Tomaso A. Poggio,et al.  A Network for Image Segmentation Using Color , 1988, NIPS.

[4]  Mohan M. Trivedi,et al.  Low-Level Segmentation of Aerial Images with Fuzzy Clustering , 1986, IEEE Transactions on Systems, Man, and Cybernetics.

[5]  Helge Ritter,et al.  Topology conserving mappings for learning motor tasks , 1987 .

[6]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory, Second Edition , 1988, Springer Series in Information Sciences.

[7]  Anil K. Jain,et al.  Segmentation and Classification of Range Images , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Giuseppe Martinelli,et al.  Nonstationary lattice quantization by a self-organizing neural network , 1990, Neural Networks.