Segmentation of color images using a two-stage self-organizing network

Abstract We propose a two-stage hierarchical artificial neural network for the segmentation of color images based on the Kohonen self-organizing map (SOM). The first stage of the network employs a fixed-size two-dimensional feature map that captures the dominant colors of an image in an unsupervised mode. The second stage combines a variable-sized one-dimensional feature map and color merging to control the number of color clusters that is used for segmentation. A post-processing noise-filtering stage is applied to improve segmentation quality. Experiments confirm that the self-learning ability, fault tolerance and adaptability of the two-stage SOM lead to a good segmentation results.

[1]  Nikos Papamarkos,et al.  Color reduction using local features and a kohonen self‐organized feature map neural network , 1999, Int. J. Imaging Syst. Technol..

[2]  Keith Price,et al.  Picture Segmentation Using a Recursive Region Splitting Method , 1998 .

[3]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[4]  S. Tominaga.  Color classification of natural color images , 1992 .

[5]  Michael A. Arbib,et al.  Color Image Segmentation using Competitive Learning , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Paola Campadelli,et al.  Color image segmentation using Hopfield networks , 1997, Image Vis. Comput..

[7]  R.M. Mersereau,et al.  The processing of hexagonally sampled two-dimensional signals , 1979, Proceedings of the IEEE.

[8]  M. Celenk.  Colour image segmentation by clustering , 1991 .

[9]  Neil Storey,et al.  An Adaptive Pipeline Processor For Real-Time Image Processing , 1990, Other Conferences.

[10]  Georgios S. Paschos,et al.  Perceptually uniform color spaces for color texture analysis: an empirical evaluation , 2001, IEEE Trans. Image Process..

[11]  P. H. Lewis,et al.  Colour Image Segment at ion Using Boundary Relaxat ion , 1992 .

[12]  A. Robertson.  The CIE 1976 Color-Difference Formulae , 1977 .

[13]  Jouko Lampinen,et al.  Clustering properties of hierarchical self-organizing maps , 1992, Journal of Mathematical Imaging and Vision.

[14]  Jaakko Astola,et al.  Clustering based region growing algorithm for color image segmentation , 1997, Proceedings of 13th International Conference on Digital Signal Processing.

[15]  Nikos Papamarkos.  Color reduction using local features and a SOFM neural network , .

[16]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[17]  R. Mehrotra,et al.  Application of neural networks in segmentation of range images , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[18]  Yee-Hong Yang,et al.  Multiresolution Color Image Segmentation , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Din-Chang Tseng,et al.  Color segmentation using perceptual attributes , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.