A New Type of ART2 Architecture and Application to Color Image Segmentation (original) (raw)

Abstract

A new neural network architecture based on adaptive resonance theory (ART) is proposed and applied to color image segmentation. A new mechanism of similarity measurement between patterns has been introduced to make sure that spatial information in feature space, including both magnitude and phase of input vector, has been taken into consideration. By these improvements, the new ART2 architecture is characterized by the advantages: (i) keeping the traits of classical ART2 network such as self-organizing learning, categorizing without need of the number of clusters, etc.; (ii) developing better performance in grouping clustering patterns; (iii) improving pattern-shifting problem of classical ART2. The new architecture is believed to achieve effective unsupervised segmentation of color image and it has been experimentally found to perform well in a modified L ∗ u ∗ v ∗ color space in which the perceptual color difference can be measured properly by spatial information.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Dong, G., Xie, M.: Color Clustering and Learning for Image Segmentation Based on Neural Networks. IEEE Transactions on Neural Networks 16(4), 925–936 (2005)
    Article Google Scholar
  2. Kohonen, T.: The Self-Organizing Map. IEEE Proceedings 78, 1464–1477 (1990)
    Article Google Scholar
  3. Carpenter, G.A., Grossberg, S.: A Massively Parallel Architecture for a Self-Organizing Neural Pattern Recognition Machine. Computer Vision, Graphics, and Image Processing 37, 54–115 (1987)
    Article Google Scholar
  4. Yeo, N.C., Lee, K.H., Venkatesh, Y.V., Ong, S.H.: Colour Image Segmentation Using the Self-Organizing Map and Adaptive Resonance Theory. Image and Vision Computing 23, 1060–1079 (2005)
    Article Google Scholar
  5. Carpenter, G.A., Grossberg, S.: The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network. Computer, 77–88 (1988)
    Google Scholar
  6. Huang, D.: Theory of Neural Network Pattern Recognition System. Electronic Industry Press, Beijing (1996)
    Google Scholar
  7. Carpenter, G.A., Grossberg, S.: ART-2: Self-Organization of Stable Category Recognition Codes for Analog Input Pattern. Applied Optics 26, 4919–4930 (1987)
    Article Google Scholar
  8. Carpenter, G.A., Grossberg, S.: ART2-A: An Adaptive Resonance Algorithm for Rapid Category Learning and Recognition. Neural Networks 4, 493–504 (1991)
    Article Google Scholar
  9. Shen, A., Yu, B., Guan, H.: Research on ART-2 Neural Network Classifier. Journal of Northern Jiaotong University 20(2), 146–151 (1996)
    Google Scholar
  10. Cong, S., Zheng, Y., Wang, Y.: The Improvement and Modeling Implementation of ART-2 Neural Network. Computer Engineering and Applications 14, 25–27 (2002)
    Google Scholar
  11. Tang, H., Sang, N., Cao, Z., Zhang, T.: Research and Improvements of ART-2 Neural Networks. Infrared and Laser Engineering 33(1), 101–106 (2004)
    Google Scholar
  12. Xu, Y., Deng, H., Li, Y.: An Improved ART2 Neural Network Clustering Algorithm. Journal of Computer Applications 26(3), 659–662 (2006)
    Google Scholar
  13. Gu, M., Ge, L.: Improved Algorithm for ART2 Neural Network. Journal of Computer Applications 27(4), 945–947 (2007)
    Google Scholar
  14. Gu, M., Ge, L.: Improvements of ART2 Neural Network Based on Amplitude Component. Computer Engineering and Applications 43(13), 52–54 (2007)
    Google Scholar
  15. Color Metric, http://www.compuphase.com/cmetric.htm

Download references

Author information

Authors and Affiliations

  1. Guangxi University, China
    Jiaoyan Ai
  2. Simon Fraser University, Canada
    Brian Funt & Lilong Shi

Authors

  1. Jiaoyan Ai
  2. Brian Funt
  3. Lilong Shi

Editor information

Véra Kůrková Roman Neruda Jan Koutník

Rights and permissions

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Ai, J., Funt, B., Shi, L. (2008). A New Type of ART2 Architecture and Application to Color Image Segmentation. In: Kůrková, V., Neruda, R., Koutník, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87536-9\_10

Download citation

Keywords

Publish with us