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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
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)
Kohonen, T.: The Self-Organizing Map. IEEE Proceedings 78, 1464–1477 (1990)
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)
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)
Carpenter, G.A., Grossberg, S.: The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network. Computer, 77–88 (1988)
Huang, D.: Theory of Neural Network Pattern Recognition System. Electronic Industry Press, Beijing (1996)
Carpenter, G.A., Grossberg, S.: ART-2: Self-Organization of Stable Category Recognition Codes for Analog Input Pattern. Applied Optics 26, 4919–4930 (1987)
Carpenter, G.A., Grossberg, S.: ART2-A: An Adaptive Resonance Algorithm for Rapid Category Learning and Recognition. Neural Networks 4, 493–504 (1991)
Shen, A., Yu, B., Guan, H.: Research on ART-2 Neural Network Classifier. Journal of Northern Jiaotong University 20(2), 146–151 (1996)
Cong, S., Zheng, Y., Wang, Y.: The Improvement and Modeling Implementation of ART-2 Neural Network. Computer Engineering and Applications 14, 25–27 (2002)
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)
Xu, Y., Deng, H., Li, Y.: An Improved ART2 Neural Network Clustering Algorithm. Journal of Computer Applications 26(3), 659–662 (2006)
Gu, M., Ge, L.: Improved Algorithm for ART2 Neural Network. Journal of Computer Applications 27(4), 945–947 (2007)
Gu, M., Ge, L.: Improvements of ART2 Neural Network Based on Amplitude Component. Computer Engineering and Applications 43(13), 52–54 (2007)
Color Metric, http://www.compuphase.com/cmetric.htm
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 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
DOI: https://doi.org/10.1007/978-3-540-87536-9_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87535-2
Online ISBN: 978-3-540-87536-9
eBook Packages: Computer ScienceComputer Science (R0)