Abstract
The recognition of images beyond basic image processing often relies on training an adaptive system using a set of samples from a desired type of images. The adaptive algorithm used in this research is a learning automata model called CLS (collective learning systems). Using CLS, we propose a hierarchy of collective learning layers to learn color and texture feature patterns of images to perform three basic tasks: recognition, classification and segmentation. The higher levels in the hierarchy perform recognition, while the lower levels perform image segmentation. At the various levels the hierarchy is able to classify images according to learned patterns. In order to test the approach we use three examples of images: a) Satellite images of celestial planets, b) FFT spectral images of audio signals and c) family pictures for human skin recognition. By studying the multi-dimensional histogram of the selected images at each level we are able to determine the appropriate set of color and texture features to be used as input to a hierarchy of adaptive CLS to perform recognition and segmentation. Using the system in the proposed hierarchical manner, we obtained promising results that compare favorably with other AI approaches such as Neural Networks or Genetic Algorithms.
“To understand is to perceive patterns”
Sir Isaiah Berlin (1909-1997)
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
Becker, G., Bock, P.: The ALISA Shape Module. In: Proceedings of the Second International Conference on Cognitive and Neural Systems, Boston (1998)
Bhanu, B., Wu, X.: Genetic Algorithms for Adaptive Image Segmentation. In: Nayar, S.K., Poggio, T. (eds.) Early Visual Learning. Oxford University Press, Oxford (1996)
Bock, P., Klinnert, R., Kober, R., Rovner, R., Schmidt, H.: Gray-Scale ALIAS. IEEE Transactions on Knowledge and Data Engineering 4(2) (1992)
Bock, P.: ALISA: Adaptive Learning Image and Signal Analysis. In: Proceedings of the SPIE Applied Imagery Pattern Recognition Conference, Washington D.C. (1998)
Carson, C., Belongie, S., Greenspan, H., Malik, J., Blobworld, J.: Image segmentation using expectation-maximization and its application to image querying. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(8), 1026–1038 (2002)
Cornell Lab of Ornithology: Raven Version 1.2 Ithaca, NY (2003)
European Space Agency: ESA Programs, National News. Available at ESA site (2004)
Greenspan, H.: Non Parametric Texture Learning. In: Nayar, S.K., Poggio, T. (eds.) Early Visual Learning. Oxford University Press, Oxford (1996)
Hubshman, J., Bock, P., Achikian, M.: Detection of Targets in Terrain Images with ALIAS. In: Proceedings of the Twenty-Third Annual Pittsburgh Conference on Modeling and Simulation, pp. 927–942 (1992)
Narendra, K.S., Thatachar, L. (eds.): Special Issue on Learning Automata. Journal of Cybernetics and Info Science 1, 2–4 (1977)
National Auronatics and Space Administration, NASA: News and Events, Missions Exploring the Universe. Available at NASA Site (2004)
Pratt, W.K.: Digital Image Processing, 3rd edn. PIKS Inside. J.Wiley, New York (2001)
Sanchez, A.: Learning Automata: An Alternative to Neural Networks. In: Rudomin, P., Arbib, M.A., Cervantes Pérez, F., Romo, P. (eds.) Neuroscience: From Neural Net works to Artificial Intelligence. Research Notes in Neural Computing, vol. 4. Springer, Heidelberg (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sanchez, A., Diaz, R., Bock, P. (2005). A CLS Hierarchy for the Classification of Images. In: Gelbukh, A., de Albornoz, Á., Terashima-Marín, H. (eds) MICAI 2005: Advances in Artificial Intelligence. MICAI 2005. Lecture Notes in Computer Science(), vol 3789. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11579427_37
Download citation
DOI: https://doi.org/10.1007/11579427_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29896-0
Online ISBN: 978-3-540-31653-4
eBook Packages: Computer ScienceComputer Science (R0)