Abstract
In this paper, the authors have proposed an algorithm of segmenting grayscale image using associative memories approach. The algorithm is divided in three steps. In the first step, a set of regions (classes), where each one groups to a certain number of pixel values, is obtained. In the second step, the associative memories training phase is applied to the information obtained from first phase and an associative network, that contains the centroids group of each of the regions in which the image will be segmented, is obtained. Finally, using the associative memories classification phase, the centroid to which each pixel belongs is obtained and the image segmentation process is completed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Salem, A., Samma, B., Abdul, R.: Adaptation of K-Means Algorithm for Image Segmentation. Proceedings of World Academy of Science, Engineering and Technology 38, 58–62 (2009)
Dragan, M., Pavlovic, M., Reljin, I.: Image Segmentation Method Based on Self Organizing Maps and K-Means Algorithm. In: 9th Symposium on Neural Network Applications in Electrical Engineering, Belgrade, Serbia, pp. 27–30 (2008)
Yanling, L., Yi, S.: Robust Image Segmentation Algorithm Using Fuzzy Clustering Based on Kernel-Induced Distance Measure. In: International Conference on Computer Science and Software Engineering, Wuhan, China, vol. 1, pp. 1065–1068 (2008)
Yang, Z., Chung, F.L., Shitong, W.: Robust fuzzy clustering based image segmentation. Applied Soft Computing Journal 9(1), 80–84 (2008)
Shirakawa, S., Nagao, T.: Evolutionary Image Segmentation Based on Multi objective Clustering. In: IEEE Congress on Evolutionary Computation, Trondheim, Norway, pp. 2466–2473 (2009)
Handle, J., Knowles, J.: Multiobjective clustering with automatic determination of the number of clusters. Technical Report TR-COMPSYSBIO-2004-02, Department of chemistry, UMIST, Manchester (2004)
Handle, J., Knowles, J.: An evolutionary approach to multiobjective clustering. IEEE Transactions on Evolutionary Computation 11(1), 56–76 (2007)
Deb, K.: Multi-Objective Optimization Using Evolutionary Algorithms. John Wiley & Sons, New York (2001)
Coello, C., Lamont, G., Van Veldhuizen, D.: Evolutionary Algorithms for Solving Multi-Objective Problems, 2nd edn. Springer, New York (2007)
Xue-xi, Z., Yi-min, Y.: Hybrid Intelligent Algorithms for Color Image Segmentation. In: Chinese Control and Decision Conference, Yantai, China, pp. 264–268 (2008)
Sossa, H., Barrón, R., Vázquez, A.: Real-valued Patterns Classification based on Extended Associative Memory. In: Fifth Mexican International Conference on Computer Science, México, pp. 213–219. IEEE Computer Society, Los Alamitos (2004)
Steinbuch, K.: Die Lernmatrix. Kybernetik 1(1), 26–45 (1961)
Barron, R.: Associative Memories and Morphological Neural Networks for Patterns Recall (in Spanish). PhD dissertation, Center for Computing Research - National Polytechnic Institute, México (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Guzmán, E., Jiménez, O.M.C., Pérez, A.D., Pogrebnyak, O. (2011). Using Associative Memories for Image Segmentation. In: Liu, D., Zhang, H., Polycarpou, M., Alippi, C., He, H. (eds) Advances in Neural Networks – ISNN 2011. ISNN 2011. Lecture Notes in Computer Science, vol 6677. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21111-9_44
Download citation
DOI: https://doi.org/10.1007/978-3-642-21111-9_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21110-2
Online ISBN: 978-3-642-21111-9
eBook Packages: Computer ScienceComputer Science (R0)