Arabic Handwritten Characters Classification Using Learning Vector Quantization Algorithm
In this module, Learning Vector Quantization LVQ neural network is first time introduced as a classifier for Arabic handwritten character. Classification has been performed in two different strategies, in first strategy, we use one classifier for all 53 Arabic Character Basic Shapes CBSs in training and testing phases, in second strategy we use three classifiers for three subsets of 53 Arabic CBSs, the three subsets of Arabic CBSs are; ascending CBSs, descending CBSs and embedded CBSs. Three training algorithms; OLVQ1, LVQ2 and LVQ3 were examined and OLVQ1 found as the best learning algorithm.
KeywordsArabic handwritten recognition Neural Network Classification Character Recognition
- 2.Kohonen, T.: New developments and applications of self-organizing maps Neural Networks for Identification. In: Proceedings of International Workshop on Control, Robotics, and Signal/Image Processing, pp. 164–172 (1996) Google Scholar
- 3.Kohonen, T., Barna, G., Chrisley, R.: Statistical pattern recognition with neural networks: benchmarking studies. In: IEEE International Conference on Neural Networks, vol. 1, pp. 61–68 (1988)Google Scholar
- 7.Menasri, F., Vincent, N., Cheriet, M., Augustin, E.: Shape-Based Alphabet for Off-line Arabic Handwriting Recognition. In: Ninth International Conference on Document Analysis and Recognition, ICDAR, vol. 2, pp. 969–973 (2007)Google Scholar