Combination and fusion of some 2D invariant moments with generative and discriminative classifiers for recognition of isolated handwritten Tifinagh characters

Abstract

In order to improve the recognition rate and accuracy of the Tifinagh OCR, this document proposes an approach to build a powerful automatic recognition system of isolated handwritten Tifinagh characters by using a combination and fusion of some features extraction methods. The Krawtchouk, Chebyshev and Gaussian Hermite moments are used as descriptors in the features extraction phase due to their invariance to translation, rotation and scaling changes. In the classification phase, the discriminative power of the neural networks, the multiclass SVM (Support Vector Machine), the nearest neighbour classifiers, and the generative nature of the Bayesian networks, are combined together in order to benefit from their complementarity. The experimental results of each single features extraction method and each single classification method are compared with our approach to show its robustness. To approve the claimed hypothesis and results, the experiments are conducted using databases of Handwritten Tifinagh Characters.