Cluster based weighted SVM for the recognition of Farsi handwritten digits

Abstract

The recognition of handwritten characters and digits is an important and challenging issue in OCR algorithms. This article presents a new method in which cluster based weighted support vector machine is used for the classification and recognition of Farsi handwritten digits that is reasonably robust against rotation and scaling. In the proposed algorithm, after applying the necessary preprocessing on the digits images, the required features are extracted using principle component analysis (PCA) and linear discrimination analysis (LDA) algorithms. The extracted features are then classified using a new classification algorithm called cluster based weighted SVM (CBWSVM). We tested the proposed algorithm with a database containing 7600 handwritten digits with and without rotation and the results showed the recognition rate of 96.5% in digits without rotation and 95.6% in digits with rotation of the 15 degrees. The comparison of the results with those of other methods showed the efficiency of the proposed algorithm.