Recognition of isolated handwritten Persian/Arabic characters and numerals using support vector machines

In this paper we propose a system for recognition of isolated handwritten Persian/Arabic characters and numerals. Wavelet transform has been used for feature extraction in this system. We used Haar wavelet. The Support Vector Machine (SVM), which is a new learning machine with very good generalization ability, and has been used widely in pattern recognition and regression estimation, uses as classifier in this system. The training and test patterns were gathered from various people with different ages and different educational backgrounds. The 32 characters in Persian language were categorized into 8 different classes in which characters of each class are very similar to each others. There are ten digits in Persian/Arabic languages where two of them are not used in zip codes in Iran. So, we have 8 different extra classes for digits. This system was used for recognizing the isolated handwritten postal addresses, which contain the name of cities and their zip codes. Our database contains 579 postal addresses in Iran. The system yields the recognition rate of 98.96% for these postal addresses. The results show an increment in recognition rates in comparison with our previous work in which we used the MLP neural network as classifier.