Arabic character recognition using statistical and geometric moment features

Feature extraction is one of the most important steps in character recognition system as each character has different features that distinguish it from other characters. Choosing good features is an important factor that affects recognition process. This paper proposed a novel and effective procedure for recognizing Arabic characters using a combination of statistical features and geometric moment features which are independent of the font and size of the character. These features are used by backpropagation neural network to classify the characters. Recognition rate of 97% is achieved using 6 different fonts.