A robust approach for offline English character recognition

Recognition rate of offline handwritten English character is still bounded due to large variation of shape, slants, and scales in hand writings. A sophisticated hand written character recognition system requires a better feature extraction technique that would take care of such variation of hand writing. In this paper, we propose a recognition model based on Artificial Neural Network (ANN) supported by novel feature extraction technique. Hand written data has continued to persist as a means of recording information in day-to-day life with the introduction of latest technologies. The constant development of computer tools lead to the requirement of easier interface between human and computers. Recognition of handwritten characters by computers is complicated task as compared to typed character. The proposed system is been implemented using MATLAB successfully. The ANN accepts the input as a scanned image. This input undergoes a sequence of pre-processing steps; binarization and normalization. Then features are extracted and matched from the stored data in the database. A data-base of 2600 samples is collected from 100 writers for each character. 1041 samples have been used to train the neural network and the rest are used to test recognition model. Using our proposed recognition system we have achieved a good average recognition rate of about 86.74 percent with minimum training time.