Recognition of Arabic (Indian) bank check digits using log-gabor filters

In this paper we present a technique for the automatic recognition of Arabic (Indian) bank check digits based on features extracted by using the Log Gabor filters. The digits are classified by using the K-Nearest Neighbor (K-NN), Hidden Markov Models (HMM) and Support Vector Machines (SVM) classifiers. An extensive experimentation is conducted on the CENPARMI data, a database consisting of 7390 samples of Arabic (Indian) digits for training and 3035 samples for testing extracted from real bank checks. The data is normalized to a height of 64 pixels, maintaining the aspect ratio. Log Gabor filters with several scales and orientations are used. In addition, the filtered images are segmented into different region sizes for feature extraction. Recognition rates of 98.95%, 98.75%, 98.62%, 97.21% and 94.43% are achieved with SVM, 1-NN, 3-NN, HMM and NM classifiers, respectively. These results significantly outperform published work using the same database. The misclassified digits are evaluated subjectively and results indicate that human subjects misclassified 1/3 of these digits. The experimental results, including the subjective evaluation of misclassified digits, indicate the effectiveness of the selected Log Gabor filters parameters, the implemented image segmentation technique, and extracted features for practical recognition of Arabic (Indian) digits.