Efficient Fusion based Directional and Textural features for Signature Verification

Biometric signature verification, nowadays an important technique to recognize human identity. The accuracy of signature verification has lot of scope for improvement. In this paper, we propose an offline signature verification using fusion of Directional and Textural features. The Image is preprocessed and divided into sub-bands by applying DWT. The Directional featuresGradient, Coherence, Orientation and Textural featurescorrelation, energy and homogeneity are computed from the sub-bands and concatenated to form feature vector. The Feed Forward ANN tool in MATLAB is used for classification and verification. The results of False Rejection Rate (FAR), False Acceptance Rate (FAR) and Total Success Rate (TSR) are obtained for GPDS-960 database. A total of 204 images are used for training and testing. It is observed that the values of FRR, FAR and TSR are improved compared to the existing algorithms.