Offline Handwritten Signature Recognition Based on Upper and Lower Envelope Using Eigen Values

Automatic signature recognition is most active area of research with number of applications such as financial, official work, bank cheque, business etc. To obtain maximum possible security from fake signature there is emergent need for a signature recognition, which can assure good results and gives better performance than already established offline signature recognition methods. In this paper, we proposed and implemented an innovative approach based on upper and lower envelope and Eigen values techniques. Envelope represents the shape of the signature. The feature set consists of features such as large and small Eigen values computed from upper envelope and lower envelope and its union values. Both the envelopes are fused by performing union operation and their covariance is computed. The difference and ratios of high and low points of both the envelopes are computed. Lastly average values of both the envelopes are obtained. These features set are coupled with support vector machine classifier that lead to 98.5 % of accuracy.