Signature authentication based on subpattern analysis

Current network based authentication applications require simple robust methods which are faster and does not choke the bandwidth. Minimal features are considered using subpattern analysis which leads to less response time in a real time scenario. Certain subsections of signature vary in a genuine case subdivision process. With a high degree of certainty the minimum variance quadtree components [MVQCs] of a signature for a person are listed to apply on testing sample. Hu moments are applied on the selected subsections. The summation values of the subsections are provided as feature to radial basis function [RBF] and feed forward neural network classifiers. Results indicate that the Radial Basis Function classifier yielded 7% false rejection rate and feed forward neural network classification technique produced 9% false rejection rate. The major advantage of proposed system is, storage of person dependent template details are drastically reduced. Only the MVQC list of a person is to be cataloged.