International Journal of Advanced Research in Computer Science and Software Engineering (IJARCSSE)
People are comfortable with pen and papers for authentication and authorization in legal transactions. Due to increase in amount of offline handwritten signatures it is very essential that a person's handwritten signature to be identified uniquely. In this paper, the authors will evaluate the use of SURF features in handwritten signature verification. For each known writer they will take a sample of three genuine signatures and extract their SURF descriptors. They will calculate the intra class Euclidean distances among SURF descriptors of this known signature. Key points Euclidean distances, Image distances and the intra class thresholds will be stored as templates. They will calculate various intra class distance thresholds like maximum, average, minimum and range.