The New Method of Signature Recognition Based on Least Squares Contour Alignment

Abstract

The paper presents a new method of signature recognition based on least squares contour alignment. During the study six features of signatures were examined, such as: X, Y , P, V x, V y, V p. On the basis of the analyzed features of each signature two-dimensional graphs were created. Values of successive elements of any features of a signature, were taken as coordinates of points on the chart. Then, the chart created in such a way was treated as a contour and compared each other. In the study, usefulness of individual features was also evaluated.