Offline signature verification based on the gabor transform

Research has been active in the field of forgery detection, but relatively little work has been done on the detection of skilled forgeries. This paper presents a new feature extraction method based on the intensity of the coefficients of the Gabor transform. The new method first uses the multichannel Gabor transform, then the transformed image of Gabor was equally divided into some non-overlapping boxes, and the angle features of the position of the maxima intensity of the Gabor transform coefficients were extracted. Experiment results indicate that the proposed method enable to improve verification accuracy.