Off-line Handwritten Signature Texture Feature Extraction And Verification Based On Spectrum Analysis

Handwritten Signature Verification (HSV) is a discipline which aims to decide the identity of writers according to the handwriting styles. Its applications include banking, law etc. It has became one of the most active but difficult problems in the pattern recognition. So the study of HSV attracts more and more researchers in the recent years, but the study of off-line HSV is less than the on-line HSV. Under this background, the application background and history of development of off-line HSV techniques are briefly introduced in this thesis. The state of the off-line HSV researches at home and abroad is also surveyed. The analysis of all the exist methods is given, along with where they can be used and how they can be used. The nature of the off-line HSV problem and difficulties are analyzed, and then the overall strategy and an applicable computer off-line HSV system are proposed.In the preprocessing of signature image, the images are firstly binarized. Then, a morphological method is used to make the curve smooth and thin. Finally, the images are normalized. In the process of feature extraction, the texture features of the signatures are extracted. In fact, the methods of Fourier transform and Wavelet transform are used to extract the spectrum features of the signatures. In the process of verification, the relevant theory, the Euclidian theory and Dynamic Time Warping method are used respectively. Also, a second-time signature classification method is proposed. The experiment hasproven that the HSV system can get the satisfying right identifying rate.