Title :
A New Off-line Signature Verification Method based on Graph
Author :
Chen, Siyuan ; Srihari, Sargur
Author_Institution :
Center of Excellence for Document Anal. & Recognition, Buffalo Univ., NY
Abstract :
A graph matching approach to off-line signature verification is presented. Each of the signature images being compared is represented as a point set, which includes the local extremas of various types along the signature contours. Graph matching involves a deformation measure and a mapping function between point sets. Multiresolution signature features, as computed by gradient, structural and concavity features are used to measure local correspondence. Deformation and similarity scores are combined to make the final decision. The method performs better than previous off-line methods and is comparable to that of on-line systems
Keywords :
graph theory; handwriting recognition; image matching; image resolution; concavity features; deformation measure; gradient features; graph matching; mapping function; multiresolution signature features; offline signature verification; signature contours; signature images; structural features; Algorithm design and analysis; Biometrics; Forensics; Handwriting recognition; Image databases; Image edge detection; Joining processes; Shape measurement; Spline; Text analysis;
Conference_Titel :
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7695-2521-0
DOI :
10.1109/ICPR.2006.125