Abstract
The paper proposes a theoretically very simple, and effective multi-scale local structural patterns (MS-LSP) for off-line signature verification. The proposed strategy models the signature by probabilistically counting the distribution of each local structural pattern on multiple scales. This representation correlates with the writing style of an individual and depict the shape and structural information of signatures. Extensive experiments on two challenging databases (MCYT, GPDS960) show that the proposed approach achieves noticeably verification rates and it is expected to provide a powerful discriminative representation of the signature.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have