Revealing Reliable Signatures by Learning Top-Rank Pairs
This work addresses the critical need for reliable signature verification in financial and legal documents, representing an incremental improvement in a domain-specific task.
The paper tackles the problem of offline signature verification by proposing a method to learn top-rank pairs, which maximizes the number of absolutely reliable signatures. The model achieves significantly better pos@top ratios and competitive performance on AUC and accuracy on BHSig-B and BHSig-H datasets.
Signature verification, as a crucial practical documentation analysis task, has been continuously studied by researchers in machine learning and pattern recognition fields. In specific scenarios like confirming financial documents and legal instruments, ensuring the absolute reliability of signatures is of top priority. In this work, we proposed a new method to learn "top-rank pairs" for writer-independent offline signature verification tasks. By this scheme, it is possible to maximize the number of absolutely reliable signatures. More precisely, our method to learn top-rank pairs aims at pushing positive samples beyond negative samples, after pairing each of them with a genuine reference signature. In the experiment, BHSig-B and BHSig-H datasets are used for evaluation, on which the proposed model achieves overwhelming better pos@top (the ratio of absolute top positive samples to all of the positive samples) while showing encouraging performance on both Area Under the Curve (AUC) and accuracy.