Improving BPSO-based feature selection applied to offline WI handwritten signature verification through overfitting control
This work addresses overfitting in feature selection for signature verification, which is an incremental improvement for enhancing accuracy in biometric security systems.
The paper tackled overfitting in Binary Particle Swarm Optimization (BPSO) for feature selection in offline writer-independent handwritten signature verification, and the proposed method successfully controlled overfitting during the search for discriminant representations, as demonstrated on the GPDS-960 dataset.
This paper investigates the presence of overfitting when using Binary Particle Swarm Optimization (BPSO) to perform the feature selection in a context of Handwritten Signature Verification (HSV). SigNet is a state of the art Deep CNN model for feature representation in the HSV context and contains 2048 dimensions. Some of these dimensions may include redundant information in the dissimilarity representation space generated by the dichotomy transformation (DT) used by the writer-independent (WI) approach. The analysis is carried out on the GPDS-960 dataset. Experiments demonstrate that the proposed method is able to control overfitting during the search for the most discriminant representation.