LAUSR

Handwritten signature verification is a crucial yet challenging problem. While previous studies have made great progress in this problem, they learn signature features passively from given existing data. In this paper, we propose a novel adversarial variation network (AVN) model for handwritten signature verification which mines effective features by actively varying existing data and generating new data. Powered by a proposed novel variation consistency mechanism, the AVN contains three different types of modules unified under one end-to-end framework: the extractor seeks to extract deep discriminative features of handwritten signatures, the discriminator aims to make verification decisions based on the extracted features, and the variator is designed to actively generate signature variants for constructing a more discriminative model. The proposed model is trained in an adversarial way with a min-max loss function, by which the three modules cooperate and compete to enhance the entire model’s ability and therefore the signature verification performance is improved. We test the proposed method on four challenging signature datasets of different languages: CEDAR, BHSig-Hindi, BHSig-Bengali, and GPDS Synthetic Signature. Extensive experiments with in-depth discussions validate the effectiveness of the proposed method.