2C2S: A two-channel and two-stream transformer based framework for offline signature verification

Recently, with the outstanding performance of the transformer in NLP, approaches that employ the transformer to address vision problem is becoming a research focus. However, transformer-based research rarely focuses on signature verification. To fill this gap, this paper proposes a two-channel and two-stream transformer approach (2C2S) to cope with the signature verification problem. 2C2S is composed of original and central streams. The original stream receives the original signature pair as input, and the central stream receives the signature pair generated by cropping the central at the original pair as input. In order to establish the associations among feature channels, a squeeze-and-excitation operation is applied between two standard Swin Transformer blocks. Moreover, an up-sampling enhancement module directly steers the model to focus on useful information. The verification accuracy of 2C2S on SUES-SiG and several publically available datasets: CEDAR, BHSig-B, and BHSig-H, reaches 93.25%, 90.68%, 100%, and 72.22%, respectively. Extensive experiments illustrate that the proposed framework is competitive with the existing techniques for offline handwritten signature verification.