Learning the micro deformations by max-pooling for offline signature verification

For signature verification systems, micro deformations can be defined as the small differences in the same strokes of signatures or special writing habits of different signers. These micro deformations can reveal the core distinction between the genuine signatures and skilled forgeries. In this paper, we prove that Convolutional Neural Networks (CNNs) have the potential to extract those micro deformations by max-pooling. More specifically, the micro deformations can be determined by watching the location coordinates of the maximum values in pooling windows of max-pooling. Extensive analysis and experiments demonstrate that it is possible to achieve state-of-the-art performance by using this location information as a new feature for capturing micro deformations, along with convolutional features. The proposed method outperforms the state-of-the-art systems on four publicly available datasets of different languages, i.e., English (GPDSsynthetic, CEDAR), Persian (UTSig), and Hindi (BHSig260). (c) 2021 Elsevier Ltd. All rights reserved.

Automated summary

This paper demonstrates the potential of Convolutional Neural Networks (CNNs) to extract micro deformations for signature verification systems by watching the location coordinates of maximum values in pooling windows of max-pooling. The proposed method outperforms state-of-the-art systems on multiple publicly available datasets of different languages.