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

• Proving that CNNs have the potential to capture "micro deformations". • Learning the discrimination from a two-phase CNN based feature extractor. • Achieving state of the art on four benchmark datasets of different languages. 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). [ABSTRACT FROM AUTHOR]