On Usage of Autoencoders and Siamese Networks for Online Handwritten Signature Verification

TL;DR

This paper introduces a novel signature verification framework combining autoencoders and Siamese networks, achieving high accuracy and low computational cost on benchmark datasets.

Contribution

The paper presents a new writer-independent global feature extraction method using autoencoders and Siamese networks with attention and downsampling, improving accuracy over prior approaches.

Findings

Achieved 8.65% EER on SigWiComp2013 Japanese dataset, a 1.2% improvement.

Attained average EERs below 0.3% on GPDS dataset for various test sizes.

Framework is computationally efficient and suitable for deployment on neural network hardware.

Abstract

In this paper, we propose a novel writer-independent global feature extraction framework for the task of automatic signature verification which aims to make robust systems for automatically distinguishing negative and positive samples. Our method consists of an autoencoder for modeling the sample space into a fixed length latent space and a Siamese Network for classifying the fixed-length samples obtained from the autoencoder based on the reference samples of a subject as being "Genuine" or "Forged." During our experiments, usage of Attention Mechanism and applying Downsampling significantly improved the accuracy of the proposed framework. We evaluated our proposed framework using SigWiComp2013 Japanese and GPDSsyntheticOnLineOffLineSignature datasets. On the SigWiComp2013 Japanese dataset, we achieved 8.65% EER that means 1.2% relative improvement compared to the best-reported result. Furthermore, on the GPDSsyntheticOnLineOffLineSignature dataset, we achieved average EERs of 0.13%, 0.12%, 0.21% and 0.25% respectively for 150, 300, 1000 and 2000 test subjects which indicates improvement of relative EER on the best-reported result by 95.67%, 95.26%, 92.9% and 91.52% respectively. Apart from the accuracy gain, because of the nature of our proposed framework which is based on neural networks and consequently is as simple as some consecutive matrix multiplications, it has less computational cost than conventional methods such as DTW and could be used concurrently on devices such as GPU, TPU, etc.