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

In this paper, we propose a novel writerindependent 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. We evaluated our proposed framework using SigWiComp2013 Japanese and GPDSsyntheticOnLineOffLineSignature dataset. 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 mulKian Ahrabian School of Mathematics, Statistics, and Computer Science, University of Tehran, Tehran, Iran Tel.: +98-9125482934 E-mail: [email protected] Bagher Babaali School of Mathematics, Statistics, and Computer Science, University of Tehran, Tehran, Iran Tel.: +98-9125248895 E-mail: [email protected] 1 Equal Error Rate tiplications, it has less computational cost than conventional methods such as DTW and could be used concurrently on devices such as GPU, TPU, etc.