UTSig: A Persian Offline Signature Dataset

TL;DR

This paper introduces UTSig, a comprehensive Persian offline signature dataset with diverse samples, for improving signature verification systems and analyzing signature characteristics.

Contribution

It presents a new public Persian offline signature dataset with extensive samples, forgeries, and variables, along with evaluation setups to enhance verification performance.

Findings

UTSig has more samples, classes, and forgers than existing datasets.

Training with genuine, opposite-hand, and forgery samples improves verification accuracy.

Persian signatures have fewer branch points and end points.

Abstract

The pivotal role of datasets in signature verification systems motivates researchers to collect signature samples. Distinct characteristics of Persian signature demands for richer and culture-dependent offline signature datasets. This paper introduces a new and public Persian offline signature dataset, UTSig, that consists of 8280 images from 115 classes. Each class has 27 genuine signatures, 3 opposite-hand signatures, and 42 skilled forgeries made by 6 forgers. Compared with the other public datasets, UTSig has more samples, more classes, and more forgers. We considered various variables including signing period, writing instrument, signature box size, and number of observable samples for forgers in the data collection procedure. By careful examination of main characteristics of offline signature datasets, we observe that Persian signatures have fewer numbers of branch points and end points. We propose and evaluate four different training and test setups for UTSig. Results of our experiments show that training genuine samples along with opposite-hand samples and random forgeries can improve the performance in terms of equal error rate and minimum cost of log likelihood ratio.