# UTSig: A Persian Offline Signature Dataset

arXiv: https://arxiv.org/abs/1603.03235 · HTML: https://mlsanity.com/paper/1603.03235/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Mar 2016.

## Built on by (most cited first, 5 of 5)

- [A Perspective Analysis of Handwritten Signature Technology](https://mlsanity.com/paper/2405.13555/) (2024)
- [MSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwriting Verification](https://mlsanity.com/paper/2210.08836/) (2022)
- [Multiscale Feature Learning Using Co-Tuplet Loss for Offline Handwritten Signature Verification](https://mlsanity.com/paper/2308.00428/) (2023)
- [Enhanced Bank Check Security: Introducing a Novel Dataset and Transformer-Based Approach for Detection and Verification](https://mlsanity.com/paper/2406.14370/) (2024)
- [A comprehensive Persian offline handwritten database for investigating the effects of heritability and family relationships on handwriting](https://mlsanity.com/paper/2509.03510/) (2025)

## Abstract (arXiv)

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.