A Novel Handwritten Punjabi Signature Dataset for Developing Robust and Scalable Deep-learning based Signature Verification Systems
Abstract
However, the lack of large, diverse, and well-annotated signature datasets poses a significant challenge in developing robust and scalable deep learning-based verification models. In this work, created a new dataset of signatures from [N] signers, including both authentic and forger signatures. Because the dataset contains private information, it will not be made publicly available. Our aim is to use this dataset to encourage the development of signature verification systems that are reliable, robust, and scalable. This dataset is helpful in developing robust and scalable deep learning models for signature verification
Fields of Study & Subjects
Handwritten Text Recognition Techniques
Topic Modeling
Natural Language Processing Techniques
Publication details
- Journal / source
- 2026 International Conference on AI-Driven Smart Systems and Ubiquitous Computing (ICAUC)
- Publisher
- IEEE
- Pages
- 1301–1304
- Publication date
- 19 January 2026