SIGN-GAIL: Rewarding Online Signature Generation for Digital Imitation
Anurag Pandey, Arnav V. Bhavsar, Aditya Nigam, Divya Acharya, Basu Verma, Balaji Rao K · 2025
In real-world scenarios, signature generation involves mimicking a user's unique behavioral trajectory during on-line signing. This process presents a significant challenge: learning from expert data without direct interaction or ex-plicit feedback. Inverse reinforcement learning (IRL) approaches attempt to address this by inferring an underlying reward function from expert data and using reinforcement learning (RL) to derive policies. However, these methods are often slow and computationally expensive. To overcome these limitations, we propose SIGN-GAIL, a novel framework that leverages generative adversarial imitation learning (GAIL) to directly learn policies from expert data. Un-like traditional RL algorithms with manually defined reward functions, GAIL trains a reward function adversarially, en-abling it to act as a discriminator to distinguish between expert and generated trajectories. By framing the problem as a generative adversarial task, SIGN-GAIL effectively imitates complex behavioral trajectories, achieving high fi-delity in online signature generation. The proposed framework advances synthetic data generation in computer vision, enhancing biometric authentication systems with ro-bust dataset augmentation and improved resistance to deep-fake forgeries. Experimental results show that SIGN-GAIL outperforms traditional methods in trajectory fidelity and resemblance, demonstrating its potential for learning expert behaviors in sequential tasks like online signature generation.