Intra-Variable Handwriting Inspection Reinforced with Idiosyncrasy Analysis
This work addresses a specific problem in forensic document analysis or biometric authentication, but it appears incremental as it builds on existing deep learning techniques for handwriting analysis.
The paper tackles the challenge of intra-variable handwriting, where writing samples from the same individual vary significantly, by analyzing idiosyncrasy in handwriting to improve automatic writer inspection. It proposes methods for writer identification and verification using deep learning, reporting encouraging results on two databases.
In this paper, we work on intra-variable handwriting, where the writing samples of an individual can vary significantly. Such within-writer variation throws a challenge for automatic writer inspection, where the state-of-the-art methods do not perform well. To deal with intra-variability, we analyze the idiosyncrasy in individual handwriting. We identify/verify the writer from highly idiosyncratic text-patches. Such patches are detected using a deep recurrent reinforcement learning-based architecture. An idiosyncratic score is assigned to every patch, which is predicted by employing deep regression analysis. For writer identification, we propose a deep neural architecture, which makes the final decision by the idiosyncratic score-induced weighted average of patch-based decisions. For writer verification, we propose two algorithms for patch-fed deep feature aggregation, which assist in authentication using a triplet network. The experiments were performed on two databases, where we obtained encouraging results.