Intra-Variable Handwriting Inspection Reinforced with Idiosyncrasy Analysis

TL;DR

This paper introduces a novel deep learning approach for intra-variable handwriting analysis, focusing on identifying and verifying writers by analyzing highly idiosyncratic text patches despite significant within-writer variation.

Contribution

It presents a new deep reinforcement learning-based method to detect idiosyncratic handwriting patches and integrates this with neural architectures for improved writer identification and verification.

Findings

Encouraging results on two handwriting databases.

Effective identification of highly idiosyncratic text patches.

Improved writer verification using patch-based deep feature aggregation.

Abstract

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.