Boosting CNN-based Handwriting Recognition Systems with Learnable Relaxation Labeling

TL;DR

This paper introduces a novel handwriting recognition approach that combines learnable Relaxation Labeling with neural networks, improving accuracy and convergence speed, and outperforming some transformer-based models on benchmark datasets.

Contribution

It presents a new method integrating trainable Relaxation Labeling with neural architectures, enhancing performance and convergence in handwriting recognition.

Findings

RL processes improve generalization in handwriting recognition

The proposed method surpasses some transformer models on benchmarks

Sparsification accelerates convergence and boosts accuracy

Abstract

The primary challenge for handwriting recognition systems lies in managing long-range contextual dependencies, an issue that traditional models often struggle with. To mitigate it, attention mechanisms have recently been employed to enhance context-aware labelling, thereby achieving state-of-the-art performance. In the field of pattern recognition and image analysis, however, the use of contextual information in labelling problems has a long history and goes back at least to the early 1970's. Among the various approaches developed in those years, Relaxation Labelling (RL) processes have played a prominent role and have been the method of choice in the field for more than a decade. Contrary to recent transformer-based architectures, RL processes offer a principled approach to the use of contextual constraints, having a solid theoretic foundation grounded on variational inequality and game theory, as well as effective algorithms with convergence guarantees. In this paper, we propose a novel approach to handwriting recognition that integrates the strengths of two distinct methodologies. In particular, we propose integrating (trainable) RL processes with various well-established neural architectures and we introduce a sparsification technique that accelerates the convergence of the algorithm and enhances the overall system's performance. Experiments over several benchmark datasets show that RL processes can improve the generalisation ability, even surpassing in some cases transformer-based architectures.