# Boosting CNN-based Handwriting Recognition Systems with Learnable Relaxation Labeling

arXiv: https://arxiv.org/abs/2409.05699 · HTML: https://mlsanity.com/paper/2409.05699/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 56 references that are in the map.
- First posted on arXiv 9 Sep 2024.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Automatic differentiation in machine learning: a survey](https://mlsanity.com/paper/1502.05767/) (2015)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition](https://mlsanity.com/paper/2005.13044/) (2020)
- [Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition](https://mlsanity.com/paper/1903.07377/) (2019)
- [End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network](https://mlsanity.com/paper/2012.03868/) (2020)
- [Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition](https://mlsanity.com/paper/1604.08352/) (2016)
- [Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention](https://mlsanity.com/paper/1604.03286/) (2016)
- [Rethinking Text Line Recognition Models](https://mlsanity.com/paper/2104.07787/) (2021)
- [Dropout improves Recurrent Neural Networks for Handwriting Recognition](https://mlsanity.com/paper/1312.4569/) (2013)
- [Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks](https://mlsanity.com/paper/1812.11894/) (2018)
- [Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network](https://mlsanity.com/paper/2012.04961/) (2020)
- [The Group Loss for Deep Metric Learning](https://mlsanity.com/paper/1912.00385/) (2019)
- [Attention-based Fully Gated CNN-BGRU for Russian Handwritten Text](https://mlsanity.com/paper/2008.05373/) (2020)
- [Best Practices for a Handwritten Text Recognition System](https://mlsanity.com/paper/2404.11339/) (2024)
- [Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions](https://mlsanity.com/paper/2208.08109/) (2022)
- [Character-Based Handwritten Text Transcription with Attention Networks](https://mlsanity.com/paper/1712.04046/) (2017)
- [Are 2D-LSTM really dead for offline text recognition?](https://mlsanity.com/paper/1811.10899/) (2018)
- [Have convolutions already made recurrence obsolete for unconstrained handwritten text recognition ?](https://mlsanity.com/paper/2012.04954/) (2020)

## Abstract (arXiv)

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.