HTR-ConvText: Leveraging Convolution and Textual Information for Handwritten Text Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Truc, Pham Thach Thanh, Nam, Dang Hoai, Khoa, Huynh Tong Dang, Duy, Vo Nguyen Le
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917125323489280
author Truc, Pham Thach Thanh
Nam, Dang Hoai
Khoa, Huynh Tong Dang
Duy, Vo Nguyen Le
author_facet Truc, Pham Thach Thanh
Nam, Dang Hoai
Khoa, Huynh Tong Dang
Duy, Vo Nguyen Le
contents Handwritten Text Recognition remains challenging due to the limited data, high writing style variance, and scripts with complex diacritics. Existing approaches, though partially address these issues, often struggle to generalize without massive synthetic data. To address these challenges, we propose HTR-ConvText, a model designed to capture fine-grained, stroke-level local features while preserving global contextual dependencies. In the feature extraction stage, we integrate a residual Convolutional Neural Network backbone with a MobileViT with Positional Encoding block. This enables the model to both capture structural patterns and learn subtle writing details. We then introduce the ConvText encoder, a hybrid architecture combining global context and local features within a hierarchical structure that reduces sequence length for improved efficiency. Additionally, an auxiliary module injects textual context to mitigate the weakness of Connectionist Temporal Classification. Evaluations on IAM, READ2016, LAM and HANDS-VNOnDB demonstrate that our approach achieves improved performance and better generalization compared to existing methods, especially in scenarios with limited training samples and high handwriting diversity.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05021
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HTR-ConvText: Leveraging Convolution and Textual Information for Handwritten Text Recognition
Truc, Pham Thach Thanh
Nam, Dang Hoai
Khoa, Huynh Tong Dang
Duy, Vo Nguyen Le
Computer Vision and Pattern Recognition
Machine Learning
Handwritten Text Recognition remains challenging due to the limited data, high writing style variance, and scripts with complex diacritics. Existing approaches, though partially address these issues, often struggle to generalize without massive synthetic data. To address these challenges, we propose HTR-ConvText, a model designed to capture fine-grained, stroke-level local features while preserving global contextual dependencies. In the feature extraction stage, we integrate a residual Convolutional Neural Network backbone with a MobileViT with Positional Encoding block. This enables the model to both capture structural patterns and learn subtle writing details. We then introduce the ConvText encoder, a hybrid architecture combining global context and local features within a hierarchical structure that reduces sequence length for improved efficiency. Additionally, an auxiliary module injects textual context to mitigate the weakness of Connectionist Temporal Classification. Evaluations on IAM, READ2016, LAM and HANDS-VNOnDB demonstrate that our approach achieves improved performance and better generalization compared to existing methods, especially in scenarios with limited training samples and high handwriting diversity.
title HTR-ConvText: Leveraging Convolution and Textual Information for Handwritten Text Recognition
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2512.05021