Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Wang, Zi-Rui
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.18374
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912515387031552
author Wang, Zi-Rui
author_facet Wang, Zi-Rui
contents The segmentation-free research efforts for addressing handwritten text recognition can be divided into three categories: connectionist temporal classification (CTC), hidden Markov model and encoder-decoder methods. In this paper, inspired by the above three modeling methods, we propose a new recognition network by using a novel three-dimensional (3D) attention module and global-local context information. Based on the feature maps of the last convolutional layer, a series of 3D blocks with different resolutions are split. Then, these 3D blocks are fed into the 3D attention module to generate sequential visual features. Finally, by fusing the visual features and the corresponding global-local context features, a well-designed representation can be obtained. Main canonical neural units including attention mechanisms, fully-connected layers, recurrent units and convolutional layers are efficiently organized into a network and can be jointly trained by the CTC loss and the cross-entropy loss. Experiments on the latest Chinese handwritten text datasets (the SCUT-HCCDoc and the SCUT-EPT) and one English handwritten text dataset (the IAM) show that the proposed method can achieve comparable results with the state-of-the-art methods. The code is available at https://github.com/Wukong90/3DAttention-MultiScaleTraining-for-HTR.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18374
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Handwritten Text Recognition via 3D Attention and Multi-Scale Training
Wang, Zi-Rui
Artificial Intelligence
The segmentation-free research efforts for addressing handwritten text recognition can be divided into three categories: connectionist temporal classification (CTC), hidden Markov model and encoder-decoder methods. In this paper, inspired by the above three modeling methods, we propose a new recognition network by using a novel three-dimensional (3D) attention module and global-local context information. Based on the feature maps of the last convolutional layer, a series of 3D blocks with different resolutions are split. Then, these 3D blocks are fed into the 3D attention module to generate sequential visual features. Finally, by fusing the visual features and the corresponding global-local context features, a well-designed representation can be obtained. Main canonical neural units including attention mechanisms, fully-connected layers, recurrent units and convolutional layers are efficiently organized into a network and can be jointly trained by the CTC loss and the cross-entropy loss. Experiments on the latest Chinese handwritten text datasets (the SCUT-HCCDoc and the SCUT-EPT) and one English handwritten text dataset (the IAM) show that the proposed method can achieve comparable results with the state-of-the-art methods. The code is available at https://github.com/Wukong90/3DAttention-MultiScaleTraining-for-HTR.
title Improving Handwritten Text Recognition via 3D Attention and Multi-Scale Training
topic Artificial Intelligence
url https://arxiv.org/abs/2410.18374