• Home
  • Search
  • HRNet Encoder and Dual-Branch Decoder Framework-Based Scene Text Recognition Model
  • Cite Icon1
  • https://doi.org/10.1155/2022/2996862Copy DOI Icon

HRNet Encoder and Dual-Branch Decoder Framework-Based Scene Text Recognition Model

Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Scene text recognition (STR) is designed to automatically recognize the text content in natural scenes. Different from regular document text, text in natural scenes has the characteristics of irregular shapes, complex background, and distorted and blurred contents, which makes STR challenging. To solve the problems of STR for distorted, blurred, and low-resolution texts in natural scenes, this paper proposes a HRNet encoder and dual-branch decoder framework-based STR model. The model mainly consists of an encoder module and a dual-branch decoder module composed of a super-resolution branch and a recognition branch in parallel. In the encoder module, the HRNet is adopted to realize the cross-parallel aggregation representation with multiple resolutions during feature extraction and then outputs four kinds of feature maps with different resolutions. Moreover, the supervised attention module is used to strengthen the learning of the important feature information. In the decoder module, the dual-branch structure is adopted, in which the super-resolution branch takes the feature maps with the highest resolution obtained in the encoder module as input and restores images by upsampling through transposed convolution. The four kinds of feature maps with different resolutions are fused through independent transposed convolution layers for multiscale fusion in the recognition branch and then inputted into the attention-based decoder for text recognition. To improve the accuracy of text recognition, the feature extraction effect of the encoder module is together supervised by the super-resolution branch loss and the recognition branch loss. In addition, the super-resolution branch is only used for training and is abandoned during testing to reduce the complexity of the model. The proposed model is trained on Synth90K and SynthText datasets and tested on seven natural scene datasets. Compared with classical models such as ASTER, TextSR, and SCGAN, the recognition accuracy of the proposed model is improved and better recognition results can be achieved on irregular and blurred datasets such as IC15, SVTP, and CUTE80.

Loading PDF

Similar Papers
  • Research Article
  • Citations5

A Deep Learning-Based Text Detection and Recognition Approach for Natural Scenes

  • Oct 27, 2022
  • Journal of Circuits, Systems and Computers
  • Xuexiang Li
  • Conference Article
  • Citations6

Vietnamese Scene Text Detection and Recognition using Deep Learning: An Empirical Study

  • Jul 29, 2022
  • Nhat Truong Pham +5
  • Conference Article
  • Citations4

Research on Text Recognition of Natural Scenes for Complex Situations

  • Jul 22, 2022
  • Wenhua Yu +2
  • Research Article
  • Citations10

Soft set-based MSER end-to-end system for occluded scene text detection, recognition and prediction

  • Oct 18, 2024
  • Knowledge-Based Systems
  • Alloy Das +4
  • Conference Article
  • Citations54

Unconstrained scene text and video text recognition for Arabic script

  • Apr 01, 2017
  • Mohit Jain +2
  • Research Article
  • Citations117

Scene text detection and recognition with advances in deep learning: a survey

  • Mar 27, 2019
  • International Journal on Document Analysis and Recognition (IJDAR)
  • Xiyan Liu +2
  • Research Article
  • Citations25

Cursive-Text: A Comprehensive Dataset for End-to-End Urdu Text Recognition in Natural Scene Images

  • May 21, 2020
  • Data in Brief
  • Asghar Ali Chandio +3
  • Book Chapter
  • Citations7

How Far Deep Learning Systems for Text Detection and Recognition in Natural Scenes are Affected by Occlusion?

  • Jan 01, 2021
  • Aline Geovanna Soares +2
  • PDF
  • Research Article
  • Citations6

CNN and Fuzzy Rules Based Text Detection and Recognition from Natural Scenes

  • Jan 01, 2022
  • Computer Systems Science and Engineering
  • T Mithila +2
  • PDF
  • Research Article
  • Citations22

A Convolutional Recurrent Neural-Network-Based Machine Learning for Scene Text Recognition Application

  • Apr 02, 2023
  • Symmetry
  • Yiyi Liu +2
  • Conference Article
  • Citations9

STIRER: A Unified Model for Low-Resolution Scene Text Image Recovery and Recognition

  • Oct 26, 2023
  • Minyi Zhao +3
  • Conference Article
  • Citations4

Urdu-Text: A Dataset and Benchmark for Urdu Text Detection and Recognition in Natural Scenes

  • Sep 01, 2019
  • Asghar Ali +1
  • Conference Article
  • Citations12

Occluded Text Detection and Recognition in the Wild

  • May 01, 2022
  • Zobeir Raisi +1
  • Conference Article

STV2k

  • Aug 19, 2016
  • Pingping Xiao +3
  • Conference Article
  • Citations68

Dictionary-guided Scene Text Recognition

  • Jun 01, 2021
  • Nguyen Nguyen +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.