Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Improving Translational Accuracy

Improving Translational Accuracy

Fixing Double-strand Breaks

Fixing Double-strand Breaks

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Subnanometer Ru Sites on CeO<sub>2</sub> Oxygen Vacancy Clusters: A Highly Efficient and Durable Catalyst for Ammonia Decomposition.

Journal of the American Chemical Society·2026

Same author

Single Ce atom-assisted oxygen vacancies as active and stable sites for CO<sub>2</sub> conversion.

Nature communications·2026

Same author

Dual inhibition of caspase-11 pyroptosis and NLRP3 inflammasome by Huanglian Jiedu Decoction: A polypharmacological strategy for sepsis management.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026

Same author

Direct Insight into the Role of Cationic Lactam Nitrogen on Oxygen Electroreduction.

ACS applied materials & interfaces·2026

Same author

Reaction-induced modification of Co nanoclusters driven by Co-Mn interfacial sites to control selectivity in CO<sub>2</sub> hydrogenation.

Nature communications·2026

Same author

Development of Two In Vitro ND1-LHON Models for Evaluating Gene Therapy Efficacy.

Investigative ophthalmology & visual science·2025

Search research articles

Related Experiment Video

Updated: Jun 3, 2025

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

Text Font Correction and Alignment Method for Scene Text Recognition.

Liuxu Ding¹, Yuefeng Liu¹, Qiyan Zhao¹

¹School of Digital and Intelligent Industry, Inner Mongolia University of Science and Technology, Baotou 014010, China.

Sensors (Basel, Switzerland)

|January 8, 2025

Summary

This study introduces novel methods for robust text recognition, improving accuracy for arbitrary-shaped and occluded text in natural scenes. The developed Discriminative Standard Text Font (DSTF) and Feature Alignment and Complementary Fusion (FACF) enhance text recognition performance.

Keywords:

attention feature fusion scene text recognition text font alignment

More Related Videos

Comparing the Frequency Effect Between the Lexical Decision and Naming Tasks in Chinese

Comparing the Frequency Effect Between the Lexical Decision and Naming Tasks in Chinese

Published on: April 1, 2016

High-Accuracy Correction of 3D Chromatic Shifts in the Age of Super-Resolution Biological Imaging Using Chromagnon

High-Accuracy Correction of 3D Chromatic Shifts in the Age of Super-Resolution Biological Imaging Using Chromagnon

Published on: June 16, 2020

Related Experiment Videos

Last Updated: Jun 3, 2025

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

Comparing the Frequency Effect Between the Lexical Decision and Naming Tasks in Chinese

Comparing the Frequency Effect Between the Lexical Decision and Naming Tasks in Chinese

Published on: April 1, 2016

High-Accuracy Correction of 3D Chromatic Shifts in the Age of Super-Resolution Biological Imaging Using Chromagnon

High-Accuracy Correction of 3D Chromatic Shifts in the Age of Super-Resolution Biological Imaging Using Chromagnon

Published on: June 16, 2020

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Text recognition in natural scenes is challenging due to irregular text shapes, fonts, and occlusions.
Existing methods struggle with the variability and complexity of real-world text images.

Purpose of the Study:

To develop an improved text recognition system capable of handling arbitrary-shaped text, irregular fonts, and occlusions.
To introduce a new dataset, the VBC Chinese dataset, for evaluating text recognition under diverse lighting conditions.
To enhance the accuracy and robustness of text recognition in natural scene images.

Main Methods:

Designed Discriminative Standard Text Font (DSTF) for handling irregular text fonts.
Developed Feature Alignment and Complementary Fusion (FACF) for arbitrary-shaped text.
Proposed Dual Attention Serial Module (DASM) to address text occlusion by enhancing focus on text texture.
Created the VBC Chinese dataset with varying lighting conditions (strong light, weak light, darkness).

Main Results:

The proposed method achieved 90.8% accuracy on the VBC Chinese dataset.
An overall average accuracy of 93.8% was obtained, demonstrating competitive performance.
The integrated components effectively corrected irregular text and improved feature alignment.

Conclusions:

The novel approach significantly improves text recognition accuracy and robustness in challenging natural scenes.
The developed methods and dataset contribute to advancing the field of scene text recognition.
The system demonstrates strong performance under diverse and adverse lighting conditions.