DSSNet: a transformer-based network for dense scene text detection and recognition in complex environments

Jing Li; Huabing Zhou

doi:10.1117/12.3053112

3 January 2025 DSSNet: a transformer-based network for dense scene text detection and recognition in complex environments

Jing Li, Huabing Zhou

Author Affiliations +

Proceedings Volume 13442, Fifth International Conference on Signal Processing and Computer Science (SPCS 2024); 134420M (2025) https://doi.org/10.1117/12.3053112
Event: Fifth International Conference on Signal Processing and Computer Science (SPCS 2024), 2024, Kaifeng, China

Abstract

This paper presents a novel approach for dense scene text detection called DSSNet (Dense Script Spotter Network). The network leverages ResNet and FPN for feature extraction, employing multi-scale feature fusion and Transformer-based feature processing to enhance text recognition across varying sizes. The method generates text instance shapes using Bézier central curves and performs text recognition by integrating positional query information. Experimental results on the DSTD1500 and ICDAR2015 datasets demonstrate that DSSNet outperforms existing methods in terms of text localization accuracy, recognition accuracy, and annotation flexibility.

(2025) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jing Li and Huabing Zhou "DSSNet: a transformer-based network for dense scene text detection and recognition in complex environments", Proc. SPIE 13442, Fifth International Conference on Signal Processing and Computer Science (SPCS 2024), 134420M (3 January 2025); https://doi.org/10.1117/12.3053112

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Feature extraction

Detection and tracking algorithms

Transformers

Network architectures

Image segmentation

Visualization

Feature fusion

Show All Keywords

Keywords/Phrases

Search In:

Publication Years