MSA: an end-to-end scene text spotter with mask-supervised-attention

Xin Chen; Chaoyong Peng; Chunrong Qiu; Xiaorong Gao; Yu Zhang; Min Xu

doi:10.1117/12.2654503

15 December 2022 MSA: an end-to-end scene text spotter with mask-supervised-attention

Xin Chen, Chaoyong Peng, Chunrong Qiu, Xiaorong Gao, Yu Zhang, Min Xu

Proceedings Volume 12478, Thirteenth International Conference on Information Optics and Photonics (CIOP 2022); 124781Q (2022) https://doi.org/10.1117/12.2654503
Event: Thirteenth International Conference on Information Optics and Photonics (CIOP 2022), 2022, Xi'an, China

Abstract

End-to-end(E2E) scene text recognition (the joint detection and recognition of natural text images) is developing rapidly, and the joint optimization strategy for image sequence alignment has become a research hotspot. Those existing methods are either difficult to train or costly for character annotations. In this paper, a novel end-to-end scene text recognition framework is proposed, Based on the Swin-Transformer (Swin-T) FPN backbone network, the model adopts the instance segmentation method to obtain the text mask and binarizes it to directly locate its polygon boundaries. Meanwhile, to solve the problem of low fitting efficiency of the text sequence recognition module, we designed a self-monitoring Mask-Supervised Attention (MSA) mechanism to accelerate the fitting speed and fitting accuracy of the recognition module, thereby improving the joint performance for E2E text recognition. The results show that in the E2E text recognition task, the F-measure performance of the proposed model achieves not only 2.3%, 2.7% and 11.9% improvement on ICDAR 2015 on strong, weak and generic lexicons, but also 4.8%, 9.9% improvement on Total-text on full and none lexicons compared with other typical models.

Citation Download Citation

Xin Chen, Chaoyong Peng, Chunrong Qiu, Xiaorong Gao, Yu Zhang, and Min Xu "MSA: an end-to-end scene text spotter with mask-supervised-attention", Proc. SPIE 12478, Thirteenth International Conference on Information Optics and Photonics (CIOP 2022), 124781Q (15 December 2022); https://doi.org/10.1117/12.2654503

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
11 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Performance modeling

Data modeling

Image segmentation

Feature extraction

Systems modeling

Visual process modeling

Network architectures

Keywords/Phrases

Search In:

Publication Years