Scene text detection with improved receptive field and adaptive feature fusion

Liangjun Wang; Weijie Gu; Yuhang Ji

doi:10.1117/12.2604527

5 October 2021 Scene text detection with improved receptive field and adaptive feature fusion

Liangjun Wang, Weijie Gu, Yuhang Ji

Proceedings Volume 11911, 2nd International Conference on Computer Vision, Image, and Deep Learning; 119110V (2021) https://doi.org/10.1117/12.2604527
Event: 2nd International Conference on Computer Vision, Image and Deep Learning, 2021, Liuzhou, China

Abstract

Regression-based text detection methods are currently the research focuses due to their simple network structure and fast inference speed. However, most of them suffer from limited receptive field of convolutional neural network and simplistic feature-fusing in feature pyramid. As a consequence, the previous algorithms still have many shortcomings, such as difficulty in accurately detecting long texts and the inconsistency across different feature scales. To address these two problems, we first incorporate a densely connected atrous convolutional module into the feature extraction network, accordingly the receptive field is enlarged, and in turn the extraction of high-level semantic information is strengthened. Secondly, we weight and re-fuse the features from different levels of the feature pyramid, which can filter conflicting information at various levels to maintain the scale invariance of features. Extensive experiments have been made on ICDAR2015 and MSRA-TD500 datasets, and the experimental results have proved the effectiveness of the method.

Citation Download Citation

Liangjun Wang, Weijie Gu, and Yuhang Ji "Scene text detection with improved receptive field and adaptive feature fusion", Proc. SPIE 11911, 2nd International Conference on Computer Vision, Image, and Deep Learning, 119110V (5 October 2021); https://doi.org/10.1117/12.2604527

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
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Feature extraction

Convolution

Algorithm development

Visualization

Network architectures

Image resolution

Sensor performance

Keywords/Phrases

Search In:

Publication Years