CRNN with 2D attention for word recognition of English exams

Xinbo Zhao; Zhixiang Xiong; Tingzhen Li; Yin Wang

doi:10.1117/12.2589362

27 January 2021 CRNN with 2D attention for word recognition of English exams

Xinbo Zhao, Zhixiang Xiong, Tingzhen Li, Yin Wang

Proceedings Volume 11720, Twelfth International Conference on Graphics and Image Processing (ICGIP 2020); 117201E (2021) https://doi.org/10.1117/12.2589362
Event: Twelfth International Conference on Graphics and Image Processing, 2020, Xi'an, China

Abstract

Word recognition is a basic task for intelligent K-12 education, which leads to further complex tasks including grammar checking, composition grading, etc. However, there is little study about recognition of students’ handwritten words. We propose a novel convolutional recurrent neural network architecture that combines attention mechanism with connectionist time classification loss for student handwritten words. And the method also performs excellently in handwritings of adults. With an ablation study, we show that our method is better than its counterpart without attention. The CRNN with attention model we proposed achieve superior performance on word recognition and has the potential to support applications of intelligent K-12 education.

Citation Download Citation

Xinbo Zhao, Zhixiang Xiong, Tingzhen Li, and Yin Wang "CRNN with 2D attention for word recognition of English exams", Proc. SPIE 11720, Twelfth International Conference on Graphics and Image Processing (ICGIP 2020), 117201E (27 January 2021); https://doi.org/10.1117/12.2589362

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