Sorry, you need to enable JavaScript to visit this website.

TEXT RECOGNITION IN IMAGES BASED ON TRANSFORMER WITH HIERARCHICAL ATTENTION

Primary tabs

Citation Author(s):
Yiwei Zhu, Shilin Wang, Zheng Huang and Kai Chen
Submitted by:
yiwei zhu
Last updated:
18 September 2019 - 10:32am
Document Type:
Poster
Document Year:
2019
Event:
Paper Code:
2933

Abstract 

Abstract: 

Recognizing text in images has been a hot research topic in computer vision for decades due to its various application. However, the variations in text appearance in term of perspective distortion, text line curvature, text styles, etc., cause great trouble in text recognition. Inspired by the Transformer structure that achieved outstanding performance in many natural language processing related applications, we propose a new Transformer-like structure for text recognition in images, which is referred to as the Hierarchical Attention Transformer Network (HATN). The entire network can be trained end-to-end by using only images and sentence-level annotations. A new hierarchical attention mechanism is proposed to lean the character-level, word-level and sentence-level contexts more efficiently and sufficiently. Extensive experiments on seven public datasets with regular and irregular text arrangements have demonstrated that the proposed HATN can achieve accurate recognition results with high efficiency.

up
3 users have voted: yiwei zhu, Jiana Yang, CHeng Guan

Dataset Files

yiweizhu_poster.pdf

(118)