%0 Journal Article
%A CHEN Jie
%A FAN Gaojuan
%A YANG Shuailei
%A ZONG Ruixing
%A ZHANG Chongsheng
%T Transformer Based Scene Character Detection over Low Quality Images
%D 
%R 10.13190/j.jbupt.2021-155
%J Journal of Beijing University of Posts and Telecommunications
%P 124-130
%V 45
%N 2
%X In order to solve the problem of character-level scene text detection and recognition under imperfect imaging conditions, a Transformer based scene character detection algorithm is proposed. Firstly, a Transformer based encoding-decoding structure is designed which takes the order of characters in the text instances into account, so as to output the position and order of sequence information of each character detection box can be output. Then, the Hungarian algorithm is used to calculate the loss of the algorithm which combines bounding box coordinates and ranking losses. Finally, through the experiments on three character-level annotated data sets, we show that under different evaluation metrics, the proposed method is able to achieve good performance on in terms of both scene character localization and recognition.
%U https://journal.bupt.edu.cn/EN/10.13190/j.jbupt.2021-155