.png){kind=icon}
.png){kind=icon}
Return
STAN: A sequential transformation attention-based network for scene text recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2020.107692.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Scene text with an irregular layout is difficult to recognize. To this end, a Sequential Transformation Attention-based Network (STAN), which comprises a sequential transformation network and an attention-based recognition network, is proposed for general scene text recognition. The sequential transformation network rectifies irregular text by decomposing the task into a series of patch-wise basic transformations, followed by a grid projection submodule to smooth the junction between neighboring patches. The entire rectification process is able to be trained in an end-to-end weakly supervised manner, requiring only images and their corresponding groundtruth text. Based on the rectified images, an attention-based recognition network is employed to predict a character sequence. Experiments on several benchmarks demonstrate the state-of-the-art performance of STAN on both regular and irregular text. (C) 2020 Elsevier Ltd. All rights reserved.
Keywords:
Scene text recognition
Scene text rectification
Optical character recognition
Deep learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W