Open-Set Text Recognition via Character-Context Decoupling
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4513-4522
Abstract
The open-set text recognition task is an emerging chal-lenge that requires an extra capability to cognize novel characters during evaluation. We argue that a major cause of the limited performance for current methods is the con-founding effect of contextual information over the visual information of individual characters. Under open-set sce-narios, the intractable bias in contextual information can be passed down to visual information, consequently im-pairing the classification performance. In this paper, a Character-Context Decoupling framework is proposed to alleviate this problem by separating contextual information and character-visual information. Contextual information can be decomposed into temporal information and lin-guistic information. Here, temporal information that mod-els character order and word length is isolated with a de-tached temporal attention module. Linguistic information that models n- gram and other linguistic statistics is sepa-rated with a decoupled context anchor mechanism. A va-riety of quantitative and qualitative experiments show that our method achieves promising performance on open-set, zero-shot, and close-set text recognition datasets.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2020AAA09701)
- National Science Fund for Distinguished Young Scholars (62125601)
- National Natural Science Foundation of China (62006018,62076024)
This publication has 38 references indexed in Scilit:
- ASTER: An Attentional Scene Text Recognizer with Flexible RectificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- YOLO9000: Better, Faster, Stronger2017
- An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Synthetic Data for Text Localisation in Natural Images2016
- A robust arbitrary text detection system for natural scene imagesExpert Systems with Applications, 2014
- Toward Open Set RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- CASIA Online and Offline Chinese Handwriting Databases2011
- ICDAR 2003 robust reading competitions: entries, results, and future directionsInternational Journal on Document Analysis and Recognition (IJDAR), 2005
- Explaining 'explaining away'IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993