Robust Text Detection in Natural Scene Images

Yin, XC;Yin, XW;Huang, KZ;Hao, HW

[Yin, Xu-Cheng; Yin, Xuwang] Univ Sci & Technol Beijing, Dept Comp Sci & Technol, Sch Comp & Commun Engn, Beijing 100083, Peoples R China.
[Yin, Xu-Cheng] Univ Sci & Technol Beijing, Beijing Key Lab Mat Sci Knowledge Engn, Sch Comp & Commun Engn, Beijing 100083, Peoples R China.
[Huang, Kaizhu] Xian Jiaotong Liverpool Univ, Dept Elect & Elect Engn, Suzhou 215123, Peoples R China.
[Hao, Hong-Wei] Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE

Volume:36 Issue:5Pages:970-983

DOI:10.1109/TPAMI.2013.182

Publication Year:2014

JCR:Q1

CAS JCR:1区

ESI Discipline:ENGINEERING

Latest Impact Factor:16.389

Document Type:Journal Article

Abstract

Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks. In this paper, we propose an accurate and robust method for detecting texts in natural scene images. A fast and effective pruning algorithm is designed to extract Maximally Stable Extremal Regions (MSERs) as character candidates using the strategy of minimizing regularized variations. Character candidates are grouped into text candidates by the single-link clustering algorithm, where distance weights and clustering threshold are learned automatically by a novel self-training distance metric learning algorithm. The posterior probabilities of text candidates corresponding to non-text are estimated with a character classifier; text candidates with high non-text probabilities are eliminated and texts are identified with a text classifier. The proposed system is evaluated on the ICDAR 2011 Robust Reading Competition database; the f-measure is over 76%%, much better than the state-of-the-art performance of 71%%. Experiments on multilingual, street view, multi-orientation and even born-digital databases also demonstrate the effectiveness of the proposed method. Finally, an online demo of our proposed scene text detection system has been set up at http://prir.ustb.edu.cn/TexStar/scene-text-detection/.

Keywords

Scene text detection maximally stable extremal regions single-link clustering distance metric learning

Copyright 2006-2020 © Xi'an Jiaotong-Liverpool University 苏ICP备07016150号-1 京公网安备 11010102002019号