Accurate and robust text detection: A step-in for text retrieval in natural scene images

Xu Cheng Yin*, Xuwang Yin, Kaizhu Huang, Hong Wei Hao

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

19 Citations (Scopus)

Abstract

We propose and implement a robust text detection system, which is a prominent step-in for text retrieval in natural scene images or videos. Our system includes several key components: (1) A fast and effective pruning algorithm is designed to extract Maximally Stable Extremal Regions as character candidates using the strategy of minimizing regularized variations. (2) Character candidates are grouped into text candidates by the single-link clustering algorithm, where distance weights and threshold of clustering are learned automatically by a novel self-training distance metric learning algorithm. (3) The posterior probabilities of text candidates corresponding to non-text are estimated with an character classifier; text candidates with high probabilities are then eliminated and finally texts are identified with a text classifier. The proposed system is evaluated on the ICDAR 2011 Robust Reading Competition dataset and a publicly available multilingual dataset; the f measures are over 76% and 74% which are significantly better than the state-of-the-art performances of 71% and 65%, respectively.

Original languageEnglish
Title of host publicationSIGIR 2013 - Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval
Pages1091-1092
Number of pages2
DOIs
Publication statusPublished - 2013
Event36th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2013 - Dublin, Ireland
Duration: 28 Jul 20131 Aug 2013

Publication series

NameSIGIR 2013 - Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval

Conference

Conference36th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2013
Country/TerritoryIreland
CityDublin
Period28/07/131/08/13

Keywords

  • Distance metric learning
  • Maximally stable extremal regions
  • Scene text detection
  • Single-link clustering

Fingerprint

Dive into the research topics of 'Accurate and robust text detection: A step-in for text retrieval in natural scene images'. Together they form a unique fingerprint.

Cite this