Fast Lexicon-Based Scene Text Recognition with Sparse Belief Propagation

  title={Fast Lexicon-Based Scene Text Recognition with Sparse Belief Propagation},
  author={J. J. Weinman and E. Learned-Miller and A. Hanson},
  journal={Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)},
  • J. J. Weinman, E. Learned-Miller, A. Hanson
  • Published 2007
  • Computer Science
  • Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)
  • Using a lexicon can often improve character recognition under challenging conditions, such as poor image quality or unusual fonts. We propose a flexible probabilistic model for character recognition that integrates local language properties, such as bigrams, with lexical decision, having open and closed vocabulary modes that operate simultaneously. Lexical processing is accelerated by performing inference with sparse belief propagation, a bottom-up method for hypothesis pruning. We give… CONTINUE READING
    9 Citations

    Figures, Tables, and Topics from this paper

    Scene Text Recognition Using Similarity and a Lexicon with Sparse Belief Propagation
    • 187
    • PDF
    A discriminative semi-Markov model for robust scene text recognition
    • 26
    • PDF
    Whole-Book Recognition
    • Pingping Xiu, H. Baird
    • Computer Science, Medicine
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 2012
    • 27
    Using web search engines to improve text recognition
    • 14
    Scene Text Detection and Recognition: The Deep Learning Era
    • 76
    • PDF
    Figure Text Extraction in Biomedical Literature
    • 19
    • PDF


    A Bayesian framework for fusing multiple word knowledge models in videotext recognition
    • DongQing Zhang, S. Chang
    • Computer Science
    • 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
    • 2003
    • 26
    • PDF
    Fast lexicon-based word recognition in noisy index card images
    • 16
    • PDF
    Improving Recognition of Novel Input with Similarity
    • 25
    • PDF
    Text recognition of low-resolution document images
    • 43
    • PDF
    Fast script word recognition with very large vocabulary
    • M. Schambach
    • Computer Science
    • Eighth International Conference on Document Analysis and Recognition (ICDAR'05)
    • 2005
    • 15
    • PDF
    An Embedded Application for Degraded Text Recognition
    • 40
    • PDF
    Sparse Forward-Backward Using Minimum Divergence Beams for Fast Training Of Conditional Random Fields
    • 73
    • Highly Influential
    • PDF
    Piecewise Training for Undirected Models
    • 196
    • PDF
    Factor graphs and the Sum-Product Algorithm
    • 3,057