Advertisement

Text Segmentation in Complex Background Based on Color and Scale Information of Character Strokes

  • Weiqiang Wang
  • Libo Fu
  • Wen Gao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4810)

Abstract

This paper presents a robust approach to segmenting text embedded in complex background. Our approach consists of four steps: smart sampling, unsupervised clustering, the Bayesian decision, post-processing. The experimental results show that it works effectively, and is more efficient in removing complex background residues than the popular K-means method.

Keywords

text segmentation character stroke complex background 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Wu, V., Manmatha, R., Riseman, E.: Finding text in images. In: Proceedings of ACM International Conference on Digital Libraries, Philadelphia, pp. 1–10 (1997)Google Scholar
  2. 2.
    Jain, A.K., Yu, B.: Automatic text location in images and video frames. Pattern Recognition 31(12), 2055–2076 (1998)CrossRefGoogle Scholar
  3. 3.
    Chen, D., Odobez, J-M., Bourlard, H.: Text detection and recognition in images and video frames. Pattern Recognition 3(37), 595–608 (2004)CrossRefGoogle Scholar
  4. 4.
    Ye, Q., Gao, W., Wang, W., Zeng, W.: A robust text detection algorithm in images and video frames. In: 4th IEEE Pacific-Rim Conference on Multimedia, Singapore, pp. 802–806 (2003)Google Scholar
  5. 5.
    Gllavata, J., Ewerth, R., Stefi, T., Freisleben, B.: Unsupervised Text Segmentation Using Color and Wavelet Features. In: Proceedings of the 3rd International Conference on Image and Video Retrieval, Dublin, Ireland, pp. 216–224 (July 2004)Google Scholar
  6. 6.
    Fu, L., wang, W., Zhan, Y.: A robust text segmentation approach in complex background based on multiple constraints. In: Ho, Y.-S., Kim, H.J. (eds.) PCM 2005. LNCS, vol. 3768, pp. 594–605. Springer, Heidelberg (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Weiqiang Wang
    • 1
    • 2
  • Libo Fu
    • 1
  • Wen Gao
    • 1
    • 2
  1. 1.Institute of Computing Technology, CAS, Beijing, 100080China
  2. 2.Graduate School of Chinese Academy of Sciences, CAS, Beijing, 100039China

Personalised recommendations