TEXT SEGMENTATION FROM WEB IMAGES USING TWO-LEVEL VARIANCE MAPS

Insook Jung, Il-Seok Oh

Abstract

Variance map can be used to detect and distinguish texts from the background in images. However previous variance maps work as one level and they revealed a limitation in dealing with diverse size, slant, orientation, translation and color of texts. In particular, they have difficulties in locating texts of large size or texts with severe color gradation due to specific value in mask sizes. We present a method of robustly segmenting text regions in complex web color images using two-level variance maps. The two-level variance maps works hierarchically. The first level finds the approximate locations of text regions using global horizontal and vertical color variances with the specific mask sizes. Then the second level segments each text region using intensity variation with a local new mask size, in which a local new mask size is determined adaptively. By the second process, backgrounds tend to disappear in each region and segmentation can be accurate. Highly promising experimental results have been obtained using the our method in 400 web images.

References

  1. Jung, I. S., Ham, D. S., and Oh, I. S., 2008. Empirical Evaluation of Color Variance Method for Text Retrieval from Web Images, In Proceeding of the 19th Workshop on Image Processing and Image Understanding (IPIU'08).
  2. Zhou. J., and Lopresti, D., 1997, Extracting Text from WWW Images, Proceedings of the 4th International Conference on Document Analysis and Recognition (ICDAR'97), Ulm, Germany, August.
  3. Antonacopoulos, A., and Delporte, F., 1999, Automated Interpretation of Visual Representations: Extracting textual Information from WWW Images, Visual Representations and Interpretations, R. Paton and I. Neilson (eds.), Springer, London.
  4. Zhou. J., Lopresti, D., and Tasdizen, T., 1998, Finding Text in Color Images, proceedings of the IS&T/SPIE Symposium on Electronic Imaging, San Jose, California, pp. 130-140.
  5. Lopresti, A. D., and Zhou, J., 2000, Locating and Recognizing Text in WWW Images, Information Retrieval, vol. 2, pp. 177-206.
  6. Jain, A. K., and Yu, B., 1998, Automatic Text Location in Images and Video Frames, Pattern Recognition, vol.
  7. Song, Y. J., Kim, K. C., Choi, Y. W., Byun, H. R., Kim, S. H., Chi, S. Y., Jang, D. K., and Chung, Y. K., 2005, Text Region Extraction and Text Segmentation on Camera Captured Document Style Images, Proceedings of the Eight International Conference on Document Analysis and Recognition (ICDAR'05).
  8. Mario, I., and Chucon, M., 1998, Document segmentation using texture variance and low resolution images, Image Analysis and Interpretation, IEEE Southwest Symposium on.
  9. Jung, K. C. and Han, J. H., 2004, Hybrid approach to efficient text extraction in complex color images,
  10. Pattern Recognition Letters, vol. 25, pp. 679-699.
  11. Jung, K. C., Kim, K. I., and Jain, A. K., 2004, Text Information Extraction in Images and Video: A
  12. Survey, Pattern Recognition, vol. 37, no. 5, pp. 977-
Download


Paper Citation


in Harvard Style

Jung I. and Oh I. (2009). TEXT SEGMENTATION FROM WEB IMAGES USING TWO-LEVEL VARIANCE MAPS . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 363-370. DOI: 10.5220/0001808303630370


in Bibtex Style

@conference{visapp09,
author={Insook Jung and Il-Seok Oh},
title={TEXT SEGMENTATION FROM WEB IMAGES USING TWO-LEVEL VARIANCE MAPS },
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={363-370},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001808303630370},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)
TI - TEXT SEGMENTATION FROM WEB IMAGES USING TWO-LEVEL VARIANCE MAPS
SN - 978-989-8111-69-2
AU - Jung I.
AU - Oh I.
PY - 2009
SP - 363
EP - 370
DO - 10.5220/0001808303630370