DOI QR코드

DOI QR Code

Text Extraction from Complex Natural Images

  • Kumar, Manoj (Department of Computer Science, Chonnam National University) ;
  • Lee, Guee-Sang (Department of Computer Science, Chonnam National University)
  • Received : 2009.09.01
  • Accepted : 2010.04.15
  • Published : 2010.06.28

Abstract

The rapid growth in communication technology has led to the development of effective ways of sharing ideas and information in the form of speech and images. Understanding this information has become an important research issue and drawn the attention of many researchers. Text in a digital image contains much important information regarding the scene. Detecting and extracting this text is a difficult task and has many challenging issues. The main challenges in extracting text from natural scene images are the variation in the font size, alignment of text, font colors, illumination changes, and reflections in the images. In this paper, we propose a connected component based method to automatically detect the text region in natural images. Since text regions in mages contain mostly repetitions of vertical strokes, we try to find a pattern of closely packed vertical edges. Once the group of edges is found, the neighboring vertical edges are connected to each other. Connected regions whose geometric features lie outside of the valid specifications are considered as outliers and eliminated. The proposed method is more effective than the existing methods for slanted or curved characters. The experimental results are given for the validation of our approach.

Keywords

References

  1. T.N. Dinh, J.H. Park and G.S. Lee, "Low-Complexity Text Extraction in Korean Signboards for Mobile Applications," Proc. IEEE International Conference on Computer and Information Technology, 2008, pp. 333-337.
  2. P. Shivakumara, W. Huang and C.L. Tan, "Efficient Video Text Detection using Edge Feature," Proc. International conference Pattern Recognition, 2008, pp.8-11.
  3. Y. Song, A. Liu, L. Pang, S. Lin, Y. Zhang and S. Tang, "A Novel Image Text Extraction Method Based on K-Means Clustering," Proc. International conference on Information System, 2008, pp.185-190.
  4. P. Dubey, "Edge Based Text Detection for Multi-purpose Application," Proc. International Conference on Signal Processing, 2006, pp.16-20.
  5. C. Li, X.Q.Ding and Y.S.Wu , "Automatic text location in natural scene Images," Proc. International conference of Document Analysis and Recognition, 2001, pp.1069-1073.
  6. X. Li, W. Wang, S. Jiang, Q. Huang and W. Gao, "Fast and effective text detection," IEEE International Conference on Image Processing, 2008, pp.969-972.
  7. Q. Liu, C. Jung, S.K. Kim, Y.S. Moon and J.Y. Kim, "Stroke Filter for Text Localization in Video Images," IEEE International Conference on Image Processing, 2006, pp.1473-1476.
  8. S.A.R. Jafri, M.Boutin and E.J. Delp, "Automatic text area segmentation in natural images," Proc. IEEE International Conference on Imaging Processing, 2008, pp.3196-3199.
  9. A.C. Rodriguez, J.H. Kim, S.H. Kim and Y.B. Fernandez, "English to Spanish Translation of Signboard Images from Mobile Phone Camera," submitted to IEEE Transactions on PAMI,2009.
  10. X. Liu and J.Samarabandu, "Multiscale Edge-Based Text Extraction from Complex Images," Proc. International Conference of Multimedia and Expo, 2006, pp.1721-1724.
  11. F. Faradji, A.H. Rezaie, and M. Ziaratban, "A Morphological-Based License Plate Location," IEEE International Conference on Image Processing, 2007, pp.57-60.
  12. N. Otsu, "A threshold selection method from gray-level histograms," IEEE Trans. Systems Man and Cybernetics, vol.09, Jan. 1979, pp.62-66. https://doi.org/10.1109/TSMC.1979.4310076