Detecting Text in Natural Scenes Based on a Reduction of Photometric Effects: Problem of Color Invariance

  • Alain Trémeau
  • Christoph Godau
  • Sezer Karaoglu
  • Damien Muselet
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6626)


In this paper, we propose a novel method for detecting and segmenting text layers in complex images. This method is robust against degradations such as shadows, non-uniform illumination, low-contrast, large signaldependent noise, smear and strain. The proposed method first uses a geodesic transform based on a morphological reconstruction technique to remove dark/light structures connected to the borders of the image and to emphasize on objects in center of the image. Next uses a method based on difference of gamma functions approximated by the Generalized Extreme Value Distribution (GEVD) to find a correct threshold for binarization. The main function of this GEVD is to find the optimum threshold value for image binarization relatively to a significance level. The significance levels are defined in function of the background complexity. In this paper, we show that this method is much simpler than other methods for text binarization and produces better text extraction results on degraded documents and natural scene images.


Text binarization Contrast enhancement Gamma function Photometric invariants Color invariants 


  1. 1.
    Finlayson, G.D., Hordley, S.D., Lu, C., Drew, M.S.: On the Removal of Shadows From Images. IEEE Pattern Analysis and Machine Intelligence (PAMI) 28(1), 59–68 (2006)CrossRefGoogle Scholar
  2. 2.
    Maini, R., Aggarwal, H.: A Comprehensive Review of Image Enhancement Techniques. Journal of Computing 2(3), 8–13 (2010)Google Scholar
  3. 3.
    van de Weijer, J., Gevers, T., Geusebroek, J.M.: Edge and corner detection by photometric quasi-invariants. IEEE Trans. on Pattern Analysis and Machine Intelligence 27(4), 625–630 (2005)CrossRefGoogle Scholar
  4. 4.
    Li, B., Xue, X., Fan, J.: A robust incremental learning framework for accurate skin region segmentation in color images. Pattern Recognition 40(12), 3621–3632 (2007)CrossRefzbMATHGoogle Scholar
  5. 5.
    Moreno-Noguer, F., Sanfeliu, A., Samaras, D.: Integration of deformable contours and a multiple hypotheses Fischer color model for robust tracking in varying illuminant environments. Image and Vision Computing 25, 285–296 (2007)CrossRefGoogle Scholar
  6. 6.
    Trémeau, A., Tominaga, S., Plataniotis, K.: Color in Image and Video Processing: most recent trends and future research directions. EURASIP Journal on Image and Video Processing 2008, article ID 581371, 26 pages (2008)Google Scholar
  7. 7.
    Gevers, T.: Chapter 9: Color feature detection. In: Color Image Processing: Methods and Applications Book, pp. 203–226. CRC Press, Boca Raton (2007)Google Scholar
  8. 8.
    Koschan, A., Abidi, M.: Detection and classification of edges in color images. IEEE Signal Processing Magazine, 64–73 (2005)Google Scholar
  9. 9.
    Salvador, E., Cavallaro, A., Ebrahimi, T.: Cast shadow segmentation using invariant color features. Computer Vision and Image Understanding 95, 238–259 (2004)CrossRefGoogle Scholar
  10. 10.
    Dong, G., Xie, M.: Color clustering and learning for image segmentation based on neural networks. IEEE Trans. on Neural Networks 16, 925–936 (2005)CrossRefGoogle Scholar
  11. 11.
    Karatzas, D., Antonacopoulos, A.: Colour text segmentation in web images based on human perception. Image and Vision Computing 25, 564–577 (2007)CrossRefzbMATHGoogle Scholar
  12. 12.
    Trémeau, A., Fernando, B., Karaoglu, S., Muselet, D.: Detecting text in natural scenes based on a reduction of photometric effects: problem of text detection. In: Proceedings of CCIW 2011. LNCS, vol. 6626, pp. 217–233. Springer, Heidelberg (2011)Google Scholar
  13. 13.
    van de Sande, K.E.A., Gevers, T., Snoek, C.G.M.: Evaluation of color descriptors for object and scene recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 453–464 (2008)Google Scholar
  14. 14.
    Álvarez, J.M., Gevers, T., López, A.M.: Learning Photometric Invariance for Object Detection. Int. J. Comput. Vis. 90, 45–61 (2010)CrossRefGoogle Scholar
  15. 15.
    Lim, J., Park, J., Medioni, G.G.: Text segmentation in color images using tensor voting. Image and Vision Computing 25, 671–685 (2007)CrossRefGoogle Scholar
  16. 16.
    Logvinenko, A.D.: An object-color space. J. Vis. 9(11), 1–23 (2009)CrossRefGoogle Scholar
  17. 17.
    Wyszecki, G., Stiles, W.S.: Color Science: Concepts and Methods, Quantitative Data and Formulae, 2nd edn. Wiley-Interscience, Hoboken (August 2000)Google Scholar
  18. 18.
    Barnard, K.: Practical Colour Constancy, Phd thesis, Simon Fraser University, School of Computing (1999),
  19. 19.
    Rubner, Y., Puzicha, J., Tomasi, C., Buhmann, J.M.: Empirical Evaluation of Dissimilarity Measures for Color and Texture. In: International Conference on Computer Vision, vol. 2, p. 1165 (1999)Google Scholar
  20. 20.
    Chen, S., Beghdadi, A.: Natural enhancement of color image. Eurasip Journal on Image and Video Processing, 19 pages (2010), doi:10.1155/2010/175203Google Scholar
  21. 21.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 2nd edn. Pearson Education, London (2008) ISBN-13: 978-0135052679Google Scholar
  22. 22.
    Soille, P.: Morphological Image Analysis: Principles and Applications, pp. 182–198. Springer, Heidelberg (2003)zbMATHGoogle Scholar
  23. 23.
    Ye, Q., Gao, W., Huang, Q.: Automatic text segmentation from complex background. In: IEEE Int. Conf. on Image Processing, vol. 5, pp. 2905–2908 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Alain Trémeau
    • 1
  • Christoph Godau
    • 2
  • Sezer Karaoglu
    • 2
  • Damien Muselet
    • 1
  1. 1.Laboratoire Hubert CurienUniversity Jean MonnetSaint EtienneFrance
  2. 2.Erasmus Mundus CIMET MasterUniversity Jean MonnetSaint EtienneFrance

Personalised recommendations