Abstract
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.
Chapter PDF
Similar content being viewed by others
References
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)
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)
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)
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 p. (2008)
Gevers, T., van de Weijer, J., Stokman, H.: Color feature detection. In: Color Image Processing: Methods and Applications Book, ch. 9, pp. 203–226. CRC press, Boca Raton (2007)
Koschan, A., Abidi, M.: Detection and classification of edges in color images. IEEE Signal Processing Magazine, 64–73 (January 2005)
Salvador, E., Cavallaro, A., Ebrahimi, T.: Cast shadow segmentation using invariant color features. Computer Vision and Image Understanding 95, 238–259 (2004)
Dong, G., Xie, M.: Color clustering and learning for image segmentation based on neural networks. IEEE Trans. on Neural Networks 16, 925–936 (2005)
Trémeau, A., Godau, C., Karaoglu, S., Muselet, D.: Detecting text in natural scenes based on a reduction of photometric effects: problem of color invariance. In: Schettini, R., Tominaga, S., Trémeau, A. (eds.) CCIW 2011. LNCS, vol. 6626, pp. 234–248. Springer, Heidelberg (2011)
Karatzas, D., Antonacopoulos, A.: Colour text segmentation in web images based on human perception. Image and Vision Computing 25, 564–577 (2007)
Fernando, B., Karaoglu, S., Trémeau, A.: Extreme value theory based text binarization in documents and natural scenes. In: Proceedings of IEEE, ICMV, Hong-Kong (to be published)
Karaoglu, S., Fernando, B., Trémeau, A.: A Novel Algorithm for Text Detection and Localization in Natural Scene Images. In: Proceedings of IEEE, DICTA 2010, Sydney, Australia, December 1-3 (2010) (to be published)
ICDAR 2003 robust reading competitions. In: Proc. of 7th Intl. Conf. on Document Analysis and Recognition, pp. 682–687 (2003)
ICDAR 2003 text locating competition results. In: Proc. of 8th Intl. Conf. on Document Analysis and Recognition, pp. 80–84(1) (2005)
Document Image Binarization Contest (DIBCO 2009) in the framework of ICDAR2009. In: Proc. of 10th Intl. Conf. on Document Analysis and Recognition, pp. 1375–1382 (2009)
Lienhart, R., Wernickle, A.: Localizing and segmenting text in images and videos. IEEE Trans. on Circuits and Systems for Video Technology 12(4), 256–268 (2002)
Niblack, W.: An Introduction to Image Processing, pp. 115–116. Prentice-Hall, Englewood Cliffs (1986)
Sauvola, J., Pietaksinen, M.: Adaptive document image binarization. Pattern Recogn. 33, 225–236 (2000)
Trier, O.D., Taxt, T.: Evaluation of binarization methods for document images. IEEE Trans. Pattern Anal. Machine Intell. 17, 312–315 (1995)
Lim, J., Park, J., Medioni, G.G.: Text segmentation in color images using tensor voting. Image and Vision Computing 25, 671–685 (2007)
Soille, P.: Morphological Image Analysis: Principles and Applications, pp. 182–198. Springer, Heidelberg (2003)
Coles, S.: An Introduction to Statistical Modeling of Extreme Values, pp. 45–50, 75-78. Springer, Heidelberg (2001) ISBN 1-85233-459-2,
Lawless, J.F.: Statistical Models and Methods for Lifetime Data, pp. 211–255. Wiley, New York (1982)
Prescott, P.: Parameter estimation for the generalized extreme value distribution. Journal of Statistical Computation and Simulation 16(3&4), 241–250 (1983)
Pickands, J.: Statistical inference using extreme order statistics. The Annals of Statistics 3, 119–131 (1975)
Behrens, C.N., Lopes, H.F., Gamerman, D.: Bayesian Analysis of Extreme Events with Threshold Estimation. Statistical Modeling 4(3), 227–244 (2004)
Otsu, N.: A threshold selection method from graylevel histograms. IEEE Trans. Systems Man Cybernet. 9(1), 62–66 (1979)
Álvarez, J.M., Gevers, T., López, A.M.: Learning Photometric Invariance for Object Detection. Int. J. Comput. Vis. 90, 45–61 (2010)
Pratikakis, I., Gatos, B., Ntirogiannis, K.: H-DIBCO 2010 - Handwritten Document Image Binarization Competition. In: Proceedings of the 12th International Conference on Frontiers in Handwriting Recognition, pp. 727–732 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Trémeau, A., Fernando, B., Karaoglu, S., Muselet, D. (2011). Detecting Text in Natural Scenes Based on a Reduction of Photometric Effects: Problem of Text Detection. In: Schettini, R., Tominaga, S., Trémeau, A. (eds) Computational Color Imaging. CCIW 2011. Lecture Notes in Computer Science, vol 6626. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-20404-3_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-20404-3_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-20403-6
Online ISBN: 978-3-642-20404-3
eBook Packages: Computer ScienceComputer Science (R0)