Text Segmentation from Images with Various Light Conditions Based on Gaussian Mixture Model

Title & Authors
Text Segmentation from Images with Various Light Conditions Based on Gaussian Mixture Model
Tran, Khoa Anh; Lee, Gueesang;

Abstract
Standard Gaussian Mixture Model (GMM) is a well-known method for image segmentation. However, one of its problems is that we consider the pixel as independent to each other, which can cause the segmentation results sensitive to noise. It explains why some of existing algorithms still cannot segment texts from the background clearly. Therefore, we present a new method in which we incorporate the spatial relationship between a pixel and its neighbors inside $\small{3{\times}3}$ windows to segment the text. Our approach works well with images containing texts, which has different sizes, shapes or colors in case of light changes or complex background. Experimental results demonstrate the robustness, accuracy and effectiveness of the proposed model in image segmentation compared to other methods.
Keywords
Gaussian Mixture Model (GMM);Image Segmentation;Spatial Neighboring Relationships;Expectation Maximization;
Language
English
Cited by
1.
MSER을 이용한 다중 스케일 영상 분할과 응용,이진선;오일석;

한국콘텐츠학회논문지, 2014. vol.14. 3, pp.11-21
References
1.
W.Niblack, Introduction to Digital Image Processing, Prentice Hall, 1986, pp.115-116.

2.
Omer. D, A. H. Musa, Sahoo. K. Prasanna, Image processing with Matlab, Applications in Medicine and Biology, CRC Press, 2009, pp 269-284.

3.
Carlo Tomasi, Estimating Gaussian Mixture Densities with EM - A Tutorial, Duke University.

4.
C. M. Bishop, Pattern Recognition and Machine Learning, Berlin, Germany: Springer, 2006.

5.
G. J. MacLachlan and T. Krishman, The EM Algorithm and Extensions, Wiley Series in Probability and Statistics. New York: Wiley, 1997.

6.
Gonzalez, Rafael; Richard Woods. Digital Image Processing (3rd ed.). Upper Saddle River, NewJersey: Pearson Education, Inc.. pp. 165-68. ISBN 978-0-13-168728-8.

7.
D. Marr and E.Hildreth. Theory of edge detection. Proc. R. Soc. Lond. A, Math, Phys. Sci, vol. B 207, 1980, pp. 187-217.

8.
H. D. Cheng, X. H. Jiang, Y. Sun, Jingli Wang, "Color image segmentation; Advances and prospets", Pattern Recognition 34.

9.
F. Meyer, "Color image segmentation", Proc. IEE Int. Conf. Image Processing and its Applications, The Netherlands, 1992, pp. 303-306.

10.
N. Otsu, "A threshold selection method from gray-level histograms", IEEE Transactions Systems Man Cybernetics, vol. 9, no. 1, 1979, pp: 62-66.

11.
J. Kittler, J. Illingworth, and J. Foglein, "Threshold selection based on a simple image statistic", Computer Vision, Graphics, and Image Processing, vol. 30, no. 2, 1985, .

12.
D. Ziou, S. Tabbone, "Edge Detection Techniques-An Overview", technical report, No. 195, Dept Math & Informatique, Universit de Sherbrooke, 1997.

13.
Stephen G, Tianshi G, Daphne K, "Region-based Segmentation and Object Detection", NIPS conference, 2009.

14.
Chan, K.C.C, Xudong H, Bao. P, "Fuzzy segmentation for document analysis", IEE Int. Conf. System, Man, and Cybernetics, Computational Cybernetics and Simulation, vol. 2, 1997, pp. 977-982.

15.
Gudnason, J., Brookes. M, "Distribution based classification using Gaussian Mixture Models", IEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), vol. 4, 2002, pp. IV-4159.

16.
B. Gatos, K. Ntirogiannis, and I. Pratikakis, "ICDAR 2009 document image binarization contest (DIBCO 2009)," ICDAR, 2009, pp. 1375-1382.

17.
Thanh Minh Nguyen, Wu, Q.M.J, " Gaussian-Mixture- Model-Based Spatial Neighborhood Relationships for Pixel Labeling Proble", IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics,2012,pp. 193-202.