Text Segmentation from Images with Various Light Conditions Based on Gaussian Mixture Model
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
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 3x3 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.
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 3x3 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.
참고문헌 (17)
- W.Niblack, "Introduction to Digital Image Processing", pp.115~116 (1986), Prentice Hall
- Omer. D, "Image processing with Matlab, Applications in Medicine and Biology", pp.269~284 (2009), CRC Press
- Carlo Tomasi, "Estimating Gaussian Mixture Densities with EM – A Tutorial", Duke University
- C. M. Bishop, "Pattern Recognition and Machine Learning" (2006), Springer
- G. J. MacLachlan, "The EM Algorithm and Extensions, Wiley Series in Probability and Statistics" (1997), Wiley
- Gonzalez, Rafael, "Digital Image Processing (3rd ed.)", pp.165~168, Pearson Education, Inc.
- D. Marr, "Theory of edge detection", Proc. R. Soc. Lond. A, Math, Phys. Sci, B 207, pp.187~217 (1980)
- H. D. Cheng, "Color image segmentation; Advances and prospets", Pattern Recognition, 34
- F. Meyer, "Color image segmentation", Proc. IEE Int. Conf. Image Processing and its Applications, pp.303~306 (1992)
- N. Otsu, "A threshold selection method from gray-level histograms", IEEE Transactions Systems Man Cybernetics, 9(1), pp.62~66 (1979)
- J. Kittler, "Threshold selection based on a simple image statistic", Computer Vision, Graphics, and Image Processing, 30(2) (1985)
- Edge Detection Techniques-An Overview, "D. Ziou", Dept Math & Informatique, Universit de Sherbrooke, ~, pp.technical report, No. 195 (1997)
- Stephen G, "Region-based Segmentation and Object Detection", NIPS conference (2009)
- Chan, K.C.C, "Fuzzy segmentation for document analysis", IEE Int. Conf. System, Man, and Cybernetics, Computational Cybernetics and Simulation, 2, pp.977~982 (1997)
- Gudnason, J., "Distribution based classification using Gaussian Mixture Models", IEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), 4, pp.IV-4159~ (2002)
- B. Gatos, "ICDAR 2009 document image binarization contest (DIBCO 2009)", ICDAR, pp.1375~1382 (2009)
- Thanh Minh Nguyen, "Gaussian-Mixture- Model-Based Spatial Neighborhood Relationships for Pixel Labeling Proble", IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, pp.193~202 (2012)