In this dissertation, we propose three methods to solve the problem with varying lighting effects. The first method is to achieve document image binarization. The image binarization is a difficult work for digital camera. It needs to find a proper threshold value for image. The threshold value selection will be affected by lightness for digital camera. For solving the problem, we propose a document image binarization method which can avoid lightness influence. The second and the third method are to achieve the detection and compensation of backlight image. In detection part, we use fuzzy inference method to detect the backlight degree of image.
Because an image has different backlight degree, fuzzy inference can effectively and correctly detect the backlight degree. In compensation part, we propose two compensation curves to compensate a backlight image. The two curves are parabolic curve and cubic curve, respectively. We discovered that the advantages of using the two compensation curves are that they can effectively improve image backlight problem and be implemented on hardware. The future works will be oriented toward improvement present technique and hardware implementation of algorithm.
References
[1] B. Gatos, I. Pratikakis, and S.J. Perantonis, “An adaptive binarisation technique for low quality historical documents,” IAPR Workshop on Document Analysis systems (DAS’2004), Lecture Notes in Computer Science (3163), pp. 102-113, Florence Italy.
[2] J. Sauvola and M. Pietik~inen, “Adaptive document image binarization,”
Pattern Recognition, Vol. 33, No. 2, pp. 225- 236, 2000.
[3] M. Seeger and C. Dance, “ Binarising camera images for OCR,” ICDAR, pp.
54–59, 2001.
[4] M. Sezgin and B. Sankur, “Survey over image thresholding techniques and quantitative performance evaluation,” Journal of Electronic Imaging, Vol.
13, No. 1, pp. 146-165, 2004.
[5] R. R. Brooks, Lynne Grewe and S. S. Iyengar, “Recognition in the wavelet domain: A survey”, Journal of Electronic Imaging, pp. 757-784, July 2001.
[6] L. K. Shark and C. Yu, “Denoising by optimal fuzzy thresholding in wavelet domain,” Electronics Letters, Vol. 36, pp. 581 –582, March 2000.
[7] R. D. Nowak and R.G. Baraniuk, “Wavelet-domain filtering for photon imaging systems,” IEEE Trans. on Image Processing, Vol. 8, pp. 666 –678, May 1999.
[8] J. Z. Liu and W. Q. Li, “The automatic thresholding of gray-level pictures via two-dimensional otsu method,” (in Chinese), Acta Automat. Sinica, Vol.
19, pp. 101–105, 1993.
[9] D. M. Tsai, “A fast thresholding selection procedure for multimode and unimodel histograms,” Pattern Recognition Letter, Vol. 16, pp. 653–666, 1995.
[10] N. Otsu, “A thresholding selection method from gray-scale histogram,”
IEEE Trans. Syst., Man, Cybern, Vol. 9, pp. 62–66, 1979.
[11] L. O’Gorman, “Binarization and multithresholding of document images using connectivity,” CVGIP: Graphical Models and Image Processing, Vol.
56, No. 6, pp. 494-506, 1994.
[12] J. Sauvola and M. Pietik¨ainen : Adaptive document image binarization, Pattern Recognition, Vol. 33, pp. 225–236, 2000.
[13] M. Seeger and C. Dance, “Binarising camera images for OCR,” ICDAR, pp.
54-59, 2001.
[14] T. K. Kim, J. K. Paik and B. S. Kang, “Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering,” IEEE Trans. on Consumer Electronics, Vol. 44, pp. 82 –87, February 1998.
[15] R. C. Gonzalez and R. E. Woods, “Digital Image Processing,”
Addison-Wesley, 1992.
[16] Y. Yang and H. Yan “An adaptive logical method for binarization of degraded document images,” Pattern Recognition, pp. 787-807, 33 (2000).
[17] G. W. Snedecor and W. G. Cochran, “Statistical Methods,” Ames, IA: Iowa State Univ. Press, 1989.
[18] M. Cheriet, J. N. Said, and C. Y. Suen, “A Recursive Thresholding Technique for Image Segmentation,” IEEE Trans. Image Processing, Vol. 7, No. 6, pp. 918–921, June 1998.
[19] H. D. Cheng and Y. Sun, “A Hierarchical Approach to Color Image Segmentation Using Homogeneity,” IEEE Trans. Image Processing, Vol. 9, No. 12, pp. 2071-2082, 2000.
[20] Levenshtein, “V. I.: Binary codes capable of correcting deletions,”
insertions and reversals. Sov. Phys. Dokl., pp. 707-710, 6 (1966).
[21] Markus Junker and Rainer Hoch, “On the Evaluation of Document Analysis Components by Recall, Precision, and Accuracy,” Proceedings of ICDAR, pp. 713–716, 1999.
[22] Chun-Ming Tsai and Hsi-Jian Lee, “Binarization of color document images via luminance and saturation color features,” IEEE Transactions on Image Processing, Vol. 11, pp. 434-451, Issue 4, April 2002.
[23] Chiun-Li Chin and Chin-Teng Lin, “Detection and Compensation Algorithm for Backlight Images with Fuzzy Logic and Adaptive Compensation Curve,” International Journal of Pattern Recognition and Artificial Intelligence, Vol. 19, No. 8, pp. 1041-1057, 2005.
[24] A. Morimura, K. Uomori, Y. Kitamura, A. Fujioka, J. Harada, S. Iwamura, and M. Hirota, “A digital video camera system,” IEEE Trans. on Consumer Electronics, Vol. 36, No. 4, pp. 886-875, November 1990.
[25] T. Haruki and K. Kikiuchi, “Video camera system using fuzzy logic,” IEEE Trans. on Consumer Electronics, Vol. 38, No. 3, pp. 624-634, Aug. 1992.
[26] S. Shimizu, T. Kondo, T. Koashi, M. Tsurata, and T. Komura, “A new algorithm for exposure control based on fuzzy logic for video cameras,”
IEEE Trans. on Consumer Electronics, Vol. 38, No. 3, pp. 617-623, August 1992.
[27] M. Murakami and N. Honda, “An exposure control system of video cameras based on fuzzy logic using color information,” Proceedings of the Fifth IEEE International Conference on Fuzzy Systems, Vol. 3, 1996.
[28] T. Kuno and H. Sugiura, “A new automatic exposure system for digital still cameras,” IEEE Trans. on Consumer Electronics, Vol. 44, No. 1, pp.
192-199, February 1998.
[29] J. Q. Huang, “New technique for digital backlight image compensation,”
Master Thesis, Department of Computer Science and Information Engineering, Chung Hua University, Taiwan, June 2001.
[30] R. C. Gonazlea and R. E. Woods, “Digital Image Processing,” second edition, Reading, MA: Addison-Wesley, 1992.
[31] A. K. Jain, “Fundamentals of Digital Image Processing,” Englewood Cliffs, NJ: Prentice-Hall, 1989.
[32] J. Zimmerman, S. Pizer, E. Staab, E. Perry, W. McCartney, and B. Brenton,
“Evaluation of the effectiveness of adaptive histogram equalization for contrast enhancement,” IEEE Trans. Medical Imaging, pp. 304-312, December 1988.
[33] C. M. Tsai and H. J. Lee, “Binarization of color document images via luminance and saturation color features,” IEEE Trans. on Image Processing, Vol. 11, No. 4, April 2002.
[34] C. C. Yang and J. J. Rodriguea, “Efficient luminance and saturation processing techniques for color images,” J. Vis. Commun. Image Represent, Vol. 3, No. 3, pp. 263-277, September 1997.
[35] R. J. Williams and D. Zipser, “A learning algorithm for continually running recurrent neural networks,” Neural Comput., Vol. 1, No. 2, pp. 270–280, 1989.
[36] B. A. Pearlmutter, “Gradient calculations for dynamic recurrent neural networks: a survey,” IEEE Trans. Neural Networks, Vol. 6, pp. 1212–1228, 1995.
[37] S. W. Pich´e, “Steepest descent algorithms for neural-network controllers and filters,” IEEE Trans. Neural Networks, Vol. 5, pp. 198–212, 1994.
[38] D. Guinea, A. Gordaliza, J. Vicente, and M. C. García-Alegre, “CNN based visual processing for industrial inspection,” Proc. of SPIE, Vol. 3966, No.
45, 2000.
[39] C. L. Chang and C. T. Lin, “CNN-based defect inspection in images with regular pattern,” The 16th European Conference on Circuit Theory and Design (ECCTD), pp. I221-I224, 2003.
[40] C. T. Lin and Y. C. Lu, “A neural fuzzy system with fuzzy supervised learning,” IEEE Transactions on Systems, Man, and Cybernetics --- Part B:
Cybernetics, Vol. 26, No. 5, pp. 744-763, 1996.
[41] G. Liu and S. Oe, “Texture image segmentation method based on multilayer CNN,” 12th IEEE Int. Conference on Tools with Artificial Intelligence (ICTAI’00), pp. 147–150, Canada, 2000.
[42] Chin-Teng Lin, Wen-Chang Cheng, and S. F. Liang, “An On-line ICA-Mixture-Model-Based Self-Constructing Neural Fuzzy Network,”
IEEE Transactions on Circuits and Systems Part I: Regular paper, Vol. 52, No. 1, pp. 207-221, 2005.
List of Publication
著作目錄
姓名: 秦群立(Chiun-Li Chin) 已刊登或被接受之期刊論文：
[1] Chiun-Li Chin and Chin-Teng Lin, “Detection and Compensation Algorithm for Backlight Images with Fuzzy Logic and Adaptive Compensation Curve,”
International Journal of Pattern Recognition and Artificial Intelligence, Vol. 19, No. 8, pp. 1041-1057, 2005. (2 點)
[2] Chin-Teng Lin and Chiun-Li Chin, “Using Fuzzy Inference and Cubic Curve to Detect and Compensate Backlight Image,” International Journal of Fuzzy Systems, Vol. 8, No. 1, March 2006. (2 點)
研討會論文：
[1] Chin-Teng Lin, Chiun-Li Chin, Kan-Wei Fan and Chun-Yeon Lin, “A novel architecture for converting single 2D image into 3D effect image,” 2005 9th IEEE International Workshop on Cellular Neural Networks and their Applications, Hsinchu, Taiwan, May 28-30, 2005.
[2] Chin-Teng Lin and Chiun-Li, “An Adaptive Image Binarization Method for Camera-based Document Images,” 18th conference on Computer Vision, Graphics and Image Processing(CVGIP), pp. 1304~1308, 2005. (國內研討會).
Vita
博士候選人學經歷資料
姓名: 秦群立 性別: 男
生日: 中華民國 64 年 4 月 28 日 籍貫: 台灣省台北縣
論文題目: 中文: 高度光線變化影響之影像的分析及處理技術開發
英文: The Development of Analysis and Processing Techniques for Images with Varying Lighting Effects
學歷:
1. 民國 87 年 6 月 中華大學資訊工程系畢業。
2. 民國 89 年 6 月 私立中華大學電機工程研究所畢業。
3. 民國 89 年 9 月 國立交通大學電機及控制工程研究所博士班。
經歷:
1. 民國 92 年至民國 95 年 明道管理學院資訊工程系專任講師