本論文提出了一套應用於結核菌顯微影像之自動結核菌判讀系統，達到自動取像並且將影像傳回伺服器進行結核菌判讀，偵測結核菌區域，並針對檢出區域加以判讀的目的，並將其結果建立為資料庫，以方便醫檢師查看並修改。
整個系統可以分為多解析度自動對焦系統、結核菌判讀系統與結核菌資料庫系統。(1)在多解析度自動對焦系統方面，我們建置一個三維空間之自動化取樣顯微平台，並發展多解析度顯微影像自動對焦演算法，以達到自動聚焦與取像動作。(2)在結核菌判讀方面，我們提出了一套以色彩為基礎之自動化結核菌判讀系統，包含了顯微影像亮度補償、影像色彩標準化等步驟，以降低在染色情況以及拍攝條件不同時所造成的顯微影像之色彩差異。結核菌區域偵測的目的為將在顏色上與結核菌色彩分布相近的像素分割出來，其中包含了結核菌候選區域偵測和計算特徵參數等步驟。並使用向後順序浮動搜尋法(sequential backward floating search, SBFS)挑選特徵。而在結核菌候選區域分類的階段，為了解決之前研究在辨識時遭遇的偽陽性率過高的問題，我們利用整合式分類器Ada-boost以提升辨識的敏感度。(3)在資料庫系統方面，將各醫院或醫療機構所傳回之影像儲存，並執行結核菌判，將辨識結果儲存於資料庫。針對各醫院或醫療機構儲存相對應之訓練資料、辨識結果，供醫檢師查看及驗證，並可修改其圈選結果，加強辨識效果。

This thesis presents an automated mycobacterium tuberculosis (TB) microscopic identification system to capture images automatically, to transfer images back to the server for TB identification, to detect and identify TB zones, and to save the result in database for later review and modify by medical technicians.
The system can be subdivided into three subsystems: the multi-resolution auto-focusing system, automatic mycobacterium tuberculosis identification system and TB database system. (1) In the multi-resolution auto-focusing system, a three-dimensional automated sampling microscopy platform was built which provides automatic focusing and image acquisition for TB specimens. In autofocus searching, different resolution images were used in multi-resolution auto-focusing algorithm to reduce the time spent in finding focus. The experiments showed that the proposed two-stage focus searching algorithms can find the exact focusing position effectively.
(2) In the TB identification, we propose a color-based automatic mycobacterium tuberculosis identification system. The subsystem is divided into three stages: smear image normalization, TB region detection and identification of tuberculosis characteristics. The purpose of smear image normalization is to solve the variant image quality problems which arise from different image acquisition conditions, e.g. microscopic image brightness compensation and image color normalization. Image colors were normalized to reduce the color difference between the microscopic images. The way to detect TB areas was to look for pixels whose colors have similar color distribution of TB. This detection process contains candidate TB region detection and corresponding characteristic parameters calculation. After labeling and morphological processing, TB can be segmented out from the candidate region, and then the characteristic parameters were calculated. Next, the sequential backward floating search (SBFS) algorithm was applied for the feature selection. To reduce the high false positive rate in TB region detection, the Ada-boost algorithm was used to automatically select the weak classifiers which have high identification ability. The experiments in this study showed the strong classifier produced by Ada-boost algorithm could significantly reduce the false positive identification rate.
(3) An image which is transmitted from hospital or medical institution will be first saved in the database. Then TB identification processes will be performed on the image. Finally the results will be saved in the database. The professional medical staff can review and verify the results from the database later. The database can later be used for further training TB identification algorithm and the system capability can thus be further strengthened.

[1] 行政院衛生署,“結核病十年減半全民動員計畫,” 行政院衛生署, 2006。
[2] 呂喬洋、林碧芬, “建立標準結核菌實驗室,” 行政院衛生署疾病管制局九十一年度科技研究發展計畫研究報告, 2003。
[3] 呂金河, “多變量分析”, John Willey, 2005。
[4] 林展頤, “應用自動彩色顯微影像分割之結核菌偵測與評估”, 成功大學資訊工程所碩士論文, 2009。
[5] 徐福瑜, “基於漸進式自動對焦與色彩分割之結核菌顯微影像自動檢測系統”, 成功大學資訊工程所碩士論文, 2011。
[6] 章少謙, “應用色彩資訊於顯微影像之自動腫瘤細胞分割與參數統計”, 成功大學資訊工程所碩士論文, 2007。
[7] A.P. Dempster, N.M. Laird, and D.B. Rubin, “Maximum Likelihood from Incomplete Data via the EM Algorithm,” Journal of the Royal Statistical Society. Series B (Methodological), vol. 39, no. 1, pp. 1-38, 1977.
[8] A.M. Eskicioglu, P.S. Fisher, “Image quality measures and their performance,” IEEE Transactions on Communication, vol. 43, no. 12, pp. 2959-2965, 1995.
[9] A. C. Rencher, ”Multivariate Statistical Inference and Applications,” John Wily and Sons, vol. 40, no. 4, pp. 353-354, 1998.
[10] A.S. de Boer, B. Blommerde, P.E.W. de Haas, M.G. Sebek, K.S.B. Lambregts-van Weezenbeek, M. Dessens, and D. van Soolingen, “False-Positive Mycobacterium tuberculosis Cultures in 44 Laboratories in Netherlands (1993 to 2000): Incidence, Risk Factors, and Consequences,” Journal of Clinical Microbiology, vol. 40, no. 11, pp. 4004-4009, 2002.
[11] B.L. Stone, W.J. Burman, M.V. Hildred, E.A. Jarboe, R.R. Reves, and M.L. Wilson, “The Diagnostic Yield of Acid-Fast-Bacillus Smear-Positive Sputum Specimens,” Journal of Clinical Microbiology, vol. 35, no. 4, pp. 1030–1031, 1997.
[12] B. Zhang, X. Wu, J. You, Q. Li, and F. Karray, “Detection of microaneurysms using multi-scale correlation coefficients,” Pattern Recognition, vol. 43, no. 6, pp. 2237-2248, 2010.
[13] D.E. Rumelhart and J.L. McClelland, “Parallel Distribute processing: Exploration in the Microstructure of Cognition,” MIT Press Cambridge, MA, USA, vol. 1, 1986.
[14] D.L. Ruderman, T.W. Cronin, and C.-C. Chiao, “Statistics of cone responses to natural images: implications for visual coding,” Journal of the Optical Society of America A, vol. 15, no. 8, pp. 2036-2045, 1998.
[15] E.P. Krotkov, “Active Computer Vision by Cooperative Focus and Stereo”, New York: Springer-Verlag, 1989.
[16] E. Reinhard and M. Ashikhmin et al., “Color transfer between images,” IEEE Computer Graphics and Applications, vol. 21, no. 5, pp. 34-41, 2001.
[17] F. Rosenblatt, “The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain, Cornell Aeronautical Laboratory,” Psychological Review, vol. 65, no. 6, pp. 386-408, 1958.
[18] G.S. Beveridge and R.S. Schechter, “Optimization: Theory and Practice”, McGraw-Hill, New York, 1970.
[19] G. Mark, K. Nasser and R.H. Katie, “Low-Light Auto-Focus Enhancement for Digital and Cell-Phone Camera Image Pipelines,” IEEE Transactions on Consumer Electronics, vol. 53, no. 2, pp. 249-257, 2007.
[20] I.T. Jolliffe, Principal Component Analysis, Springer-Verlag, pp. 487, 1986.
[21] I. Maglogiannis, CN. Doukas, “Overview of advanced computer vision systems for skin lesions characterization," IEEE Transactions on Information Technology in Biomedicine, vol. 13, no. 5, pp. 721-733, 2009.
[22] J.M. Tenenbaum, “Accommodation in computer vision,” Ph.D thesis, Stanford University, CA, USA, 1971.
[23] J. Baina and J. Dublet, “Automatic Focus and Iris Control for Video Cameras”, the Fifth International Conference on Image Processing and its Applications, pp. 232-235, 1995.
[24] J. Latin, D. Carroll, and P. E. Green, “Analyzing Multivariate Data,” Duxbruy, 2003.
[25] K. Pearson, "On Lines and Planes of Closest Fit to Systems of Points in Space", Philosophical Magazine, vol. 2, no. 6, pp. 559-572, 1901.
[26] K. Veropoulos, C. Campbell, and G. Learnmonth, “Image processing and neural computing used in the diagnosis of tuberculosis,” IEE Colloquium on Intelligent Methods in Healthcare and Medical Applications, pp. 1-4, 1998.
[27] L.C. Ku, “Auto Focusing under Microscopic Views”, IEEE Workshop on Signal Processing Systems, pp. 533-538, 2007.
[28] M.G. Forero, E.L. Sierra, J. Alvarez, J.L. Pech, G. Cristóbal, L. Alcalá, and M. Desco, “Automatic sputum color image segmentation for tuberculosis diagnosis, ” Proceedings of SPIE, vol. 4471, pp. 251-261, 2001.
[29] M.G. Forero, F. Sroubek, J. Alvarez, N. Malpica, G. Cristóbal, A. Santos, L. Alcala, M. Desco, and L. Cohen, “Segmentation, autofocusing and signature extraction of tuberculosis sputum images,” Proceedings of SPIE, vol. 4788, pp. 171-182, 2002.
[30] M.G. Forero, F. Sroubek, and G. Cristóbal, “Identification of tuberculosis bacteria based on shape and color,” Real-Time Imaging, vol. 10, no. 4, pp. 251-262, 2004.
[31] M. Niemeijer, B. van Ginneken, J. Staal, M.S.A. Suttorp-Schulten, M.D Abramoff, “Automatic detection of red lesions in digital color fundus photographs”, IEEE Transactions on Medical Imaging, vol. 24, no. 5, pp. 584-592, 2005.
[32] M.G. Forero and G. Cristóbal, “Automatic identification of Mycobacterium tuberculosis by Gaussian Mixture Models,” Journal of Microscopy, vol. 223, no.2, pp. 120-132, 2006.
[33] M.G. Costa, C.F.M. Filho, J.F. Sena, J. Salem, and M.O. de Lima, “Automatic identification of mycobacterium tuberculosis with conventional light microscopy,” IEEE Engineering in Medicine and Biology Society, pp. 382-385, 2008.
[34] M. Moscaritolo, H. Jampel, F. Knezevich, R. Zeimer, “An Image Based Auto-Focusing Algorithm for Digital Fundus Photography,” IEEE Transactions on Medical Imaging, vol. 28, no. 11, pp. 1703-1707, 2009.
[35] M.K. Osman, M.Y. Mashor, and H. Jaafar, “Improving Performance of Hybrid Multilayered Perceptron Network for Classification of Mycobacterium tuberculosis in Tissue using Modified Recursive Prediction Error-Extreme Learning Machine,” International Journal of Research and Reviews in Soft and Intelligent Computing, vol. 1, no. 3, pp. 56-65, 2011
[36] N. OTSU, “A Threshold Selection Method from Gray-level Histogram,” IEEE Transactions on Systems, Man and Cybernetics, vol. 9, no. 1, pp. 62-66, 1979.
[37] N.K. Chern, P.A. Neow, and M.H. Ang, “Practical Issues in Pixel-Based Auto focusing for Machine Vision”, Proceedings of the IEEE International Conference on Robotics and Automation, vol. 3, pp. 2791-2796, 2001.
[38] N.N. Tsiaparas, I. Andreadis, I. Valavanis, and K.S. Nikita, “Comparison of Multiresolution Features for Texture Classification of Carotid Atherosclerosis From B-Mode Ultrasound”, IEEE transactions on information technology in biomedicine, vol. 15, no. 1, pp. 130-137, 2011
[39] P. Pudil *, J. Novovičová, J. Kittler, “Floating search methods in feature selection”, Pattern Recognition Letters, vol.15, no. 11, pp. 1119-1125, 1994
[40] P.A. Viola, M.J. Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features”, Computer Vision and Pattern Recognition, vol. 1, pp. 511-518, 2001.
[41] R.A. Fisher, “The use of multiple measurements in taxonomic,” Annals of Eugenics, vol. 7, no. 2, pp. 179-188, 1936.
[42] R.A. Jarvis, “Focus optimization criteria for computer image processing”, Microscope, vol. 24, no. 2, pp. 163-180, 1976.
[43] R. Battiti, ”Using Mutual Information for Selecting Features in Supervised Neural Net Learning,” IEEE Transactions on Neural Networks, vol. 5, no. 4, pp. 537-550, 1994
[44] R.O. Duda, P.E. Hart, and D.G. Stork, “Pattern Classification,” New York: John Wiley & Sons, 2001.
[45] R. C. Gonzalez and R. E. Woods, “Digital Image Processing,” Prentice Hall, 2002
[46] R. KHUTLANG, S. KRISHNAN, A. WHITELAW and T.S. DOUGLAS, “Automated detection of tuberculosis in Ziehl-Neelsen-stained sputum smears using two one-class classifiers”, Journal of Microscopy, vol. 237, no. 1, pp. 96-102, 2010
[47] R. Khutlang, S. Krishnan, R. Dendere, A. Whitelaw, K. Veropoulos, G. Learmonth, and T.S. Douglas, “Classification of Mycobacterium Tuberculosis in Images of ZN-Stained Sputum Smears”, IEEE Transactions on Information Technology in Biomedicine, vol. 14, no. 4, pp. 949-957, 2010.
[48] S.K. Nayar and Y. Nakagawa, “Shape from Focus: An Effective Approach for Rough Surfaces”, Proceedings of IEEE International Conference on Robotics and Automation, vol. 2, pp. 218-225, Cincinnati, USA, 1990.
[49] T.Y. Zhang and C.Y. Suen, “A Fast Parallel Algorithm for Thinning Digital Patterns,” Communications of the ACM, vol. 27, pp. 236–239, 1984.
[50] T. Acharya, W. Metz , “Auto-focusing algorithm using discrete wavelet transform,” US Patent 6,151,415, 2000.
[51] T. Hanscheid, C.M Ribeiro, H.M Shapiro, and N.G Perlmutter, "Fluorescence microscopy for tuberculosis diagnosis," The Lancet Infectious Diseases, vol. 7, pp. 236-237, 2007.
[52] T.B.K. Reddy,*, R. Riley, “TB database: an integrated platform for tuberculosis research,” Nucleic Acids Research, vol. 37, pp. 499-508, 2009.
[53] V.H. Nguyen, N.S. Dinh, R.M. Anthony, F.G. Cobelens and D van Soolingen, "Fluorescence microscopy for tuberculosis diagnosis," The Lancet Infectious Diseases, vol. 7, pp. 238–240, 2007.
[54] V. Makkaapati, R. Agrawl and R. Acharya, “Segmentation of Tuberculosis Bacilli from ZN-stained sputum Smear Images,” the 5th Annual IEEE Conference on Automation Science and Engineering, Bangalore, pp. 217-220, 2009.
[55] W. Huang and Z. Jing, “Evaluation of focus measures in multi-focus image fusion,” Pattern Recognition Letters, vol. 28, no. 4, pp. 493-500, 2006.
[56] Y.Freund and R.E. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting”, Journal of Computer and System Sciences, vol. 55, no. 1, pp. 119-139, 1997.
[57] Y.N Sun and M.H. Horng, “Assessing liver tissue fibrosis with an automatic computer morphometry system”, IEEE Engineering in Medicine and Biology, vol. 16, no. 3, pp. 66-73, 1997.
[58] Y. Yi, A. Besma, D. Narjes and A. Mongi, “Evaluation of Sharpness Measures and Search Algorithms for the Auto-Focusing of High Magnification Images,” Proceedings of SPIE, vol. 6246, pp. 1-12, 2006.
[59] Y.C. Liu, F.Y. Hsu, H.C. Chen, Y.Y. Wang, and Y.N. Sun, “A Coarse to Fine Auto-Focusing Algorithm for Microscope Image,” International Conference on System Science and Engineering, Macao, pp.416-419, 2011.