臺灣博碩士論文加值系統

生物檢測的需求隨著人類對健康的重視而更為重要，檢測時以人工細胞計數費力又耗時，且需要依賴專業人員的能力，專業人員的生理與心理狀態常會影響細胞觀測結果的準確性。為了解決以顯微鏡人工計數的不確定因素，因此本論文提出一個快速與準確的自動化計數工具。
本論文利用色彩量化演算法與標記演算法來進行細胞計數工作，相較於使用邊緣偵測及相關去除雜訊演算法的研究方式，本論文所提出的方法只需將樣本作色彩的量化分組後，針對量化的結果進行標記演算法的運算即可，因而可以達到快速且準確的結果。
　本論文實現的計算細胞方式，可依照細胞圖片的特性作相關的量化條件調整，經過調整後，其準確率約為95%，可以有效降低人力成本的支出及人為因素的誤差率。

The demand for biological testing becomes more and more important as humans pay more attention to their health. Conventional manual cell counting process in biological testing is laborious and rather time consuming. Besides, the accuracy of counting results relies on the ability of professional operators. The physical and psychological conditions of the operators often affect the accuracy of the observation results. Accordingly, we propose in this thesis an automated counting tool with a fast and accurate way to solve the uncertainty under the microscope observation, and hence to reduce the possible human errors.
This thesis uses color quantization algorithms and fast connected-component labeling (FCCL) for counting cell, rather than the familiar methods using edge detections and noise removal algorithms.
By tuning the condition of color quantization for cell counting method according to the cell image properties, we can achieve the counting accuracy rate of 95%, and efficiently reduce the labor cost and the error rate caused by human.

致謝 I
摘要 II
Abstract III
目次 IV
圖目次 VI
表目次 VIII
第一章 緒論 1
1.1 研究背景與動機 1
1.2 論文組織架構 3
第二章 色彩量化與標記演算法 4
2.1 色彩量化演算法簡介 4
2.1.1 色彩基礎 5
2.1.2 色彩模型 6
2.1.3 均勻色彩量化 8
2.1.4 Median-Cut演算法 8
2.1.5 K-Means分群演算法 10
2.2 標記演算法 11
2.2.1 標記演算法簡介 11
2.2.2 標記演算法基礎理論 12
2.3 系統平台 15
第三章 影像處理流程與演算法 16
3.1 Fuzzy C-Means 16
3.2 Fast Connected-Component Labeling 21
3.3 影像處理流程設計 26
第四章 實驗結果 27
4.1 系統介面設計 27
4.2 色彩量化結果 28
4.3 計數結果與比較 33
第五章 結論 39
參考文獻 40
附錄 43

[1]行政院衛生署，民國一百零三年國人死因統計結果分析，2015。
[2]癌症基金會，癌症的起因與生成，2007。
[3]癌症關懷諮詢網，肺癌發展形成，2014。
[4]白果能，偵搜與追殺癌細胞，科學發展期刊439期，2009年7月。
[5]R. C. Gonzalez and R. E. Woods, Digital image processing (3rd Edition), Prentice Hall, 2007.
[6]井上誠喜、八木伸行、林正樹、中須英輔、三谷公二、奧井誠人，C語言數位影像處理，台北，全華圖書股份有限公司，2009。
[7]N. Otsu, “A Threshold Selection Method from Gray Level Histogram,” IEEE Transaction on System Man, and Cybernetics, Vol. 9(1), pp. 62-66, 1978.
[8]P. Heckbert, “Color image quantization for frame buffer display,” Computer Graphics, Vol. 16, pp. 297-307, 1982.
[9]O. Verevka, “Color Image Quantization in Windows System with Local K-means Algorithm,” Proc.Western Computer Graphics Symposium, pp. 74-79, 1995.
[10]Gonzalez, Rafael C., Woods, Richard E. 2002. Digital Image Processing. Second Edition, Prentice-Hall. Fast Connected-component Labeling.
[11]Lifeng Hea,e,*, Yuyan Chaob,e, Kenji Suzukic, Kesheng Wud, Pattern Recognition, 2009.
[12]J. C. Bezek, “Pattern Recognition with Fuzzy Object Function Algorithms,” New York: Plenum, 1981.
[13]J. C. Bezek, Robert Ehrlich, William Full, “FCM : The Fuzzy C-Means Clustering Algorithm,” Computers & Geosciences Vol. 10, No. 2-3, pp. 191-203, 1984.
[14]維基百科之Broland介紹，2015.12，[online]，Available: https://zh.wikipedia.org/wiki/Borland
[15]維基百科之C++Builder介紹，2015.12，[online]，Availabel: https://zh.wikipedia.org/wiki/C%2B%2BBuilder
[16]蔡孟凱、雷穎傑、黃昭維、陳錦輝、陳正凱，C++Builder 6完全攻略，上奇科技股份有限公司，2007。
[17]王聖文，異質網路下透過睡眠模式及功率控制之能量效益改善機制，國立海洋大學碩士論文，2015年6月。
[18]維基百科之紅血球圖片，2015.7. [Online]. Available: https://zh.wikipedia.org/wiki/%E7%BA%A2%E8%A1%80%E7%90%83
[19]Fatima Chobngam, Kanyanatt Kanokwiroom, Warit Wichakool, Somchai Limsiroratana, “Preliminary Results of Death Cell Counting Based on K-mean Clustering”, Biomedical Engineering International Conference, 2012
[20]劉于綸，細胞顯為影像分割與運動分析，國立中央大學碩士論文，2004。
[21]陳孟誌，果蠅腦細胞計數之自動方法設計，國立交通大學碩士論文，2005。
[22]林俊杰，應用影像處理於線上細胞計數與監測系統之研究，國立台灣科技大學碩士論文，2009。
[23]H. Berge, D. Taylor, S. Krishnan, T. S. Douglas, “Improved red blood cell counting in thin blood smears.” IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 204-207, 2011.
[24]陳裕瑋，影像應用於血球計數盤上的細胞計數，國立中正大學碩士論文，2012。
[25]F. Chobngam, K. Kanokwiroon, S. Chatpun, W. Wichakool, “Preliminary results of death cell counting based on K-mean ckustering. ”Biomedical Engineering International Conference, pp. 1-4, 2012.
[26]H. A. Hhan, G. M. Maruf, “Counting Clustered Cells using Distance Mapping,” International Conference on Informatics, Electronics & Vision, pp. 1-6, 2013.
[27]G. Xiaomin, Yu. Feihong, “A Method of Automatic Cell Counting Based on Microscopic Image,” International Conference on Intelligent Human-Machine Systems and Cybernetics, pp. 293-296, 2013.
[28]J. M. Sharif, M. F. Miswan, M. A. Ngabi, M. S. H. Salam, M. Mahadi bin abdul Jamil, “Rad blood cell segmentation using masking and watershed algorithm: A preliminary study,” International Conference on Biomedical Engineering, pp.258-262, 27-28 Feb. 2012.
[29]M. Maitra, R. K. Gupta, M. Mukherjee, “Detection and counting of red blood cell image using hough transform,” International Journal of Computer Applications, vol. 53, no. 6, 13-17, September 2012.
[30]A. M. T. Nasution, E. K. Suryaningtyas, “Comparison of red blood cells counting using two algorithms: Connected component labeling and backprojection of artificial neural network,” PhotonicsGlobal@Singapore, IPGC 2008 pp. 1,4,8-11 Dec. 2008.
[31]S. Khan, A. Khan, F. S. Khattak, A Naseem, “An accurate and cost effective approach to blood cell count”, International Journal of Computer Applications, vol. 50, no. 1, 18-24, July 2012.