臺灣博碩士論文加值系統

對醫學檢驗單位而言，血液抹片人工鏡檢是不可廢除的一項重要檢驗依據，但是人工鏡檢確實是一個耗時耗力的過程，除了血液抹片本身製作上的優劣之外，還得要考慮到不同醫檢人員因為疲勞或者是標準不同而有不一樣的結果，因此，以數位影像分析的技術來協助這項工作的進行，將能夠減少人力的消耗，讓血液抹片鏡檢更有效率。
　　本論文所研究的對象為具有雜訊的正常血液抹片，雜訊主要來自於製作不良的血液抹片，例如抹片太薄、抹片太厚、染色不均，以及細胞破裂等等因素，在同一個人的血液抹片影像裡面，可能會因為這些原因而在後續的分析中產生不一致的結果，因此，針對這類雜訊進行處理有其必要性，如此一來實驗結果才能具有讓人信服的依據。
本論文的貢獻有三，第一，透過二值化以及區域成長法，能將上述所定義的雜訊排除，進而找出本論文所要尋找的白血球細胞核區域；第二，在找到白血球細胞核區域之後，將可以完成多顆白血球影像定位，以利後續分析；第三，利用距離轉換(distance transform)以及平均值移動演算法(mean shift)，可以找出白血球細胞核分葉特徵，配合形狀特徵以及紋理特徵將能夠使判斷更為精確。

For the medical examination unit, the artificial blood smear examination is an important test for abolition, but the process is indeed a time-consuming examination process. In addition to making blood smear on their own merits, but also have to take into account the different medical laboratory personnel due to fatigue or different standards then have different results. Therefore, to digital image analysis technology , assisting in this work, will be able to reduce human consumption, making microscopic examination of blood smears more efficient.
The object of study in this paper as having normal blood smear noise, noise mainly from the production of bad blood smears, for example, thin smear, thick smear, stain unevenly, and cell rupture, among other factors, blood smears in the same individual images which may be because of these reasons and in the subsequent analysis produced inconsistent results, therefore, were necessary for the processing of such noise, this way in order to have convincing results basis.
There are three contributions of this paper, first, through the binarization and region growing method, able to rule out noise as defined above, and then find out in this paper to find the white blood cell nucleus area; second, find the white blood cells in the nucleus zone, more satellites will be able to complete the positioning of white blood cell imaging, to facilitate subsequent analysis; Third, the use of distance transform (distance transform) and moving average algorithm (mean shift), you can find leaf characteristics of white blood cell nuclei, with the characteristic shape and texture features will be able to make more accurate judgments.

中文摘要…… i
英文摘要 ii
誌謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 白血球計數之介紹 1
1.2 影像雜訊 2
1.3 研究動機 3
1.4 相關研究之探討 3
1.5 論文主體與貢獻 5
第二章 相關知識及理論 5
2.1 色彩模型轉換 5
2.1.1 RGB色彩模型 6
2.1.2 RGB色彩模型轉換成灰階色彩模型 6
2.1.3 RGB色彩模型轉換成HSV色彩模型 8
2.2 全域二值化與區域二值化 9
2.2.1 最大類間方差二值化法 10
2.2.2 尼布蘭克二值化法 12
2.3 高斯混合模型 13
2.3.1高斯分布 14
2.3.2高斯混合模型 15
2.4 灰階共生矩陣 17
2.5 平均值移動演算法 20
2.6 支持向量機 22
第三章 系統流程 24
3.1 整體系統架構 24
3.2 RGB直方圖分析與修正 27
3.3 建立紅血球模型 29
3.3.1影像二值化處理 29
3.3.2二值影像邊緣提取 31
3.3.3高原度區塊面積分析 32
3.3.4高原度區塊半徑分析 34
3.4 白血球細胞核影像處理與特徵抽取 36
3.4.1色彩空間轉換 37
3.4.2區域成長法復原細胞核區 39
3.4.3細胞核區重新描述及多重細胞核定位 43
3.4.4擷取白血球細胞核特徵 48
3.5 分類決策樹 54
第四章 實驗結果與分析 58
4.1 實驗設備與方法 58
4.2 實驗結果分析與討論 61
4.2.1白血球細胞核影像切割 61
4.2.2多重細胞核影像切割及定位 64
4.2.3白血球細胞核分類 69
第五章 結論 72
參考文獻 73

[1] 何敏夫, 血液學, 4th edition, 合記圖書出版社, 台北市內湖區安康路322-2號, Sep. 2010.

[2] M. Habibzadeh, A. Krzyzak, and T. Fevens, “Counting of RBCs and WBCs in Noisy Normal Blood Smear Microscopic Images,” in Proceedings of SPIE on Medical Image, Lake Buena Vista, Florida, USA, Feb. 2011, vol. 7963, pp. 79633I-79633I-11.

[3] M. Bober, “MPEG-7 Visual Shape Descriptors,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 11, no. 6, June 2011.

[4] J. W. Harvey, Atlas of Veterinary Hematology - Blood and Bone Marrow of Domestic Animals, 1st edition, Saunders, Philadelphia, USA, Jan. 2001.

[5] M. Partio, B. Cramariuc, M. Gabbouj, and A. Visa, “Rock Texture Retrieval Using Gray Level Co-occurence Matrix,” in Proceedings of 5th Nordic Signal Processing S’mpmium, Oct. 2002.

[6] K. Fukunaga and L. Hostetler, “The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition,” IEEE Transactions on Information Theory, vol. 21, no. 1, pp. 32-40, Jan. 1975.

[7] Y. Cheng, “Mean Shift Mode Seeking and Clustering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 8, pp. 790-799, Aug. 1995.

[8] J. Theerapattanakul, J. Plodpai and C. Pintavirooj, “An Efficient Method for Segmentation Step of Automated White Blood Cell Classifications,” in Proceedings of IEEE Region 10 Annual International Conference (TENCON 2004), Chiang Mai, Thailand, vol. 1, pp. 191-194 , Nov. 2004.

[9] F. Zamani and R. Safabakhsh, “An unsupervised GVF Snake Approach for White Blood Cell Segmentation based on Nucleus,” IEEE Conference on Signal Processing, The 8th International Conference , vol 2, Nov. 2006.

[10] S. H. Rezatofighi, H. Soltanian-Zadeh, R. Sharifian and R.A. Zoroofi, “A New Approach to White Blood Cell Nucleus Segmentation Based on Gram-Schmidt Orthogonalization,” IEEE International Conference on Digital Image Processing, pp. 107-111, 2009.

[11] K. Cheng “White Blood Cell Detection Using a Novel Fuzzy Morphological Shared-Weight Neural Network,” IEEE International Symposium Computer Science and Computational Technology ,vol 2 , pp. 532-535 , Dec. 2008.
[12] E. Xie, T. M. McGinnity, and Q. X. Wu, “Automatic Extraction of Shape Features for Classification of Leukocytes,” IEEE International Conference Artificial Intelligence and Computational Intelligence, vol 3, pp. 220-224 , Oct. 2010.

[13] J. A. Bilmes, “A Gentle Tutorial of the EM Algorithm and its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models,” University of Berkeley, Tech. Rep. ICSI-TR-97-021, 1997.

[14] D. Comaniciu and P. Meer, “Mean Shift: a robust approach toward feature space analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 24, no. 5, pp. 603–619, 2002.

[15] H. Ramoser, V. Laurain, H. Bischof, and R. Ecker, “Leukocyte segmentationand classification in blood-smear images,” in 27th Annual Intern. Conf. of the Engineering in Medicine and Biology Society, September 2005, pp. 3371–3374.