現在醫療美容越來越受到青睞與重視，人們除了社交需要外也受到影音媒體耳濡目染下更重視自己的外觀，而偵測肌膚技術的重要性與需求性日益增加。現在醫療美容肌膚分析系統的價格較昂貴，非一般民眾能負擔，因此開發此系統透過影像處理方式對人臉肌膚進行有效判斷，可以降低價格昂貴因素。

本論文透過輸入影像中找到人臉位置，並且自動找到臉部特徵，人臉擷取 5個感興趣區域(ROI)來進行膚質檢測。最後使用四種不同的方法，分別從ROI 中偵測痘疤、痣、膚斑及皺紋。取得ROI區域後可以選取欲偵測部位進行偵測，處理方式針對影像中的色彩空間特性進行轉換，並進行執行膚斑、痘疤、皺紋進行膚質影像特徵值，之後利用敏感度、準確度、特殊性與Pearson 積差相關統計方法評估實驗結果。

The medical cosmetology has become increasingly important for people nowadays. Besides the manner of socializing, people care more about their appearance under the influence of social media. As a result, the technology of skin detection and dermatology evolves as well. But it is hardly affordable for people taking a analysis process by using the technology of medical cosmetology skin analysis system, which becomes a push power for inventing the system of analyzing human face skin by the technology of image processing.

In this paper, we invent a system that can automatically find and locate the features of faces and extract 5 regions of interests (ROI) to engage dermatology, and uses four different ways to detect smallpox, mole, skin spots and wrinkles. After selecting the ROI, the system will detect the skin features by transforming the RGB color space to collect the result. In the end we use Pearson Product Moment Correlation Coefficient and use sensitivity, specificity, accuracy to evaluate the experiment result.

書名頁 i
論文口試委員審定書 ii
授權書 iii
中文摘要 vi
英文摘要 vii
誌謝 viii
目錄 ix
表目錄 xi
圖目錄 xii
第一章、 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 1
1.3 研究流程 2
第二章、文獻探討 3
2.1 肌膚的構造 3
2.1.1 皺紋 4
2.1.2 痘疤 5
2.1.3 膚斑 6
2.1.4 痣 7
2.2 人臉偵測 7
2.2.1 積分影像 8
2.2.2 AdaBoost分類器 11
2.2.3 層疊分類器(Cascade Classifier) 11
2.3 色彩模型 12
2.3.1 RGB色彩模型空間 14
2.3.2 HSI 色彩模型空間 15
2.3.3 L*a*b 色彩空間 16
2.3.4 L Angle A Angle B色彩空間 17
2.3.5 YCbCr 色彩空間 18
2.4 邊緣偵測方法 19
2.4.1 Canny 19
2.4.2 Sobel 20
第三章、 研究架構與方法 21
3.1 研究架構 21
3.2 臉部偵測 21
3.3 皺紋偵測 22
3.4 膚斑偵測 24
3.5 痣偵測 26
3.6 痘疤偵測 29
第四章、 研究結果 32
4.1 實驗資料 32
4.2 開發環境 33
4.3 系統功能介紹 33
4.4 影像特徵值整理表 37
4.5 實驗結果 38
第五章、 結論與展望 48
參考文獻 49

[1] R. B., Oliverira, ,” Characterization of Texture in Image of Skin Lesions by Support Vector Machine.” IEEE Xplore., ISBN: 978-1-4673-2843-2 (12967487), June 2012.
[2] J. Supriya, and D.N.V.S.L.S. Indira, “Interactive Diagnosis of Nevus’ Classification using FWS Model & Feature-Based Analysis”, IEEE Xplore, ISBN: 978-1-4673-4367-1 (13399593), Dec. 2012.
[3] Q. Abbas, M. E. Celebi, and Irene F. García,”Skin tumor area extraction using an improved dynamic programming approach”, Skin Research and Technology, Vol.18 Issue 2, p133-142, Apr. 2011.
[4] R. Guo, and H. Takahashi, “Skin-Anatomy Based Face Texture Image Synthesis by Skin Feature Distribution Analyzing Method,” IEEE Xplore., ISBN: 978-1-4244-7779-1 (11530976), August 2010.
[5] H. Jeppe, M. B. T. Soerensen, Z. Linghui, S. Chen, and M. O. Jensen,“Pre-diagnostic digital imaging prediction model to discriminate between malignant melanoma and benign pigmented skin lesion”,Skin Research and Technology, Vol.16 Issue 1, p98-108, Feb. 2010.
[6] T. Igarashi, K. Nishino, and S. K. Nayar, “The Appearance of Human Skin”, Technical Report: CUCS-024-05 Department of Computer Science Columbia University, 2005.
[7] P. Agache and P. Humbert, Measuring The Skin. 2004.
[8] J. Kovac, P. Peer, and F. Solina, “Human Skin Colour Clustering for Face Detection,” EUROCON,2003.
[9] J. Serup, “Efficacy testing of cosmetic products” , Skin Research and Technology, Vol.7 Issue 3, p141, August 2001.
[10] F. Ercal, A. Chawla, W. V. Stoecker, H. Lee, and H. Mossandy, ”Neural Network Diagnosis of Malignanw Melanoma From Color Images”, IEEE Transactions on Biomedical Engineering,Vol.41, NO.9, September.1994.
[11] 林姿妙，"以資訊技術建構臺灣地區成年女性膚質老化程度之預測模型"，元智大學碩士論文。
[12] 黃欣慧，"影像處理技術應用於人臉膚質特徵之研究"，元智大學碩士論文。
[13] 吳佳穎，"影像處理技術與類神經網路於表情辨識之應用"，元智大學碩士論文。
[14] 吳敏綺，皮膚美容診療室，上旗文化。
[15] 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.
[16] Y. Freund and R. E. Schapire, "A decision-theoretic generalization of on-line learning and an application to boosting," presented at the Proceedings of the Second European Conference on Computational Learning Theory, 1995.
[17] Y. Freund and R. E. Schapire, ”Experiments with A New Boosting Algorithm,” Proceedings of the 13th Conference on Machine Learning, 1996, pp. 148-156.
[18] Y. Freund and R. E. Schapire, “A Decision-Theoretic Generalization of On-line Learning and An Application to Boosting,” Journal of Computer and System Science, Vol 55, no.. 1, pp. 119-139,1997.
[19] Adobe, http://www.adobe.com/tw/
[20] R. C. Gonzales and R. E. Woods, Digital Image Processing, 3rd edition, Prentice Hall,2008.
[21] S. E. Umbaugh, R. H. Moss, and W. V. Stoecker, “Automatic color segmentation of images with application to detection of variegated coloring in skin tumors,” IEEE Engineering in Medicine and Biology Magaine, Vol.8, pp.43-52, Dec. 1989.
[22] 劉瑞禎、于仕琪，OpenCV教程基礎篇，北京航空航天大學出版。
[23] G. Yang and T. S. Huang, ”Human face detection in a complex background,” Pattern recognition, vol. 27, pp. 53-63,1994.
[24] S. K. Singh, D. Chauhan, M. Vatsa, and R. Singh, “A robust skin color based face detection algorithm,” Tamkang Journal of Science and Engineering, vol.6, pp. 227-234, 2003.
[25] J. Wang and T. Tan, “A new face detection method based on shape information,” Pattern Recognition Letters, vol. 21, pp. 463-471, 2000.
[26] R. Brunelli and T. Poggio, “Face recognition: Features versus templates,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 15, pp. 1042-1052, 1993.
[27] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Computer Vision and Pattern Recognitiom, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, 2001, pp. I-511-I-518, vol1.
[28] C. Garcia and G. Tziritas,”Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis.” IEEE Transactions on Multimedia, vol. 1, No. 3, pp. 264-277, 1999.
[29] EmguCV, http://www.emgu.com/wiki/index.php/Emgu_CV
[30] R. L. Hsu, A. Mottaleb, and A. K. Jain, “Face detection in color images,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 24, pp.696-706, 2002.
[31] 胡學恭，“複雜背景下的多重人臉偵測與辨識”，元智大學碩士論文。