進階搜尋


下載電子全文  
系統識別號 U0026-1910201711282000
論文名稱(中文) 應用模糊聚類之膚色分群於彩妝趨勢研究
論文名稱(英文) Fuzzy C-Means Based Approach for Facial Skin-color Clustering with Cosmetic Trend Application
校院名稱 成功大學
系所名稱(中) 工業設計學系
系所名稱(英) Department of Industrial Design
學年度 106
學期 1
出版年 106
研究生(中文) 顏志晃
研究生(英文) Chih-Huang Yen
電子信箱 jordan_yan@hotmail.com
學號 P38031127
學位類別 博士
語文別 英文
論文頁數 63頁
口試委員 指導教授-蕭世文
口試委員-吳昌祚
口試委員-郭炳宏
口試委員-王中行
召集委員-杜瑞澤
中文關鍵字 膚色擷取  模糊聚類  彩妝 
英文關鍵字 facial skin colour  cosmetic  Fuzzy C-means. 
學科別分類
中文摘要 人臉膚色擷取在過往的文獻研究中,常是人臉辨識的一個環節;本研究主要針對探討人臉膚色的顏色,作為未來女性彩妝前的選色參考與應用。 大部分女性作彩妝品的採購,常以直覺或跟隨流行來挑色,無法知道自己真正的膚色來作選配,所以對妝品應用來說, 人臉的膚色是一個相當關鍵的要素。
由人臉辨識的基礎做延伸的應用,以辨識後的結果之特徵點做相對位置的擷色,再以橢圓色立體的概念製作SCE 工具,來做人臉膚色的探討;考量未來大數據之應用,經田口法的最佳化研究,提出六點擷色的假說,實驗結果以光譜儀做相對驗證。
在本研究中,首先針對巨量的圖片做人臉的辨識,再以創新的點擷色作人臉膚色的匯整分析,收集的膚色轉換為Lab空間色彩,以模糊聚類的理論為基礎,設計分群方程式,將原始資料作迭代分群。 最後呈現的分群結果以Lab數值與RGB色標表示。
在研究案例中,以超過一萬筆的亞洲女性照片、經FaceRGB作自動化膚色擷取,取得的膚色資料再經ColorFCM分群得到十八個分群結果。分群的結果可於彩妝應用中當為參考的基礎, 也可以藉此基礎,發展出適合每個人不同膚色的妝品選擇系統與模式。研究最後以個案結合默克公司的色彩趨勢研究做匹配,將擷色經分群後的6組膚色與趨勢分析中的6種膚色做配對,真正將研究結果應用於產業中,更確切的明白此研究的價值與未來的發展應用。
英文摘要 Consumer behaviour is complicated. In the cosmetic market, personal intuition and fashion trends for colour selection are guidelines for consumers. A systematic method for female facial skin-color classification and an application in the makeup market are proposed in this study. In this paper, face recognition with a large number of images is first discussed. Then, an innovative method for colour capturing at selected points is presented and complexion-aggregated analysis is performed. This innovative method is an extension of face-recognition theory. Images in RGB format are converted to Lab-space format during data collection and then Fuzzy C-means theory is utilized to cluster and group the data. The results are classified and grouped in Lab value and RGB index. Two programs are created. The first program, “FaceRGB”, captures colour automatically from images. The second program, “ColorFCM”, clusters and groups the skin-color information. The results can be used to assist an expert system in the selection of customized colours during makeup and new-product development. In the study case, with more than 10,000 Asian women photos, FaceRGB for automatic skin color capture, obtained skin color data and then divided by ColorFCM eighteen group results. In the end, the study combined with Merck's colour trend forecast, connected the clustering skin colour with six Merck's idea skin colour to do the pair, the results will be applied to cosmetic, and more clearly realize the value of research and the future development of the application.
論文目次 摘要 i
SUMMARY ii
ACKNOWLEDGEMENTS iii
TABLE OF CONTENTS iv
LIST OF TABLES vi
LIST OF FIGURES vii
LIST OF SYMBOLS AND ABBREVIATIONS viii
CHARTER 1 INTRODUCTION 1
1.1 Related research 1
1.2 Market Assessment from Merck 5
1.3 Outline of this study 5
CHAPTER 2 LITERATURE REVIEW 7
2.1 The choice for colour space 7
2.1.1 RGB colour model 7
2.1.2 CIELAB colour model 8
2.1.3 RGB & CIELAB conversions 9
2.2 Taguchi Methods 10
2.2.1 Basic concept 11
2.2.2 Properties of an orthogonal array 11
2.2.3 Assumptions of the Taguchi method 12
2.2.4 Designing an experiment 13
2.3 Fuzzy C-means 13
2.4 Facial recognition system 15
CHAPTER 3 IMPLEMENTATION METHOD 18
3.1 6 points colour detection 18
3.1.1 Hypothesis _ Captured colour from 6 points 20
3.1.2 Taguchi method finds optimization 23
3.2 Verification for 6 points to detect facial colour 26
3.2.1 Spectrometer Application 27
3.2.2 Test Design 27
3.2.3 Test comparison of FaceRGB and FOS(Fiber of spectrometer) 29
CHAPTER 4 CACE STUDY 32
4.1 FaceRGB 32
4.1.1 Outliers 33
4.1.2 FaceRGB operation 34
4.2 ColorFCM 36
4.2.1 Expectation Maximization 36
4.2.2 E-step (Expectation step) 37
4.2.3 M-step (Maximization) 37
4.2.4 K-means++ 38
4.2.5 ColorFCM implementation 39
CHAPTER 5 RESULTS & DISCUSSION 42
5.1 Experimental verification 43
5.2 RGB & YCbCr conversions 44
5.3 Training samples for FaceRGB 46
5.4 FaceRGB with a large quantity of images 48
5.5 ColorFCM result by Fuzzy C-means 49
CHAPTER 6 APPLICATION 52
6.1 Connection between the colour clusters and Merck makeup trends 54
6.2 For personal application 55
6.3 For trend applications 55
6.4 Conclusion 58
REFERENCES 60

參考文獻 Arthur D, Vassilvitskii S. (2007). k-means++: The advantages of careful seeding. Proceedings of the 18th Anal ACM-SIAM symposium on discrete algorithms. SocIndAppl Math: 1027-1035.
Brunelli R, Poggio T. (1993). Face Recognition: Features versus templates. IEEE Trans on Pattern Analysis and Machine Intelligence;15:1042-1052.
Brunelli R. (2009). Template matching techniques in computer vision: Theo. Wiley.
Boughen N. (2003). Light wave 3d 7.5 Lighting. Word ware Publishing, Inc.
Bezdek JC. (2013). Pattern Recognition with fuzzy objective function algorithms: Springer science &business media. New York.
Caisey L, Grangeat F, Lemasson A, Talabot J, Voirin A. (2006). Skin color and makeup strategies of women from different ethnic groups. IntJ Cosmet Sci; 28:427–437.
Dempster AP, Laird NM, Rubin DB. (1997). Maximum likelihood from incomplete data via the EM Algorithm. J. R. Stat. Soc.; B39:1–38.
Duhn, S. von; Ko, M. J.; Yin, L.; Hung, T.; Wei, X. (2007). Three-View Surveillance Video Based Face Modeling for Recognition. Information Forensics and Security IEEE Transactions on Pattern Analysis and Machine Intelligence; 7: 1802-1811 .
Estanislao R, Suero M, Galzote C, Rivera Z, Li J, Kim HO, Thomas S, Khaiat A, Cheong EJ, Mangubat MI, Moideen R, TagamiH, Wang X. (2003). Characterization of Asian skin though in-vivo instrumental and visual evaluations: Influences of age, season and skin care habits. In: Proceedings of 6th Scientific Conference of the Asian Societies of Cosmetic Scientists, Manila; 263–269.
F'eraud R, Bernier OJ, Viallet JE, Collobert M. (2001). A fast and accurate face detection based on neural network. IEEE Trans on Pattern Analysis and Machine Intelligence; 23:42-53.
Forsyth PH, Fleck MM. (1999). Automatic detection of human nudes. Int J comput Vis; 32:63-77
Green P, Lindsay W, Donald M. (2002). Colour Engineering: Achieving Device Independent Colour. John Wiley and Sons. ISBN 0-471-48688-4.
Hsu RL, Mohamed AM, Jain AK. (2002). Face detection in color image. IEEE Trans Pattern Anal; 24:696–706.
Hsiao SW, Chiu FY, Hsu HS. (2008). A computer-assisted color selection system based on aesthetic measure for color harmony and fuzzy logic theory. Color ResAppl;19:202–213.
Hunter RS. (1985). Photoelectric color-difference meter. J Opt Soc Am.;48:985-995.
Hastie T, Tibshirani R, Friedman J. (2001). The EM algorithm: The Elements of statistical learning. New York: Springer.
Hsiao SW. (1994). Fuzzy set theory on car-color design. Color Res Appl;19:202-213.
Hsiao SW. (1995). A systematic method for color planning in product design. Color Res Appl;20:191-205.
Hsiao SW, Chang MS. (1997). A semantic recognition-based approach for car's concept design. Int J Vehicle Design;18:53-82
Hardin, R.H., & Sloane, N. J. A. (1993). A New Approach to the Construction of Optimal Designs, Journal of Statistical Planning and Inference; 37: 339-369
Ikeda N, Miyashita K, Hakim R, Tominaga S. (2014). Reflection measurement and visual evaluation of the luminosity of skin coated with powder foundation. Color Res Appl; 39: 45–57.
James & John. (2007), Spectrograph Design Fundamentals. Cambridge University Press. ISBN 0-521-86463-1
Jones, A. B., & Smith, C. D. (2005). Curriculum and instruction: A primer. New York: Academic Press.
Jones MJ, Rehg JM. (2002). Statistical color models with application to skin detection. Int J Comput Vis;46:81-96.
Kakumanu P, Makroginnis S, Bourbakis N. (2007). Asurvey of skin-color modeling and detection methods. Pattern Recognit; 40:1106-1122
Kumar C, Bindu A. (2006). An efficient skin illumination compensation model for efficient face detection IEEE IndEle IECON Anal:34444-34449.
Lam EY. (2005). Combining Gray World and Retinex Theory for Automatic White Balance in Digital Photography, IEEE Transactions on Consumer Electronics;14-16:134-139.
Mario D, Maltoni D. (2000). Real-time face location on gray-scalstaic image. Pattern Recognit;33:1352-1539.
Nock R, Nielsen F. (2006). On weighting clustering. IEEE Trans Pattern Anal;28:1–13.
Pukelsheim, Friedrich (2006). Optimal Design of Experiments. SIAM. ISBN 978-0-89871-604-7.
Reichman OJ, Jones MB, Schildhauer MP. (2011). Challenges and opportunities of open data in ecology, Sci.; 6018:703–705.
Rona, PECLERS PARIS. (2015). Merck Group.
Socolinsky, Diego A.; Selinger, Andrea (2004). "Thermal Face Recognition in an Operational Scenario". IEEE Computer Society; 1012–1019
Sharma G, Wu W, Dalai EN. (2004). The CIE DE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations. ColorResAppl; 30: 21–30.
Smith, C. (2001). Understanding the role of instruction in the curricular context. In E. F. Johnson & G. H. Wise (Eds.); 210-230).
Smith, C. D., & Jones, A. B. (2004). Perspectives on curriculum and instruction. Journal of Educational Research; 55(1), 28-54.
Sun, Y., Wang, X., Tang, X. (2013). Deep Convolutional Network Cascade for Facial Point Detection. IEEE Conference on Computer Vision and Pattern Recognition ; 3476-3483.
Merck Group, Products & Industries. (2016). Available at http://www.merckgroup.com/en/products/products.html
Tan WR, Chan CS, Yogarajah P. (2014). Condell J, A Fusion approach for efficient human skin detection. IEEE Trans on IndInf;8:138-147.
Vadakkepat P, Lim P, Silva D, Jing L, Ling LL. (2008). Multimodal approach to human-face detection and tracking IEEE Trans Ind Ele;55:1385-1393
Wu H, Chen Q, Yachida M, (1999). Face detection from color images using a fuzzy pattern matching method. IEEE Trans on Pattern Analysis and Machine Intelligence; 21.
Yoshikawa H, Kikuchi K, Takata S, Yaguchi H. (2009). Development of avisual and quantitative evaluation method for facial skin color, Proceedings of 11th Congress of the AIC, CD-ROM, Sydney.
Yoshikawa H, Kikuchi K, Kim J, NishikawaS, YaguchiH, Mizokami Y. (2007). Effect of the chromatic components on the whiteness evaluation of skin. Midtemmeeting of congress of international color association; 203-206.
Zeng H & Luo MR. (2011). Skin color modeling of digital photographic images. J. Imaging Sci. Technol; 55:030201
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2018-12-31起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2018-12-31起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw