Fuzzy C-Means Based Approach for Facial Skin-color Clustering with Cosmetic Trend Application

Abstract

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

Date of Award	2017 Oct 20
Original language	English
Supervisor	Shih-Wen Hsiao (Supervisor)