Categorization methodology for skin color images into pre-defined color scales

Date created: 
2019-09-09
Identifier: 
etd20526
Keywords: 
Skin color
Image classification
Histogram matching
Abstract: 

The ability to classify skin color based on images from bare skin is highly sought after in various industries and professions, including dermatology, cosmetics, skincare products, laser-based therapies, etc. The focus of the present research work is on designing an algorithm capable of classifying images of various skin colors utilizing the Fitzpatrick and cosmetic brand skin color scales. The images are taken from a skin area by any camera, including a smartphone camera. In this study, two different methods are employed to classify a query image into a set of reference images. Both methods introduced here are among the most commonly used approaches for comparing two image histograms and defining a Difference Index (DI). The application of the proposed algorithms is not limited to the classification of skin colors. These algorithms can be applied in painting industry for building interiors, developing apps for assisting people who are color-blind, etc.

Document type: 
Thesis
Rights: 
This thesis may be printed or downloaded for non-commercial research and scholarly purposes. Copyright remains with the author.
File(s): 
Supervisor(s): 
Farid Golnaraghi
Department: 
Applied Sciences: School of Mechatronic Systems Engineering
Thesis type: 
(Thesis) M.A.Sc.
Statistics: