NORMA eResearch @NCI Library

Foundation Makeup Shade Recommendation using Computer Vision Based on Skin Tone Recognition

Kamble, Sanica Sanjay (2023) Foundation Makeup Shade Recommendation using Computer Vision Based on Skin Tone Recognition. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (5MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (3MB) | Preview


Skin detection has a wide range of uses in fields including surveillance, criminal justice, and health, among others, and has shown to be a fantastic innovation. In order to recommend or advise the best matching foundation shade to users, this research focuses on skin detection, which involves extracting the skin tone RGB values from face photos belonging to different ethnic groups. This method, which is based on a three-tier architecture, addresses three components of the process: skin detection, identifying the skin tone, and recommending the foundation shade, brand and product that is most appropriate. Three color-space models have been compared for the detection of skin and skin tones: HSV color space with Gaussian blur, HSV color space alone, and a mix of HSV and YCrCb color space with histogram equalization and Otsu’s image segmentation. For each of the three methodologies, the difference between the calculated RGB skin tone values and the actual RGB skin tone values has been measured using the delta-E metric. By producing the lowest Delta-E average value of 17.51427022, the color-model using a mix of the HSV and YCrCb color spaces outperformed the other two techniques.

Item Type: Thesis (Masters)
Simiscuka, Anderson Augusto
Uncontrolled Keywords: RGB; HSV; YCrCb; Delta-E; Histogram Equalization; Image Segmentation; Skin Tone; Skin Detection; Color Space
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence
H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Cosmetics Industry
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 19 May 2023 14:18
Last Modified: 19 May 2023 14:18

Actions (login required)

View Item View Item