Advanced search
Start date
Betweenand

Skin Tone Color Correction from mobile devices.

Grant number: 23/15404-1
Support Opportunities:Scholarships in Brazil - Scientific Initiation
Start date: January 01, 2024
End date: December 31, 2024
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
Principal Investigator:João Do Espirito Santo Batista Neto
Grantee:Rodrigo Rodrigues de Castro
Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

The color representation of skin tones in images is often inaccurate, since various external factors, such as natural skin irregularities, differences in lighting sources and variations in the configuration of the imaging device, may lead to the generation of images with colors that are disproportionate to the real ones. However, the identification of human skin color is fundamental in various areas of research where facial images are the means of analysis, such as photography, dermatology, cosmetics and visual entertainment, for example. In this sense, the main purpose of this research proposal is to develop a method for correcting human skin color (white balance) in images acquired by mobile devices, which can present considerable variability in color tones. The proposed method is based on using an ideally accurate reference image to correct an input image. By segmenting the skin regions of interest in both images, colour gradation techniques between the images will promote a smooth transition between different skin tones from the accurate image to the inaccurate one, providing skin colour correction in the affected image while maintaining colour fidelity in the image background. This proposal is part of a wider project aimed at classifying skin tone using machine learning, for which color correction is a very relevant stage.

News published in Agência FAPESP Newsletter about the scholarship:
More itemsLess items
Articles published in other media outlets ( ):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)