• Varsha S
• Disha D
• Vitesh Babu M

Skin tone has significant impacts across various domains, but existing methods to measure and classify skin color suffer from subjectivity and potential biases. We introduce CASCo (Classification Algorithm for Skin Color) - an objective, automated approach that leverages computer vision and machine learning techniques to robustly classify skin tones from facial images. CASCo is an open-source Python library accessible to researchers, overcoming major limitations of traditional measurement techniques. It uses face detection, skin segmentation and k-means clustering algorithms to determine the skin tone category of portraits. Through extensive evaluation, we demonstrate CASCo's effectiveness as a reliable and customizable tool for studying the social implications of skin color in an inclusive manner.

Skin tone classification, Computer vision, Machine learning, Facial analysis, Objective measurement, Automated analysis, Open-source software Python library, social implications, Inclusive research, Unbiased algorithms, Demographic studies

"SkinToneNet: A Deep Learning Framework for Automated and Unbiased Skin Color Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.e810-e814, May-2024, Available :http://www.jetir.org/papers/JETIR2405495.pdf

"SkinToneNet: A Deep Learning Framework for Automated and Unbiased Skin Color Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppe810-e814, May-2024, Available at : http://www.jetir.org/papers/JETIR2405495.pdf