• PRANJIT DAS
• ADARSH SATSANGI
• ALI KHALID

Researchers have been working on an effective skin detection technology for decades. Current methods, on the other hand, have not been able to overcome substantial constraints. To address these restrictions, a clustering and efficient optimization strategy is given. These strategies, when combined with sufficient understanding, result in a more successful algorithm. The idea is to be able to dynamically define the number of clusters in a collection of pixels structured as an image. The number of clusters in clustering for most problem areas is defined a priori and thus does not perform well across a wide range of data contents. As a result, this study developed a skin detection approach that confirmed the previous findings. This method uses the K-means algorithm along with the Particle swarm optimization method for the efficient working of the ML model and to obtain an accurate output. It also consists of a UI framework for the people less equipped with the coding part.

Machine Learning, Particle Swarm Optimization, K-means clustering, User Interface

"HUMAN SKIN TONE DETECTION USING UNSUPERVISED LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 6, page no.g610-g618, June-2022, Available :http://www.jetir.org/papers/JETIR2206674.pdf

"HUMAN SKIN TONE DETECTION USING UNSUPERVISED LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 6, page no. ppg610-g618, June-2022, Available at : http://www.jetir.org/papers/JETIR2206674.pdf