Supervised Learning Methods for Skin Segmentation Based on Pixel Color Classification

Keywords: Supervised learning methods, Skin segmentation, RGB colors, YCbCr representation

Abstract

Over the last few years, skin segmentation has been widely applied in diverse aspects of computer vision and biometric applications including face detection, face tracking, and face/hand-gesture recognition systems. Due to its importance, we observed a reawakened interest in developing skin segmentation approaches. In this paper, we offer a comparison between five major supervised learning algorithms for skin segmentation. The algorithms involved in this comparison are: Support Vector Machines (SVM), K-Nearest-Neighbors (KNN), Naive Bayes (NB), Decision Tree (DT), and Logistic Regression (LR). Various scenarios of data pre-processing are proposed including a conversion from RGB into YCbCr color space. Using YCbCr representation gave a better performance in skin/non-skin classification. Despite the settled comparison criteria, KNN was found to be the most desirable model that provides a stable performance overall the several experiments conducted.

Author Biographies

Ahmad TAAN, Data Science and Engineering MSc student

Eötvös Loránd University, Faculty of Informatics, Department of Data Science and Engineering, Hungary, MSc student

Zakarya FAROU, Data Science and Engineering Ph.D. Student
After finishing my MSc studies in 2019 with honors at ELTE and obtained a Master's degree in computer science, I joined the Department of Data Science and Engineering as a Ph.D. candidate in Data Science. I started my studies in Hungary after graduating from 08 May 1945 Guelma University with honors and obtained a Bachelor’s degree in Information and Computer Systems in 2017. Research interests: - IoT, Smart Systems - Text Mining - Time series classification - Bio-Mining - Data mining - Synthetic data generation - Generative adversarial networks
Published
2020-12-15
How to Cite
TAAN, A., & FAROU, Z. (2020). Supervised Learning Methods for Skin Segmentation Based on Pixel Color Classification. Central-European Journal of New Technologies in Research, Education and Practice, 3(1). https://doi.org/10.36427/CEJNTREP.3.1.779
Section
Scientific Papers