Skin segmentation using color pixel classification: analysis and comparison

TLDR

The study investigates how color representation, color quantization, and classification algorithms affect skin segmentation using color pixel classification. The authors evaluate multiple color spaces, color quantization levels, and classification methods—including a Bayesian classifier with histogram technique and a multilayer perceptron—within a color pixel classification framework. Their analysis shows that skin segmentation is largely insensitive to color space choice, degrades when only chrominance channels are used, benefits from higher histogram sizes (up to 64 bins per channel), and that the Bayesian-histogram and MLP classifiers outperform other tested classifiers.

Abstract

This work presents a study of three important issues of the color pixel classification approach to skin segmentation: color representation, color quantization, and classification algorithm. Our analysis of several representative color spaces using the Bayesian classifier with the histogram technique shows that skin segmentation based on color pixel classification is largely unaffected by the choice of the color space. However, segmentation performance degrades when only chrominance channels are used in classification. Furthermore, we find that color quantization can be as low as 64 bins per channel, although higher histogram sizes give better segmentation performance. The Bayesian classifier with the histogram technique and the multilayer perceptron classifier are found to perform better compared to other tested classifiers, including three piecewise linear classifiers, three unimodal Gaussian classifiers, and a Gaussian mixture classifier.