Fair comparison of skin detection approaches on publicly available datasets

TL;DR

This paper provides a comprehensive comparison of skin detection methods across multiple datasets, introduces a unified evaluation framework, and proposes an ensemble approach that outperforms individual methods without extensive tuning.

Contribution

It offers a detailed literature review, a new evaluation framework with open source code, and an ensemble skin detection method validated on over 10,000 images.

Findings

The proposed method achieves superior performance compared to standalone approaches.

The ensemble approach is effective across diverse datasets.

The framework facilitates fair and standardized comparison of skin detection techniques.

Abstract

Skin detection is the process of discriminating skin and non-skin regions in a digital image and it is widely used in several applications ranging from hand gesture analysis to track body parts and face detection. Skin detection is a challenging problem which has drawn extensive attention from the research community, nevertheless a fair comparison among approaches is very difficult due to the lack of a common benchmark and a unified testing protocol. In this work, we investigate the most recent researches in this field and we propose a fair comparison among approaches using several different datasets. The major contributions of this work are an exhaustive literature review of skin color detection approaches, a framework to evaluate and combine different skin detector approaches, whose source code is made freely available for future research, and an extensive experimental comparison among several recent methods which have also been used to define an ensemble that works well in many different problems. Experiments are carried out in 10 different datasets including more than 10000 labelled images: experimental results confirm that the best method here proposed obtains a very good performance with respect to other stand-alone approaches, without requiring ad hoc parameter tuning. A MATLAB version of the framework for testing and of the methods proposed in this paper will be freely available from https://github.com/LorisNanni