Human Skin Detection in Color Images Using Deep Learning

Human Skin Detection in Color Images Using Deep Learning

Mohammadreza Hajiarbabi, Arvin Agah
Copyright: © 2020 |Pages: 13
DOI: 10.4018/978-1-7998-0414-7.ch073
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Human skin detection is an important and challenging problem in computer vision. Skin detection can be used as the first phase in face detection when using color images. The differences in illumination and ranges of skin colors have made skin detection a challenging task. Gaussian model, rule based methods, and artificial neural networks are methods that have been used for human skin color detection. Deep learning methods are new techniques in learning that have shown improved classification power compared to neural networks. In this paper the authors use deep learning methods in order to enhance the capabilities of skin detection algorithms. Several experiments have been performed using auto encoders and different color spaces. The proposed technique is evaluated compare with other available methods in this domain using two color image databases. The results show that skin detection utilizing deep learning has better results compared to other methods such as rule-based, Gaussian model and feed forward neural network.
Chapter Preview
Top

2. Methods For Skin Color Detection

Different methods have been used for detecting human skin in images. Among them Gaussian, rule-based, and neural networks are some of the more popular approaches.

The Gaussian model (Wu et al., 2008) uses the YCbCr color space. The density function for Gaussian variable is used to make a decision of whether or not a pixel belongs to human skin. The parameters of the density function are calculated using training images. If the probability is more than a given threshold then that pixel is considered as human skin. The density function for Gaussian variable 978-1-7998-0414-7.ch073.m01 is:

978-1-7998-0414-7.ch073.m02
where
978-1-7998-0414-7.ch073.m03
, and the parameters are:

Chen et al. (2008) used conditional probability density function and Bayesian classification in order to define some rules for detecting human skin. RGB was used as color space. The rules are:

with α=100, β1=10, β2=70, γ1=24, γ2=112, σ1=0 and σ2=70.

Kovac et al. (2003) introduced two sets of rules one for indoor images and one for images taken in daylight illumination. Kovac also used RGB as color space. The rules are:

  • For indoor images:R>95, G>40, B>20, max{R,G,B} – min{R,G,B}>15, |R‑G|>15, R>G, R>B

  • For images taken in daylight illumination:R>220, G>210, B>170, |R‑G|≤15, R>B, G>B

Complete Chapter List

Search this Book:
Reset