Towards independent color space selection for human skin detection

Authors:
Tao Xu;Yunhong Wang;Zhaoxiang Zhang
Affiliations:
Laboratory of Intelligent Recognition and Image Processing, Beijing Key Laboratory of Digital Media, Beihang University, Beijing, China;Laboratory of Intelligent Recognition and Image Processing, Beijing Key Laboratory of Digital Media, Beihang University, Beijing, China;Laboratory of Intelligent Recognition and Image Processing, Beijing Key Laboratory of Digital Media, Beihang University, Beijing, China
Venue:
PCM'12 Proceedings of the 13th Pacific-Rim conference on Advances in Multimedia Information Processing
Year:
2012

Citing 8
Cited 0

Statistical color models with application to skin detection

International Journal of Computer Vision
Skin Segmentation Using Color Pixel Classification: Analysis and Comparison

IEEE Transactions on Pattern Analysis and Machine Intelligence
A survey of skin-color modeling and detection methods

Pattern Recognition
Flexible neural trees ensemble for stock index modeling

Neurocomputing
Detecting skin in face recognition systems: A colour spaces study

Digital Signal Processing
Grammar-based Genetic Programming: a survey

Genetic Programming and Evolvable Machines
Small-time scale network traffic prediction based on flexible neural tree

Applied Soft Computing
Color based skin classification

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

Skin color detection plays an important role in video based applications. Without considering the selection of suitable color space, a novel skin color detection method is proposed based on the flexible neural tree, which can identify the important components of color spaces automatically. With large training data sets, our method builds a flexible neural tree structure and optimizes its parameters using Genetic Programming and Particle Swarm Optimization algorithms. In experiments, features comprised of all channels extracted from RGB, YCbCr and HSV color spaces are used for the constructing and evaluating of the novel skin color model, in which six most important components, i.e., R, G, B, Y, Cr and S are selected for testing. Furthermore, our method achieves higher accuracy and lower false positive rate than state of the art methods on Compaq and ECU data set.