A Fuzzy Approach to Skin Color Detection

Authors:
Francisco A. Pujol;Rafael Espí;Higinio Mora;José Luis Sánchez
Affiliations:
Specialized Processor Architectures Lab Dept. Tecnología Informática y Computación, Universidad de Alicante, Alicante, (Spain) E-03080;Specialized Processor Architectures Lab Dept. Tecnología Informática y Computación, Universidad de Alicante, Alicante, (Spain) E-03080;Specialized Processor Architectures Lab Dept. Tecnología Informática y Computación, Universidad de Alicante, Alicante, (Spain) E-03080;Specialized Processor Architectures Lab Dept. Tecnología Informática y Computación, Universidad de Alicante, Alicante, (Spain) E-03080
Venue:
MICAI '08 Proceedings of the 7th Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
Year:
2008

Citing 5
Cited 0

Fuzzy thresholding: mathematical framework, bound functions and weighted moving average technique

Pattern Recognition Letters
Detecting Faces in Images: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Skin Color Detection Using Multiple Cues

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
VALID: a new practical audio-visual database, and comparative results

AVBPA'05 Proceedings of the 5th international conference on Audio- and Video-Based Biometric Person Authentication
A model based on linguistic 2-tuples for dealing with multigranularhierarchical linguistic contexts in multi-expert decision-making

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Skin detection is a useful tool for many subsequent image processing tasks, such as face detection, face tracking or human-computer interfaces. In many cases, using a skin color detection scheme is related to a proper representation of the color space chosen to interpret image information. In this work, we propose a fuzzy system for detecting skin in the RGB color space, so that each color plane is modeled using fuzzy sets. As a consequence, the development of the membership functions, the inference system and the defuzzifying process are described throughout this paper. The experiments have been performed with the XM2VTS and VALID face databases and the results show that our system has high detection rates and low false positive rates compared to other similar skin color detectors.