A new and improves skin detection method using RGB vector space

Aznaveh, MM; Mirzaei, H; Roshan, E; Saraee, MH

Abstract

This paper describes a new method for skin detection based on RGB vector space. Skin color has proven to be a useful cue for pre-process of face detection, localization and tracking. Image content filtering, content aware video compression and image color balancing applications can also benefit from automatic detection of skin in images. Numerous works for skin color segmentation and detection have been reported in the literature in the last few years. In this paper first few pixel based methods are presented and then vector calculations as an efficient approach for determination of skin area based on implicit mathematical model is proposed. In order to evaluate our method we performed an experimental study. Results obtained are very promising and shows important advantages over other techniques.

Citation

Aznaveh, M., Mirzaei, H., Roshan, E., & Saraee, M. (2008, July). A new and improves skin detection method using RGB vector space. Presented at 5th International Multi-Conference on Systems, Signals and Devices, 2008. IEEE SSD 2008., Amman Jordan

• Presentation Conference Type: Other
• Conference Name: 5th International Multi-Conference on Systems, Signals and Devices, 2008. IEEE SSD 2008.
• Conference Location: Amman Jordan.
• Start Date: Jul 20, 2008
• End Date: Jul 23, 2008
• Deposit Date: Nov 4, 2011
• Book Title: 2008 5th International Multi-Conference on Systems, Signals and Devices
• DOI: https://doi.org/10.1109/SSD.2008.4632786
• Publisher URL: http://dx.doi.org/10.1109/SSD.2008.4632786
• Additional Information: Event Type : Conference