Region-based skin color detection

Authors: Poudel, R.P.K., Nait-Charif, H., Zhang, J.J. and Liu, D.

Volume: 1

Pages: 301-306

ISBN: 9789898565037

Abstract:

Skin color provides a powerful cue for complex computer vision applications. Although skin color detection has been an active research area for decades, the mainstream technology is based on the individual pixels. This paper presents a new region-based technique for skin color detection which outperforms the current state-of-the-art pixel-based skin color detection method on the popular Compaq dataset (Jones and Rehg, 2002). Color and spatial distance based clustering technique is used to extract the regions from the images, also known as superpixels. In the first step, our technique uses the state-of-the-art non-parametric pixel-based skin color classifier (Jones and Rehg, 2002) which we call the basic skin color classifier. The pixel-based skin color evidence is then aggregated to classify the superpixels. Finally, the Conditional Random Field (CRF) is applied to further improve the results. As CRF operates over superpixels, the computational overhead is minimal. Our technique achieves 91.17% true positive rate with 13.12% false negative rate on the Compaq dataset tested over approximately 14,000 web images.

https://eprints.bournemouth.ac.uk/20497/

Source: Scopus

Preferred by: Jian Jun Zhang and Hammadi Nait-Charif

Region-based skin color detection

Authors: Poudel, R.P.K., Nait-Charif, H., Zhang, J.J. and Liu, D.

Volume: 1

Pages: 301-306

Publisher: VISAPP

Abstract:

Skin color provides a powerful cue for complex computer vision applications. Although skin color detection has been an active research area for decades, the mainstream technology is based on the individual pixels. This paper presents a new region-based technique for skin color detection which outperforms the current state-of-the-art pixel-based skin color detection method on the popular Compaq dataset (Jones and Rehg, 2002). Color and spatial distance based clustering technique is used to extract the regions from the images, also known as superpixels. In the first step, our technique uses the state-of-the-art non-parametric pixel-based skin color classifier (Jones and Rehg, 2002) which we call the basic skin color classifier. The pixel-based skin color evidence is then aggregated to classify the superpixels. Finally, the Conditional Random Field (CRF) is applied to further improve the results. As CRF operates over superpixels, the computational overhead is minimal. Our technique achieves 91.17% true positive rate with 13.12% false negative rate on the Compaq dataset tested over approximately 14,000 web images.

https://eprints.bournemouth.ac.uk/20497/

Source: Manual

Preferred by: Rudra Poudel

Region-based Skin Color Detection.

Authors: Poudel, R.P.K., Nait-Charif, H., Zhang, J.J. and Liu, D.

Editors: Csurka, G. and Braz, J.

Pages: 301-306

Publisher: SciTePress

ISBN: 978-989-8565-03-7

https://eprints.bournemouth.ac.uk/20497/

http://www.informatik.uni-trier.de/~ley/db/conf/visapp/visapp2012-1.html

Source: DBLP

Region-based Skin Color Detection.

Authors: Poudel, R.P.K., Nait-Charif, H., Zhang, J.J. and Liu, D.

Volume: 1

Pages: 301-306

Publisher: VISAPP

Abstract:

Skin color provides a powerful cue for complex computer vision applications. Although skin color detection has been an active research area for decades, the mainstream technology is based on the individual pixels.

This paper presents a new region-based technique for skin color detection which outperforms the current state-of-the-art pixel-based skin color detection method on the popular Compaq dataset (Jones and Rehg, 2002). Color and spatial distance based clustering technique is used to extract the regions from the images, also known as superpixels. In the first step, our technique uses the state-of-the-art non-parametric pixel-based skin color classifier (Jones and Rehg, 2002) which we call the basic skin color classifier. The pixel-based skin color evidence is then aggregated to classify the superpixels. Finally, the Conditional Random Field (CRF) is applied to further improve the results. As CRF operates over superpixels, the computational overhead is minimal. Our technique achieves 91.17% true positive rate with 13.12% false negative rate on the Compaq dataset tested over approximately 14,000 web images.

https://eprints.bournemouth.ac.uk/20497/

Source: BURO EPrints