Bergasa, L.M., Mazo, M., Gardel, A., Sotelo, M.A., and Boquete, L. Unsupervised and adaptive Gaussian skin-color model, Image and Vision Computing 18, pp.987-1003, 2000.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....uses skin color segmentation based on the work of [Yan96a] to get an initial set of face candidates. Our experimental results show that the stated before the normalized color space gives repeated results on images which were acquired from an inexpensive on board CCD camera. The authors of work [Ber00a] came to the conclusion that the normalized color space is the best chrominance representation considering the face detection tasks. Valuable remarks about a performance of some color spaces in color image segmentation can be found in work [Ska94a] One of the advantage of the normalized color ....

Bergasa, L.M., Mazo, M., Gardel, A., Sotelo, M.A., and Boquete, L. Unsupervised and adaptive Gaussian skin-color model, Image and Vision Computing 18, pp.987-1003, 2000.

....(b) a 2D projection in the C b C r subspace; c) a 2D projection in the (C b =Y ) C r =Y ) subspace. Modeling skin color requires choosing an appropriate color space and identifying a cluster associated with skin color in this space. It has been observed that the normalized red green (rg) space [5] is not the best choice for face detection [40] 34] Based on Terrillon et al. s [40] comparison of nine di erent color spaces for face detection, the tint saturation luma (TSL) space provides the best results for two kinds of Gaussian density models (unimodal and a mixture of Gaussians) We ....

L.M. Bergasa, M. Mazo, A. Gardel, M.A. Sotelo, and L. Boquete, \Unsupervised and Adaptive Gaussian Skin-color Model," Image and Vision Computing, vol. 18, pp. 987-1003.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC