ICIP 2006, Atlanta, GA

Slide Show

Atlanta Conv. & Vis. Bureau


Technical Program

Paper Detail

Session:Machine Learning for Image and Video Classification
Time:Monday, October 9, 14:20 - 17:00
Presentation: Poster
Authors: Sangho Yoon; Stanford University 
 Michael Harville; Hewlett-Packard Laboratories 
 Harlyn Baker; Hewlett-Packard Laboratories 
 Nina Bhatii; Hewlett-Packard Laboratories 
Abstract: We describe an automatic, low-cost method for classifying skin color, independent of lighting and imaging device characteristics, using consumer digital cameras and a simple color calibration target. After color normalization and face detection are performed as described in prior work, pixels within the face region are clustered in color space in an unsupervised fashion, and a Gaussian mixture model (GMM) of the person's skin color is formed from the pixels belonging to the densest clusters containing at least some minimum fraction of the total pixels. This technique allows accurate modeling of non-uniformities in skin tone that are common in individuals, while avoiding contamination from shadows, specularities, eyes, lips, hair, and background. We incorporate these models into a skin color classification framework with improved performance over prior work. Given a set of exemplar face images with skin color labels assigned by an expert, we predict the label that would be chosen by the same expert for a new, test image by comparison of the respective GMMs of the test image and each exemplar. Specifically, we select the label of the exemplar image whose GMM has smallest Kullback-Leibler divergence from that of the test image.