Automatic Skin Pixel Selection and Skin Color Classification

We describe an automatic 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 is performed, pixels of each face image are clustered in an unsupervised fashion. Pixels likely to be representative of skin color, rather than of distractors such as shadows, specularities, eyes, and lips, are identified by selecting the dominant clusters that have large number of pixels assigned per volume. A Gauss mixture model (GMM) of a person's skin color is formed from the pixels belonging to the selected clusters. When a set of exemplar images with skin color labels by an expert, we show that the label assigned by the same expert to a new, test face image can be predicted by comparison of the GMMs of the test image and the exemplars. Specifically, we use the label of the exemplar whose GMM has smallest KL divergence from that of the test image.

[1]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[2]  Shiri Gordon,et al.  An efficient image similarity measure based on approximations of KL-divergence between two gaussian mixtures , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[3]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[4]  Sabine Süsstrunk,et al.  Consistent image-based measurement and classification of skin color , 2005, IEEE International Conference on Image Processing 2005.

[5]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[6]  Thomas M. Cover,et al.  Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing) , 2006 .

[7]  I. Lemahieu,et al.  Consistent digital color image acquisition of the skin , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[8]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[9]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[10]  Tamás Linder,et al.  Mismatch in high-rate entropy-constrained vector quantization , 2003, IEEE Trans. Inf. Theory.

[11]  Nuno Vasconcelos,et al.  On the complexity of probabilistic image retrieval , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[12]  Robert M. Gray,et al.  Lloyd clustering of Gauss mixture models for image compression and classification , 2005, Signal Process. Image Commun..

[13]  M. Nischik,et al.  Analysis of skin erythema using true-color images , 1997, IEEE Transactions on Medical Imaging.

[14]  David G. Stork,et al.  Pattern Classification , 1973 .

[15]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[16]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[17]  H. Takiwaki.  Measurement of skin color: practical application and theoretical considerations. , 1998, The journal of medical investigation : JMI.