A Novel Color Face Segmentation Algorithm Using Multi-Feature

Abstract:

In the paper, a novel and simple color face segmentation algorithm using multi-features is presented. The regions are completely segmented in the basis of the edge image which is derived from the difference between the dilated image and the eroded image. The candidate face regions are selected by the skin-color and twice shape features, and make the selected regions convex using the convex hull of the set composed by the discrete points in the region. The true face regions are determined by the Euler number of the convex regions finally. The results show that the algorithm is very simple and fast, it is robust to the expression, pose and illumination.

• Periodical: Advanced Materials Research (Volumes 532-533)
• Pages: 1872-1876
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.532-533.1872
• Online since: June 2012
• Authors: Dong Mei Wei, Wei Dong Zhou
• Keywords: Candidate Face Regions, Circumscribed Convex Polygon, Edge, Interpolate, Regions

References

[1] R.L. Hsu, M. A. Mottaleb and A.K. Jain: Face Detection in Color Images, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 24(2002) No. 5, pp.696-706.

DOI: 10.1109/34.1000242

[2] B. Moghaddam and A. Pentland: Probabilistic Visual Learning for Object Representation, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19(1997)No. 7 , pp.696-710.

DOI: 10.1109/34.598227

[3] H.A. Rowley, S. Baluja and T. Kanade: Neural Network-Based Face Detection, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20(1998) No. 1, pp.23-38.

DOI: 10.1109/34.655647

[4] T.Q. Xu, B.C. Li and B. Wang: Face detection and recognition using neural network and hidden Markov models, Proceeding of the 2003 International conference on Neural Networks and Signal Processing, (Nanjing, China, Dec. 14-17, 2003) Vol. 1, pp.228-231.

DOI: 10.1109/icnnsp.2003.1279253

[5] P. Viola and M. Jones: Rapid Object Detection Using a Boosted Cascade of Simple Features, Proceeding of the 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(Kauai, Hawaii USA Dec. 8-14, 2001), Vol. 1, p. I-511-I-518.

DOI: 10.1109/cvpr.2001.990517

[6] J. Karlekar J and U.B. Desai: Finding faces in color images using wavelet transform, Proceeding of the 10th International Conference on Image Analysis and Processing (Venice, Italy, Sept. 27-29, 1999), pp.1085-1088.

DOI: 10.1109/iciap.1999.797744

[7] Y.T. Pai, S.J. Ruan, M.C. Shie and Y.C. Liu: A Simple and Accurate Color Face Detection Algorithm in Complex Background, Proceeding of the 2006 IEEE International Conference on Multimedia and Expo(Toronto, Canada, July 9-12, 2006), pp.1545-1548.

DOI: 10.1109/icme.2006.262838

[8] S.P. Yu: Face segmentation form the color image with the complex background (Ms, Nanjing University of Aeronautics, China 2001), p. (in Chinese).