Face Detection Method Using PCNN and Skin Color Model

Abstract:

This paper presented a face detection method for the color image using pulse coupled neural network (PCNN) and skin color model. The color image which is processed well through light compensation is converted from RGB to YCbCr color space, then the skin area are divided into sub-block, and skin color segmentation is made for the image in YCbCr space. Finally, we use PCNN to extract all sub-block ignition time sequence, and calculate various sub-block difference degrees between target face and the tested image, if the difference degree is the smallest, then the target face himself is the same person. Experimental results show that the proposed method has higher accuracy and robustness, can obtain satisfactory detection effect.

• Periodical: Advanced Materials Research (Volumes 562-564)
• Pages: 1377-1381
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.562-564.1377
• Online since: August 2012
• Authors: Dong Ming Zhou, Hong Cai
• Keywords: Difference Degree, Face Detection, PCNN, Skin Color Model

References

[1] H. Adeli, A. Panakkat. A probabilistic neural network for earthquake magnitude prediction. Neural Networks, Vol. 22(10) (2009) pp.1018-1024.

DOI: 10.1016/j.neunet.2009.05.003

[2] Y. Kato, T. Hiranoa, O. Nakamura. Fast template matching algorithm for contour images based on its chain coded description applied for human face identification, Pattern Recognition, Vol. 40(6) (2007) pp.1646-1659.

DOI: 10.1016/j.patcog.2006.09.004

[3] Z. Jin, Z. Lou, J. Y. Yang et al. Face detection using template matching and skin-color information. Neurocomputing, Vol. 70(4-6) (2007) pp.794-800.

DOI: 10.1016/j.neucom.2006.10.043

[4] J. Wang, A. Barreto, L. Wang et al. Multilinear principal component analysis for face recognition with fewer features. Neurocomputing, Vol. 73(10-12) (2010) pp.1550-1555.

DOI: 10.1016/j.neucom.2009.08.022

[5] M. Jose, C. Gonzalez, A. Miguel et al. Detecting skin in face recognition systems: A colour spaces study. Digital Signal Processing, Vol. 20(3) (2010) pp.806-823.

DOI: 10.1016/j.dsp.2009.10.008

[6] H. S. Lee, D. Kim. Robust face tracking by integration of two separate trackers: Skin color and facial shape. Pattern Recognition Letters, Vol. 40 (11) (2007) pp.3225-3235.

DOI: 10.1016/j.patcog.2007.03.003

[7] F. Wen, J. Zhou, C. S. Zhang et al. color face detection based on local linear mapping neural network and brightness compensation. Journal of Tsinghua University (Natural Science Edition), Vol. 39 (7) (1999) pp.68-75. in Chinese.

[8] V. Abolghasemi, A. Ahmadyfard. An edge-based color-aided method for license plate detection. Image and Vision Computing, Vol. 27 (8) (2009) pp.1134-1142.

DOI: 10.1016/j.imavis.2008.10.012

[9] M. S. C. Almeida, L. B. Almeida. Wavelet-based separation of nonlinear show-through and bleed-through image mixtures. Neurocomputing, Vol. 72 (1-3) (2008) pp.57-70.

DOI: 10.1016/j.neucom.2007.12.048

[10] M. Wen, J. M. Chabagno, G. Silverman et al. Edge-strengthening of flat glass with acrylate coatings. Journal of Non-Crystalline Solids, Vol. 354 (45-46) (2008) pp.5060-5067.

DOI: 10.1016/j.jnoncrysol.2008.08.004