Face Recognition with Single Sample Based on Candide-3 Reconstruction Model

Abstract:

In this study, we present a method for virtual images generation based on Candide-3 model to increase the number of training samples for the face recognition with single sample, where the Principle Component Analysis is used for feature extraction and the test samples are classified by the method of Support Vector Machine (SVM). Experimental results on from the YaleB and ORL databases show that the recognition rate of the face recognition with single sample can be improved by the proposed method.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 3623-3628
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.3623
• Online since: August 2013
• Authors: Nan Deng, Ya Bo Pei, Zheng Guang Xu
• Keywords: Candide-3 Model, Face Recognition, Single Sample, Support Vector Machine (SVM)

References

[1] Xiaoyang Tan, Songcan Chen, Zhihua Zhou, et al., Face recognition from a single image per person: A survey, Pattern Recognition, vol 39, no 9, pp.1725-1745, (2006).

DOI: 10.1016/j.patcog.2006.03.013

[2] Beymer. D, Poggio. T, Face Recognition from One Example View, Proc of Computer Vision, pp.500-507, (1995).

DOI: 10.1109/iccv.1995.466898

[3] S-G Shan, B Cao, W Gao, et al., Extend Fisherfaces for Face Recognition from a Single Example Image per Person,. Proceedings of the IEEE International Symposium on Circuits and Systems, vol 2, pp.81-84, (2002).

DOI: 10.1109/iscas.2002.1010929

[4] D-Q Zhang, S-C Chen, Z-H Zhou, A new face recognition method based on SVD perturbation for single example image per person, Applied mathematics and computation vol 163, no 2, pp.895-907, (2005).

DOI: 10.1016/j.amc.2004.04.016

[5] X Lu, R L Hsu, et al., Face recognition with 3D model-based synthesis,. Biometric Authentication, Lecture Notes in Computer Science, vol 3072, pp.147-162, (2004).

[6] D-L Jiang, Y-X Hu, et al., Efficient 3D Reconstruction for Face Recognition, [J]. Pattern Recognition, vol 38, no 6, pp.787-798, (2005).

DOI: 10.1016/j.patcog.2004.11.004

[7] Y-K Hu, Y Zheng, Z-F Wang. Reconstruction of 3D Face from a Single 2D Image for Face Recognition, Proceedings 2nd Joint IEEE International Workshop on VS-PETS, Beijing, pp.217-222, (2005).

DOI: 10.1109/vspets.2005.1570918

[8] J Ahlberg. CANDIDE-3 – An Updated Parameterised Face,. Report No. LiTH-ISY-R-2326, http: /www. bk. isy. liu. se/publications/LiTH-ISY-R-2, Dept. of Electrical Engineering, Linköping University, Sweden, (2001).

DOI: 10.3384/diss.diva-100820

[9] Cootes T F, Taylor C, Cooper D., Active shape models-their training and application,. Computer Vision and Image Understanding, vol 61, no 1, pp.38-59, (1995).

DOI: 10.1006/cviu.1995.1004

[10] RichardS. Wright. Jr., OpenGL SuperBible Fifth Edition, Posts & Telecom Press，(2010).

[11] ZHANG Jian-ming，Chen Fu-bing，Yang jing-yu, Some reseaches on face recognition with one training image per person, , Computer science，vol 33, no 2, pp.225-229, (2006).

[12] ZHANG Jian-ming, LIU Xiao, FAN Li-jing, Face Recognition with Single Sample Based on Three-layer Virtual Image Generation, [J]. Computer engineering， vol 36, no 9, pp.187-189, (2010).

[13] XU Xiao-yong, Face Recognition Method for Single Sample Based on Virtual Image, Computer engineering, vol 38, no 1, pp.143-145, (2012).