Research of Face Recognition Method Based on Multiple Classifier Fusion

Abstract:

In this paper, a recognition method for multiple classifiers is proposed, which combines an improved eigenface method with Support Vector Machine(SVM). The combining classifiers can make use of high recognition rate for SVM and high speed for distance classification. The distance classifier may classify the input images and give the final results when the rejecting rule is satisfied. Otherwise, these images are delivered to SVM for further classification. Experiment data show that the fusion of multiple classifiers for face recognition has higher efficiency, accuracy of recognition and lower rate of error recognition.

• Periodical: Advanced Materials Research (Volumes 532-533)
• Pages: 1075-1079
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.532-533.1075
• Online since: June 2012
• Authors: Yu Long Xu, Yong Mei Zhang
• Keywords: Face Recognition, Improved Eigenface Method, Multiple Classifier Combination, Principal Component Analysis (PCA), Support Vector Machine (SVM)

References

[1] LISZ, JAIN AK. Handbook of Face Recognition Facial Skin Color Modeling. Springer pattern Recognition Book, (2004), pp.109-131.

[2] Dailey M N, Cottrell G W, Adolphs R. A Six-unit Network Is All You Need to Discover Happiness. Proceedings of the Twenty-second Annual Conference of the Cognitive Science Society, Mabwan, NJ, USA, (2000).

[3] Lin S H, Kung S Y, Lin L J. Face recognition/detection by probabilistic decision-based neural network. IEEE Transactions on Neural Networks, Vol. 8(1997), pp.114-132.

DOI: 10.1109/72.554196

[4] Lu X, Wang Y, Jain A K. Combining Classifiers for Face Recognition. Proc. ICME 2003, IEEE International Conference on Multimedia & Expo. Baltimore: (2003), pp.13-16.

DOI: 10.1109/icme.2003.1221236

[5] Wan Feng, Du Minghui. The Comparison of Adaptability for Eigenface and EBGM. Computer Engineering and Applications. Vol. 26(2005), pp.69-71.