Feature extraction based on graph discriminant embedding and its applications to face recognition
- 148 Downloads
Graph embedding-based learning methods have been widely employed to reduce the dimensionality of high-dimensional data, while how to construct adjacency graphs to discover the essential structure of the data is the key problem in these methods. In this paper, we present a novel algorithm called graph discriminant embedding (GDE) for feature extraction and recognition. GDE combines local information and label information of data points to construct two neighbor graphs, which help to pull the same-class samples nearer and nearer and repel the not-same-class samples farther and farther when they are projected onto a feature subspace. Significantly differing from most of the other graph embedding methods, GDE does not only emphasize the importance of the nearby points but also enhance the importance of the distant points which may have potential advantages for classification. Experimental results on the AR, CMU PIE and FERET face databases demonstrate the effectiveness of the proposed algorithm.
KeywordsManifold learning Feature extraction Face recognition Graph construction Marginal Fisher analysis
This work is supported by the National Natural Science Foundation of China (Grant Nos. 61503195 and 61502245), the China Postdoctoral Science Foundation (Grant No. 2016M600433), Open Fund Project of Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University) (No. MJUKF201717) and Open Fund Project of Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education (Nanjing University of Science and Technology) (No. JYB201709).
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
- Huang P, Chen CK (2009) Enhanced marginal Fisher analysis for face recognition. In: Proceedings of 2009 international conference on artificial intelligence and computational intelligence, pp 403–407Google Scholar
- Huang P, Tang ZM, Yang ZJ, Shi J (2013) Feature extraction using graph discriminant embedding. In: Proceedings of the 2013 6th international congress on image and signal processing (CISP2013), Hangzhou, China, pp 432–436Google Scholar
- Martinez AM, Benavente R (1998) The AR face database. CVC Technical Report #24, JuneGoogle Scholar
- Zhang DG, Wang X, Song XD, Zhang T, Zhu YN (2015d) New clustering routing method based on PECE for WSN. EURASIP J Wirel Commun Netw 2015(162):1–13Google Scholar
- Zhang DG, Li WB, Liu S, Zhang XD (2016a) Novel fusion computing method for bio-medical image of WSN based on spherical coordinate. J VibroEng 18(1):522–538Google Scholar
- Zhao CR, Lai ZH, Sui Y, Chen Y (2008) Local maximal marginal embedding with application to face recognition. In: Proceedings of 2008 chinese conference on pattern recognition, pp 1–6Google Scholar