An improved fast face recognition algorithm based on adjacent pixel intensity difference quantization histogram

Author

Lee, Fei-fei ; Kotani, Koji ; Chen, Qiu ; Ohmi, Tadahiro

Author_Institution

New Ind. Creation Hatchery Center, Tohoku Univ., Sendai

Volume

1

fYear

2008

fDate

30-31 Aug. 2008

Firstpage

316

Lastpage

320

Abstract

In this paper, we present an improved face recognition algorithm based on adjacent pixel intensity difference quantization (APIDQ) histogram method proposed by Kotani et al. [12]. We optimize the quantization method of APIDQ according to the maximum entropy principle (MEP), and determine the best parameters for APIDQ. Experimental results show maximum average recognition rate of 97.2% for 400 images of 40 persons (10 images per person) from the publicly available AT&T face database.

Keywords

face recognition; image resolution; maximum entropy methods; quantisation (signal); APIDQ; AT&T face database; MEP; adjacent pixel intensity difference quantization histogram; improved fast face recognition algorithm; maximum entropy principle; Entropy; Face recognition; Filtering; Histograms; Image databases; Image recognition; Low pass filters; Pixel; Quantization; Wavelet analysis; Adjacent pixel intensity difference quantization (APIDQ); Face recognition; Maximum entropy principle (MEP);

fLanguage

English

Publisher

ieee

Conference_Titel

Wavelet Analysis and Pattern Recognition, 2008. ICWAPR '08. International Conference on

Conference_Location

Hong Kong

Print_ISBN

978-1-4244-2238-8

Electronic_ISBN

978-1-4244-2239-5

Type

conf

DOI

10.1109/ICWAPR.2008.4635796

Filename

4635796