Interpolation of low resolution images for improved accuracy in human face recognition

Author

Elazhari, Abbas ; Ahmadi, Mahdi

Author_Institution

Dept. of Electr. & Comput. Eng., Univ. of Windsor, Windsor, ON, Canada

fYear

2013

fDate

8-11 Dec. 2013

Firstpage

425

Lastpage

428

Abstract

This paper presents the effect of interpolation schemes, namely, nearest-neighbor, bilinear, and bicubic, when applied to low-resolution images as a preprocessing step for improving the recognition rate in human face recognition system. Three feature extraction methods are used, namely, Local Binary Pattern, Discrete Wavelet Transform, and Block-Based Discrete Cosine Transform, with and without interpolation for comparison purpose. The experiments are conducted on the ORL database. Bicubic and bilinear improve the recognition rate of low resolution images considerably.

Keywords

discrete cosine transforms; discrete wavelet transforms; face recognition; feature extraction; image resolution; interpolation; ORL database; bicubic scheme; bilinear scheme; block-based discrete cosine transform; discrete wavelet transform; feature extraction method; human face recognition system; interpolation schemes; local binary pattern; low resolution images; nearest-neighbor scheme; recognition rate; Discrete wavelet transforms; Face; Face recognition; Feature extraction; Image resolution; Interpolation; Principal component analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Circuits, and Systems (ICECS), 2013 IEEE 20th International Conference on

Conference_Location

Abu Dhabi

Type

conf

DOI

10.1109/ICECS.2013.6815445

Filename

6815445