A neural network based human face recognition of low resolution images

Author

Elazhari, Abbas ; Ahmadi, Majid

Author_Institution

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

fYear

2014

fDate

3-7 Aug. 2014

Firstpage

185

Lastpage

190

Abstract

In this work, a human face recognition algorithm based on Block-based Discrete Cosine Transform (BBDCT) and Extreme Learning Machine (ELM) is proposed for low resolution input images. We also investigate the effect of image resolution on the recognition rate of the proposed face recognition system. Furthermore to improve the low resolution input images, three interpolation schemes, namely, Nearest-Neighbor, Bilinear, and Bicubic, are used as a pre-processing step to obtain better recognition rate. The experiments are conducted on the ORL database to demonstrate the performance of the proposed algorithm.

Keywords

discrete cosine transforms; face recognition; image resolution; interpolation; learning (artificial intelligence); neural nets; BBDCT; ELM; ORL database; bicubic interpolation; bilinear interpolation; block-based discrete cosine transform; extreme learning machine; human face recognition; image resolution; interpolation scheme; low resolution images; nearest-neighbor interpolation; neural network; recognition rate; Discrete cosine transforms; Face recognition; Feature extraction; Image recognition; Image resolution; Interpolation; Neurons; Discrete Cosine Transform; Extreme learning Machine; Face Recognition; Interpolation; Low resolution;

fLanguage

English

Publisher

ieee

Conference_Titel

World Automation Congress (WAC), 2014

Conference_Location

Waikoloa, HI

Type

conf

DOI

10.1109/WAC.2014.6935767

Filename

6935767