Optimization of LBP parameters

Author

Loderer, Marek ; Pavlovicova, Jarmila

Author_Institution

Fac. of Electr. Eng. & Inf. Technol., Slovak Univ. of Technol. in Bratislava, Bratislava, Slovakia

fYear

2014

fDate

10-12 Sept. 2014

Firstpage

1

Lastpage

4

Abstract

In this paper, we propose the optimal parameters of local binary patterns such as type of pattern, size of blocks in the feature space and distance measure for face recognition using a genetic algorithm. The genetic algorithm is able to optimize all these parameters quickly and to improve the recognition accuracy. We provide a comparative study of three types of local binary patterns (LBP, LGP and NRLBP) and four distance measures (L1, L2, χ², EMD). The genetic algorithm is also used to optimize parameters such as dimension of histograms. Our results are tested on three different face databases which have the similar properties. We can set these optimal parameters into our face recognition system suitable for the next-generation of hybrid broadcast broadband television.

Keywords

face recognition; feature extraction; genetic algorithms; LBP parameter optimization; LGP; NRLBP; block size; distance measure; face recognition; feature space; genetic algorithm; hybrid broadcast broadband television; local binary patterns; recognition accuracy improvement; Accuracy; Databases; Face; Face recognition; Feature extraction; Genetic algorithms; Histograms; Face recognition; LBP; LGP; NRLBP; genetic algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

ELMAR (ELMAR), 2014 56th International Symposium

Conference_Location

Zadar

Type

conf

DOI

10.1109/ELMAR.2014.6923329

Filename

6923329