Increasing the performance of face recognition in near infrared region with Hierarchical Grouping

Author

Yildiz, Huseyin ; Torunoglu, Osman ; Saraydemir, Safak

Author_Institution

Elektrik ve Elektron. Muhendisligi Bolumu, Kara Harp Okulu, Ankara, Turkey

fYear

2015

fDate

16-19 May 2015

Firstpage

1284

Lastpage

1287

Abstract

In this study, a new method is proposed to increase the performance for near infrared region(NIR) face recognition problem. this method is named as Hierarchical Grouping (HG). Principal Component Analysis (PCA) and Local Binary Pattern (LBP) methods which are widely used in literature, are used for feature extraction and for classification k Nearest Neighbor (kNN) method is used. The developed algorithm is tested on CBSR NIR database. Performance increase is obtained for the different preprocessed database by using hierarchical grouping method.

Keywords

face recognition; feature extraction; image classification; principal component analysis; visual databases; CBSR NIR database; LBP method; NIR face recognition; PCA; feature extraction; hierarchical grouping method; k nearest neighbor method; kNN method; local binary pattern methods; near infrared region; principal component analysis; Biomedical imaging; Computer vision; Conferences; Databases; Face; Face recognition; Principal component analysis; LBP; NIR; PCA; face recognition; hierarchical grouping; kNN;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Communications Applications Conference (SIU), 2015 23th

Conference_Location

Malatya

Type

conf

DOI

10.1109/SIU.2015.7130073

Filename

7130073