On Effectiveness of Histogram of Oriented Gradient Features for Visible to Near Infrared Face Matching

Author

Dhamecha, Tejas Indulal ; Sharma, Parmanand ; Singh, Rajdeep ; Vatsa, Mayank

Author_Institution

IIIT-Delhi, New Delhi, India

fYear

2014

fDate

24-28 Aug. 2014

Firstpage

1788

Lastpage

1793

Abstract

The advent of near infrared imagery and it´s applications in face recognition has instigated research in cross spectral (visible to near infrared) matching. Existing research has focused on extracting textural features including variants of histogram of oriented gradients. This paper focuses on studying the effectiveness of these features for cross spectral face recognition. On NIR-VIS-2.0 cross spectral face database, three HOG variants are analyzed along with dimensionality reduction approaches and linear discriminant analysis. The results demonstrate that DSIFT with subspace LDA outperforms a commercial matcher and other HOG variants by at least 15%. We also observe that histogram of oriented gradient features are able to encode similar facial features across spectrums.

Keywords

face recognition; feature extraction; gradient methods; image matching; image texture; infrared imaging; visual databases; DSIFT; HOG variants; NIR-VIS-2.0 cross spectral face database; cross spectral matching; dimensionality reduction approach; face recognition; histogram; linear discriminant analysis; near infrared face matching; near infrared imagery; oriented gradient features; subspace LDA; textural feature extraction; Accuracy; Face; Feature extraction; Histograms; Measurement; Principal component analysis; Vectors; Cross Spectral Face Recognition; HOG Descriptor;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition (ICPR), 2014 22nd International Conference on

Conference_Location

Stockholm

ISSN

1051-4651

Type

conf

DOI

10.1109/ICPR.2014.314

Filename

6977025