Wavelet Transform based Score Fusion for Face Recognition using SIFT Descriptors

Ameen, Musa M. and Ahmed, Bilal and Anwar, Muhammed and Hussein, Payam M. (2017) Wavelet Transform based Score Fusion for Face Recognition using SIFT Descriptors. Eurasian Journal of Science and Engineering, 2 (2). pp. 48-55. ISSN 24145629

[img] Text (Published Research Article)
eajse.v2i2p48.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (819kB)
Official URL: http://dx.doi.org/10.23918/eajse.v2i2p48

Abstract

One of the main areas in computer vision is automatic face recognition which deals with detecting human face autonomously. Developments and the progress in the field of face recognition have shown that many face recognition systems and applications the automated methods outperform humans. The conventional Scale-Invariant Feature Transform (SIFT) is used in face recognition where they provide high performances. However, this performance can be improved further by transforming the input into different domains before applying SIFT algorithm. Hence, we apply Discrete Wavelet Transform (DWT) or Gabor Wavelet Transform (GWT) at the input face images, which provides denser and extra information to be used by the conventional SIFT algorithm. Matching scores of SIFT from each subimage is fused before making final decision. Simulations show that the proposed approaches based on wavelet transforms using SIFT provides very high performance compared to the conventional algorithm.

Item Type: Article
Uncontrolled Keywords: SIFT, Face Recognition, Wavelet Transform, DWT, GWT, Score Fusion
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
T Technology > T Technology (General)
Divisions: Ishik Eurasian Journal of Science and Engineering > VOL 2, NO 2 (2017)
Depositing User: Depositor @ Ishik University
Date Deposited: 04 May 2018 10:52
Last Modified: 04 May 2018 10:52
URI: http://eprints.ishik.edu.iq/id/eprint/70

Actions (login required)

View Item View Item