Skip to content

This paper presents a new approach for face recognition system based on template matching in frequency domain. The idea of using template matching is to design a specific Minimum Average correlation energy filter (MACE). The proposed recognition technique is performed by a cross correlation between the input images and the designed filter. The t…

Notifications You must be signed in to change notification settings

hjleed/Face-Recognition-System-Based-on-Template-Matching-in-Frequency-Domain

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Face Recognition System Based on Template Matching in Frequency Domain

It is a new approach for face recognition system based on template matching in frequency domain. The idea of using template matching is to design a specific Minimum Average correlation energy filter (MACE). The proposed recognition technique is performed by a cross correlation between the input images and the designed filter. The technique is applied on the ORL database which consists of more than 400 face images.
The experimental results show that this technique is powerful and improve the recognition accuracy

Test Image 1

@inproceedings{ghar2013face,
title={Face Recognition System Based on Template Matching in Frequency Domain},
author={Ghariba, Bashir and Jleed, Hitham},
booktitle={2013 BCS International IT Conference},
pages={13--16},
year={2013},
organization={IEEE}
}

About

This paper presents a new approach for face recognition system based on template matching in frequency domain. The idea of using template matching is to design a specific Minimum Average correlation energy filter (MACE). The proposed recognition technique is performed by a cross correlation between the input images and the designed filter. The t…

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages