A Study on Optimal Face Ratio for Recognition Using Part-based Feature Extractor

This paper aims to investigate the optimal face ratio for recognition. Face data are normalized to several ratios, which are 25%, 50% (equivalent to right and left face), and 75% of the full-face. The advantages of using different face ratios are these face data reduce the amount of computational po...

Full description

Bibliographic Details
Main Authors: Neo, Han Foon, Teo, Chuan Chin, Teoh, Andrew Beng Jin
Format: Conference or Workshop Item
Language:English
Published: IEEE 2007
Subjects:
Online Access:http://shdl.mmu.edu.my/2949/
http://shdl.mmu.edu.my/2949/1/A%20Study%20on%20Optimal%20Face%20Ratio.pdf
_version_ 1848790192908926976
author Neo, Han Foon
Teo, Chuan Chin
Teoh, Andrew Beng Jin
author_facet Neo, Han Foon
Teo, Chuan Chin
Teoh, Andrew Beng Jin
author_sort Neo, Han Foon
building MMU Institutional Repository
collection Online Access
description This paper aims to investigate the optimal face ratio for recognition. Face data are normalized to several ratios, which are 25%, 50% (equivalent to right and left face), and 75% of the full-face. The advantages of using different face ratios are these face data reduce the amount of computational power and storage requirements significantly. For fair comparison, various part-based linear subspace feature extractors, namely Non-negative matrix factorization (NMF), Local NMF (LNMF) and Spatially Confined NMF (SFNMF) are used to estimate the optimal face ratio. Our results show that 75% faces are good enough to produce demonstrably recognition accuracy.
first_indexed 2025-11-14T18:08:43Z
format Conference or Workshop Item
id mmu-2949
institution Multimedia University
institution_category Local University
language English
last_indexed 2025-11-14T18:08:43Z
publishDate 2007
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling mmu-29492021-09-21T07:51:34Z http://shdl.mmu.edu.my/2949/ A Study on Optimal Face Ratio for Recognition Using Part-based Feature Extractor Neo, Han Foon Teo, Chuan Chin Teoh, Andrew Beng Jin T Technology (General) QA75.5-76.95 Electronic computers. Computer science This paper aims to investigate the optimal face ratio for recognition. Face data are normalized to several ratios, which are 25%, 50% (equivalent to right and left face), and 75% of the full-face. The advantages of using different face ratios are these face data reduce the amount of computational power and storage requirements significantly. For fair comparison, various part-based linear subspace feature extractors, namely Non-negative matrix factorization (NMF), Local NMF (LNMF) and Spatially Confined NMF (SFNMF) are used to estimate the optimal face ratio. Our results show that 75% faces are good enough to produce demonstrably recognition accuracy. IEEE 2007-12 Conference or Workshop Item NonPeerReviewed text en http://shdl.mmu.edu.my/2949/1/A%20Study%20on%20Optimal%20Face%20Ratio.pdf Neo, Han Foon and Teo, Chuan Chin and Teoh, Andrew Beng Jin (2007) A Study on Optimal Face Ratio for Recognition Using Part-based Feature Extractor. In: 2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System, 16-18 Dec. 2007, Shanghai, China. https://ieeexplore.ieee.org/document/4618846 10.1109/SITIS.2007.52 10.1109/SITIS.2007.52 10.1109/SITIS.2007.52
spellingShingle T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
Neo, Han Foon
Teo, Chuan Chin
Teoh, Andrew Beng Jin
A Study on Optimal Face Ratio for Recognition Using Part-based Feature Extractor
title A Study on Optimal Face Ratio for Recognition Using Part-based Feature Extractor
title_full A Study on Optimal Face Ratio for Recognition Using Part-based Feature Extractor
title_fullStr A Study on Optimal Face Ratio for Recognition Using Part-based Feature Extractor
title_full_unstemmed A Study on Optimal Face Ratio for Recognition Using Part-based Feature Extractor
title_short A Study on Optimal Face Ratio for Recognition Using Part-based Feature Extractor
title_sort study on optimal face ratio for recognition using part-based feature extractor
topic T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2949/
http://shdl.mmu.edu.my/2949/
http://shdl.mmu.edu.my/2949/
http://shdl.mmu.edu.my/2949/1/A%20Study%20on%20Optimal%20Face%20Ratio.pdf