A Study on optimal face ratio for recognition using part-based feature extractor

Han Foon Neo, Chuan Chin Teo, Andrew Beng Jin Teoh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007
Pages735-741
Number of pages7
DOIs
Publication statusPublished - 2007 Dec 1
Event3rd IEEE International Conference on Signal Image Technologies and Internet Based Systems, SITIS'07 - Jiangong Jinjiang, Shanghai, China
Duration: 2007 Dec 162007 Dec 18

Publication series

NameProceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007

Other

Other3rd IEEE International Conference on Signal Image Technologies and Internet Based Systems, SITIS'07
CountryChina
CityJiangong Jinjiang, Shanghai
Period07/12/1607/12/18

Fingerprint

Factorization

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Signal Processing

Cite this

Neo, H. F., Teo, C. C., & Teoh, A. B. J. (2007). A Study on optimal face ratio for recognition using part-based feature extractor. In Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007 (pp. 735-741). [4618846] (Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007). https://doi.org/10.1109/SITIS.2007.52
Neo, Han Foon ; Teo, Chuan Chin ; Teoh, Andrew Beng Jin. / A Study on optimal face ratio for recognition using part-based feature extractor. Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007. 2007. pp. 735-741 (Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007).
@inproceedings{1c68991d73554ec0842bf852d5ea3861,
title = "A Study on optimal face ratio for recognition using part-based feature extractor",
abstract = "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.",
author = "Neo, {Han Foon} and Teo, {Chuan Chin} and Teoh, {Andrew Beng Jin}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/SITIS.2007.52",
language = "English",
isbn = "9780769531229",
series = "Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007",
pages = "735--741",
booktitle = "Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007",

}

Neo, HF, Teo, CC & Teoh, ABJ 2007, A Study on optimal face ratio for recognition using part-based feature extractor. in Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007., 4618846, Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007, pp. 735-741, 3rd IEEE International Conference on Signal Image Technologies and Internet Based Systems, SITIS'07, Jiangong Jinjiang, Shanghai, China, 07/12/16. https://doi.org/10.1109/SITIS.2007.52

A Study on optimal face ratio for recognition using part-based feature extractor. / Neo, Han Foon; Teo, Chuan Chin; Teoh, Andrew Beng Jin.

Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007. 2007. p. 735-741 4618846 (Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A Study on optimal face ratio for recognition using part-based feature extractor

AU - Neo, Han Foon

AU - Teo, Chuan Chin

AU - Teoh, Andrew Beng Jin

PY - 2007/12/1

Y1 - 2007/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=57849125909&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57849125909&partnerID=8YFLogxK

U2 - 10.1109/SITIS.2007.52

DO - 10.1109/SITIS.2007.52

M3 - Conference contribution

AN - SCOPUS:57849125909

SN - 9780769531229

T3 - Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007

SP - 735

EP - 741

BT - Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007

ER -

Neo HF, Teo CC, Teoh ABJ. A Study on optimal face ratio for recognition using part-based feature extractor. In Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007. 2007. p. 735-741. 4618846. (Proceedings - International Conference on Signal Image Technologies and Internet Based Systems, SITIS 2007). https://doi.org/10.1109/SITIS.2007.52