Minimum resolution for human face detection and identification

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

12 Citations (Scopus)

Abstract

Our goal is to build an automated system for face recognition. Such a system for a realistic application is likely to have thousands, possibly millions of faces. Hence, it is essential to have a compact representation for a face. So an important issue is the minimum spatial and grayscale resolutions necessary for a pattern to be detected as a face and then identified. Several experiments were performed to estimate these limits using a collection of 64 faces imaged under very different conditions. All experiments were performed using human observers. The results indicate that there is enough information in 32 × 32 × 4 bpp images for human eyes to detect and identify the faces. Thus an automated system could represent a face using only 512 bytes.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsBernice E. Rogowitz, Michael H. Brill, Jan P. Allebach
PublisherPubl by Int Soc for Optical Engineering
Pages81-89
Number of pages9
Volume1453
StatePublished - 1991
EventSPIE/IS&T Symposium on Electronic Imaging Science and Technology - San Jose, CA, USA
Duration: Feb 24 1991Mar 1 1991

Other

OtherSPIE/IS&T Symposium on Electronic Imaging Science and Technology
CitySan Jose, CA, USA
Period2/24/913/1/91

Fingerprint

Face recognition
spatial resolution
estimates
Experiments

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Samal, A. K. (1991). Minimum resolution for human face detection and identification. In B. E. Rogowitz, M. H. Brill, & J. P. Allebach (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 1453, pp. 81-89). Publ by Int Soc for Optical Engineering.

Minimum resolution for human face detection and identification. / Samal, Ashok K.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / Bernice E. Rogowitz; Michael H. Brill; Jan P. Allebach. Vol. 1453 Publ by Int Soc for Optical Engineering, 1991. p. 81-89.

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

Samal, AK 1991, Minimum resolution for human face detection and identification. in BE Rogowitz, MH Brill & JP Allebach (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 1453, Publ by Int Soc for Optical Engineering, pp. 81-89, SPIE/IS&T Symposium on Electronic Imaging Science and Technology, San Jose, CA, USA, 2/24/91.
Samal AK. Minimum resolution for human face detection and identification. In Rogowitz BE, Brill MH, Allebach JP, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 1453. Publ by Int Soc for Optical Engineering. 1991. p. 81-89
Samal, Ashok K. / Minimum resolution for human face detection and identification. Proceedings of SPIE - The International Society for Optical Engineering. editor / Bernice E. Rogowitz ; Michael H. Brill ; Jan P. Allebach. Vol. 1453 Publ by Int Soc for Optical Engineering, 1991. pp. 81-89
@inproceedings{397f35a0b1dd49dcaf6c0a134bbff401,
title = "Minimum resolution for human face detection and identification",
abstract = "Our goal is to build an automated system for face recognition. Such a system for a realistic application is likely to have thousands, possibly millions of faces. Hence, it is essential to have a compact representation for a face. So an important issue is the minimum spatial and grayscale resolutions necessary for a pattern to be detected as a face and then identified. Several experiments were performed to estimate these limits using a collection of 64 faces imaged under very different conditions. All experiments were performed using human observers. The results indicate that there is enough information in 32 × 32 × 4 bpp images for human eyes to detect and identify the faces. Thus an automated system could represent a face using only 512 bytes.",
author = "Samal, {Ashok K}",
year = "1991",
language = "English (US)",
volume = "1453",
pages = "81--89",
editor = "Rogowitz, {Bernice E.} and Brill, {Michael H.} and Allebach, {Jan P.}",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "Publ by Int Soc for Optical Engineering",

}

TY - GEN

T1 - Minimum resolution for human face detection and identification

AU - Samal, Ashok K

PY - 1991

Y1 - 1991

N2 - Our goal is to build an automated system for face recognition. Such a system for a realistic application is likely to have thousands, possibly millions of faces. Hence, it is essential to have a compact representation for a face. So an important issue is the minimum spatial and grayscale resolutions necessary for a pattern to be detected as a face and then identified. Several experiments were performed to estimate these limits using a collection of 64 faces imaged under very different conditions. All experiments were performed using human observers. The results indicate that there is enough information in 32 × 32 × 4 bpp images for human eyes to detect and identify the faces. Thus an automated system could represent a face using only 512 bytes.

AB - Our goal is to build an automated system for face recognition. Such a system for a realistic application is likely to have thousands, possibly millions of faces. Hence, it is essential to have a compact representation for a face. So an important issue is the minimum spatial and grayscale resolutions necessary for a pattern to be detected as a face and then identified. Several experiments were performed to estimate these limits using a collection of 64 faces imaged under very different conditions. All experiments were performed using human observers. The results indicate that there is enough information in 32 × 32 × 4 bpp images for human eyes to detect and identify the faces. Thus an automated system could represent a face using only 512 bytes.

UR - http://www.scopus.com/inward/record.url?scp=0025846715&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025846715&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0025846715

VL - 1453

SP - 81

EP - 89

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Rogowitz, Bernice E.

A2 - Brill, Michael H.

A2 - Allebach, Jan P.

PB - Publ by Int Soc for Optical Engineering

ER -