Minimum resolution for human face detection and identification

Ashok Samal

Minimum resolution for human face detection and identification

Ashok Samal

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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 language	English (US)
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Editors	Bernice E. Rogowitz, Michael H. Brill, Jan P. Allebach
Publisher	Publ by Int Soc for Optical Engineering
Pages	81-89
Number of pages	9
Volume	1453
State	Published - 1991
Event	SPIE/IS&T Symposium on Electronic Imaging Science and Technology - San Jose, CA, USA Duration: Feb 24 1991 → Mar 1 1991

Other

Other	SPIE/IS&T Symposium on Electronic Imaging Science and Technology
City	San Jose, CA, USA
Period	2/24/91 → 3/1/91

ASJC Scopus subject areas

Electrical and Electronic Engineering
Condensed Matter Physics

Cite this

Minimum resolution for human face detection and identification. / Samal, Ashok.
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 proceeding › Conference contribution

@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 = "Ashok Samal",

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",

note = "SPIE/IS&T Symposium on Electronic Imaging Science and Technology ; Conference date: 24-02-1991 Through 01-03-1991",

}

TY - GEN

T1 - Minimum resolution for human face detection and identification

AU - Samal, Ashok

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

T2 - SPIE/IS&T Symposium on Electronic Imaging Science and Technology

Y2 - 24 February 1991 through 1 March 1991

ER -

Minimum resolution for human face detection and identification

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this