Comparison of human face matching behavior and computational image similarity measure

Wenfeng Chen; Changhong Liu; Karen Lander; Xiaolan Fu

doi:10.1007/s11432-009-0044-6

Comparison of human face matching behavior and computational image similarity measure

Wenfeng Chen, Changhong Liu, Karen Lander, Xiaolan Fu

Research output: Contribution to journal › Article › peer-review

Abstract

Computational similarity measures have been evaluated in a variety of ways, but few of the validated computational measures are based on a high-level, cognitive criterion of objective similarity. In this paper, we evaluate two popular objective similarity measures by comparing them with face matching performance in human observers. The results suggest that these measures are still limited in predicting human behavior, especially in rejection behavior, but objective measure taking advantage of global and local face characteristics may improve the prediction. It is also suggested that human may set different criterions for "hit" and "rejection" and this may provide implications for biologically-inspired computational systems. © 2009 Science in China Press and Springer-Verlag GmbH.

Original language	English
Pages (from-to)	316-321
Number of pages	5
Journal	Science in China, Series F: Information Sciences
Volume	52
Issue number	2
DOIs	https://doi.org/10.1007/s11432-009-0044-6
Publication status	Published - Feb 2009

Keywords

Face matching
Human behaviour
Image similarity
Objective measure
Subjective measure

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/s11432-009-0044-6

Cite this

@article{ad0c3ff512554ec3bca27a855e55e5f2,

title = "Comparison of human face matching behavior and computational image similarity measure",

abstract = "Computational similarity measures have been evaluated in a variety of ways, but few of the validated computational measures are based on a high-level, cognitive criterion of objective similarity. In this paper, we evaluate two popular objective similarity measures by comparing them with face matching performance in human observers. The results suggest that these measures are still limited in predicting human behavior, especially in rejection behavior, but objective measure taking advantage of global and local face characteristics may improve the prediction. It is also suggested that human may set different criterions for {"}hit{"} and {"}rejection{"} and this may provide implications for biologically-inspired computational systems. {\textcopyright} 2009 Science in China Press and Springer-Verlag GmbH.",

keywords = "Face matching, Human behaviour, Image similarity, Objective measure, Subjective measure",

author = "Wenfeng Chen and Changhong Liu and Karen Lander and Xiaolan Fu",

year = "2009",

month = feb,

doi = "10.1007/s11432-009-0044-6",

language = "English",

volume = "52",

pages = "316--321",

journal = "Science in China, Series F: Information Sciences",

issn = "1009-2757",

publisher = "Science in China Press",

number = "2",

}

TY - JOUR

T1 - Comparison of human face matching behavior and computational image similarity measure

AU - Chen, Wenfeng

AU - Liu, Changhong

AU - Lander, Karen

AU - Fu, Xiaolan

PY - 2009/2

Y1 - 2009/2

N2 - Computational similarity measures have been evaluated in a variety of ways, but few of the validated computational measures are based on a high-level, cognitive criterion of objective similarity. In this paper, we evaluate two popular objective similarity measures by comparing them with face matching performance in human observers. The results suggest that these measures are still limited in predicting human behavior, especially in rejection behavior, but objective measure taking advantage of global and local face characteristics may improve the prediction. It is also suggested that human may set different criterions for "hit" and "rejection" and this may provide implications for biologically-inspired computational systems. © 2009 Science in China Press and Springer-Verlag GmbH.

AB - Computational similarity measures have been evaluated in a variety of ways, but few of the validated computational measures are based on a high-level, cognitive criterion of objective similarity. In this paper, we evaluate two popular objective similarity measures by comparing them with face matching performance in human observers. The results suggest that these measures are still limited in predicting human behavior, especially in rejection behavior, but objective measure taking advantage of global and local face characteristics may improve the prediction. It is also suggested that human may set different criterions for "hit" and "rejection" and this may provide implications for biologically-inspired computational systems. © 2009 Science in China Press and Springer-Verlag GmbH.

KW - Face matching

KW - Human behaviour

KW - Image similarity

KW - Objective measure

KW - Subjective measure

U2 - 10.1007/s11432-009-0044-6

DO - 10.1007/s11432-009-0044-6

M3 - Article

SN - 1009-2757

VL - 52

SP - 316

EP - 321

JO - Science in China, Series F: Information Sciences

JF - Science in China, Series F: Information Sciences

IS - 2

ER -

Comparison of human face matching behavior and computational image similarity measure

Abstract

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this