Face Recognition by Humans: Nineteen Results All Computer Vision Researchers Should Know About

Sinha, Pawan; Balas, Benjamin; Ostrovsky, Yuri; Russell, Richard

doi:10.1109/jproc.2006.884093

Cited by 557 publications

(343 citation statements)

References 87 publications

Supporting

Mentioning

314

Contrasting

Unclassified

Order By: Relevance

“…In Torralba et al (2007), a low dimensional image representation is used to guide attention incorporating information about the scene context and task constraints. Studies on face perception (Bachmann, 1991;Harmon & Julesz, 1973;Schyns & Oliva, 1997;Sinha et al, 2006) have shown that when a picture of a face is down-sampled to a resolution as low as 16x16 pixels, observers are able to perform various face recognition tasks reliably (i.e. identity, gender, emotion).…”

Section: Introductionmentioning

confidence: 99%

How many pixels make an image?

2009

View full text Add to dashboard Cite

The human visual system is remarkably tolerant to degradation in image resolution: human performance in scene categorization remains high no matter whether low resolution images or multi-mega pixel images are used. This observation raises the question of how many pixels are required to form a meaningful representation of an image and identify the objects it contains. In this paper, we show that very small thumbnail images at the spatial resolution of 32x32 color pixels provide enough information to identify the semantic category of real world scenes. Most strikingly, this low resolution permits observers to report, with 80% accuracy, 4-5 of the objects that the scene contains, despite the fact that some of these objects are unrecognizable in isolation. The robustness of the information available at very low resolution for describing semantic content of natural images could be an important asset to explain the speed and efficiently at which the human brain comprehends the gist of visual scenes.

show abstract

Section: Introductionmentioning

confidence: 99%

How many pixels make an image?

2009

View full text Add to dashboard Cite

show abstract

“…Cognitive psychological research, employing face pool comparison tasks, demonstrated that the true positive hit rates were ranged below 80%. The hit rates dramatically dropped when facial textures, hairs, skin colours, light or posture were removed or changed from the actual features [8,[94][95][96][97]. The overall lower hit rates in this research maybe caused by these limitations of difficulties in unifying the photographs and unfamiliar face recognition for the accuracy survey.…”

Section: Discussionmentioning

confidence: 74%

The unfamiliar face effect on forensic craniofacial reconstruction and recognition

Lee

Wilkinson

2016

Forensic Science International

View full text Add to dashboard Cite

Previous research into the reliability of forensic craniofacial reconstruction (CFR) has focused primarily on the accuracy of reconstructed faces from European or African ancestry skulls. Moreover, the recognition of CFR in relation to the experience and ancestry of the practitioners and the assessors has not been previously considered. The cross-race effect is a recognised phenomenon in psychology studies, where familiar ancestry faces are recognised more readily than unfamiliar ancestry faces, but there is a paucity of research addressing the relationship between the accuracy of reconstructed faces and the familiarity with this ancestry by the practitioners/assessors. The aims of this research were to investigate whether 'unfamiliar-race effect' has any influence on the accuracy of CFR and to evaluate how much the correct recognition rate of CFR is affected by the cross-race effect. Eight CFRs from three ancestry groups were produced by experienced practitioners in order to explore the aims. The results demonstrated that practitioners produced more recognisable CFRs using skulls from a familiar ancestry than skulls from unfamiliar ancestries.

show abstract

“…Recognition may be multi-modal (for example, combining face data with body shape or gait), but the studies in [29] indicate that facial information is one of the principal ways in which we recognise each other. A multi-modal recognition system could take metrics such as gait into consideration, combined with facial recognition to increase robustness.…”

Section: Face Recognition By Humansmentioning

confidence: 99%

“…A robust recognition system will combine results from multiple techniques. [29] asserts that the spatial relationship between facial features is more important than the shape of the features themselves. Like humans, machines can accurately recognise faces from a low-resolution image (see [27]) as these spatial relationships are preserved.…”

Section: Face Recognition By Humansmentioning

confidence: 99%

Real-Time Face Recognition from Surveillance Video

Davis

Popov

Surlea

2011

Intelligent Video Event Analysis and Understanding

View full text Add to dashboard Cite

This chapter describes an experimental system for the recognition of human faces from surveillance video. In surveillance applications, the system must be robust to changes in illumination, scale, pose and expression. The system must also be able to perform detection and recognition rapidly in real time.Our system detects faces using the Viola-Jones face detector, then extracts local features to build a shape-based feature vector. The feature vector is constructed from ratios of lengths and differences in tangents of angles, so as to be robust to changes in scale and rotations in-plane and out-of-plane. Consideration was given to improving the performance and accuracy of both the detection and recognition steps.

show abstract

Face Recognition by Humans: Nineteen Results All Computer Vision Researchers Should Know About

Cited by 557 publications

References 87 publications

How many pixels make an image?

How many pixels make an image?

The unfamiliar face effect on forensic craniofacial reconstruction and recognition

Real-Time Face Recognition from Surveillance Video

Contact Info

Product

Resources

About