Empirical studies of face recognition suggest that faces might be stored in memory by means of a few canonical representations. The nature of these canonical representations is, however, unclear. Although psychological data show a three-quarter-view advantage, physiological studies suggest profile and frontal views are stored in memory. A computational approach to reconcile these findings is proposed. The pattern of results obtained when different views, or combinations of views, are used as the internal representation of a two-stage identification network consisting of an autoassociative memory followed by a radial-basis-function network are compared. Results show that (i) a frontal and a profile view are sufficient to reach the optimal network performance; and (ii) all the different representations produce a three-quarter view advantage, similar to that generally described for human subjects. These results indicate that although three-quarter views yield better recognition than other views, they need not be stored in memory to show this advantage.
Get full access to this article
View all access options for this article.
References
1.
AbdiH, 1988“Generalized approaches for connectionist autoassociative memories: Interpretation, implication, and illustration for face processing”, in Artificial Intelligence and Cognitive Sciences Ed. DemongeotJ, (Manchester: Manchester University Press) pp 151–164.
2.
AbdiH, 1994“A neural network primer”Journal of Biological Systems2247–281.
3.
AbdiHValentinDEdelmanBO'TooleA, 1995“More about the difference between men and women: Evidence from linear neural networks and the principal component approach”Perception24539–562.
4.
BaddeleyAWoodheadM, 1981“Techniques for improving eye-witness identification skills”, paper presented at the SSRC Law and Psychology Conference, April 1981 Trinity College, Oxford.
5.
BruceV, 1982“Changing faces: Visual and non-visual coding processes in face recognition”British Journal of Psychology73105–116.
6.
BruceV, 1988Recognising Faces (London: Lawrence Erlbaum Associates).
7.
BruceVValentineTBaddeleyA, 1987“The basis of the 3/4 advantage in face recognition”Applied Cognitive Psychology1109–120.
8.
BruceVYoungA, 1986“Understanding face recognition”British Journal of Psychology77363–383.
9.
BruyerRGalvezC, 1989“The structural orientation of the mental representation of faces”Archives de Psychologie57259–269.
10.
DaviesGEllisHShepherdJ, 1978“Face recognition accuracy as a function of mode of presentation”Journal of Applied Psychology63180–187.
11.
DesimoneRAlbrightTGrossCBruceC, 1984“Stimulus selective properties of inferior temporal neurons in macaque”Journal of Neuroscience82051–2062.
12.
FaganJ, 1979“The origins of facial pattern recognition”, in Psychological Development from Infancy: Image to Intention Eds BornsteinMKeesenW, (Hillsdale, NJ: Lawrence Erlbaum Associates) pp 83–113.
13.
HasselmoMRollsEBaylisGNalwaV, 1989“Object-centered encoding by face-selective neurons in the cortex in the superior temporal sulcus of the monkey”Experimental Brain Research79417–429.
14.
KrouseF, 1981“Effects of pose, pose change, and delay on face recognition performance”Journal of Applied Psychology66651–654.
15.
LogieRBaddeleyAWoodheadM, 1987“Face recognition, pose and ecological validity”Applied Cognitive Psychology153–69.
16.
MacmillanNCreelmanC, 1991Detection Theory: A User's Guide (Cambridge: Cambridge University Press).
17.
O'TooleAAbdiHDeffenbacherKValentinD, 1993“A low dimensional representation of faces in the higher dimensions of the space”Journal of the Optical Society of America A10405–411.
18.
PalmerSRoschEChaseP, 1981“Canonical perspective and the perception of objects”, in Attention and PerformanceVolume IX, Eds LongJBaddeleyA, (Hillsdale, NJ: Lawrence Erlbaum Associates) pp 135–151.
19.
PattersonKBaddeleyA, 1977“When face recognition fails”Journal of Experimental Psychology: Human Learning and Memory3406–417.
20.
PentlandAMoghaddamBStarnerT, 1994“View-based and modular eigenspaces for face recognition”Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition (New York: IEEE) pp 84–90.
21.
PerrettDMistlinJChittyA, 1987“Visual neurons responsive to faces”Trends in Neurosciences10358–364.
22.
PerrettDMistlinAHarriesM, 1989“Seeing faces: The representation of facial information in temporal cortex”, in Seeing Contour and Colour Eds KulikowskiJDickinsonCMurrayI, (Oxford: Pergamon) pp 770–754.
23.
PerrettDMistlinAPotterDSmithPHeadAChittyABroennimannRMilnerAEllisM, 1986“Functional organization of visual neurons processing face identity”, in Aspects of Face Processing Eds EllisHJeevesMNewcombeFYoungA, (Dordrecht: Martinus Nijhoff) pp 187–198.
24.
PerrettDOramMHarriesMBevanRHietanenJBensonPThomasS, 1991“Viewer-centered and object-centered coding of heads in the macaque temporal cortex”Experimental Brain Research86159–173.
25.
PerrettDOramMHietanenJBensonP, 1994“Issues of representation in object vision”, in The Neuropsychology of High Level Vision: Collected Tutorial Essay Eds FarahMRatcliffG, (London: Lawrence Erlbaum Associates) pp 33–61.
26.
PerrettDRollsECaanW, 1982“Visual neurons responsive to faces in the monkey temporal cortex”Experimental Brain Research47329–342.
27.
PerrettDSmithPPotterDMistlinAHeadAMilnerAJeevesM, 1985“Visual cells in the temporal cortex sensitive to face view and gaze direction”Proceedings of the Royal Society of London, Series B223293–317.
28.
SirovichLKirbyM, 1987“Low dimensional procedure for the characterization of human faces”Journal of the Optical Society of America A4519–524.
29.
TurkMPentlandA, 1991“Eigenfaces for recognition”Journal of Cognitive Neurosciences371–86.
30.
ValentinDAbdiH, 1996“Can a linear autoassociator recognize faces from new orientations?”Journal of the Optical Society of America A13717–724.
31.
ValentinDAbdiHO'TooleA, 1994“Categorization and identification of human face images by neural networks: A review of the linear autoassociative and principal component approaches”Journal of Biological Systems2413–429.
