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.
Similar content being viewed by others
References
Lades M, Vorbrüggen J C, Buhmann J, et al. Distortion invariant object recognition in the dynamic link architecture. IEEE T Comput, 1993, 42(3): 300–311
Biederman I, Kalocsai P. Neurocomputational bases of object and face recognition. Phil Trans R Soc B, 1997, 352: 1203–1219
Burton A M, Miller P, Bruce V, et al. Human and automatic face recognition: A comparison across image formats. Vision Res, 2001, 41: 3185–3195
Russell R, Biederman I, Nederhouser M, et al. The utility of surface reflectance for the recognition of upright and inverted faces. Vision Res, 2007, 47: 157–165
Steyvers M, Busey T. Predicting similarity ratings to faces using physical descriptions. In: Wenger M, Townsend J, eds. Computational, Geometric, and Process Perspectives on Facial Cognition: Contexts and Challenges. Lawrence Erlbaum Associates, 2000
Farah M J, Wilson K D, Drain H M, et al. What is “special” about face perception? Psychol Rev, 1998, 105: 482–498
Rakover S S. Featural vs. configurational information in faces: a conceptual and empirical analysis. Brit J Psychol, 2002, 93(1): 1–30
Adini Y, Moses Y, Ullman S. Face recognition: the problem of compensating for changes in illumination direction. IEEE Trans Patt Anal Mac Intel, 1997, 19(7): 721–732
Liu C H, Bhuiyan A -A, Ward J. Transfer between pose and illumination training in face recognition. Percept, 2007, 36(Suppl.): 148
Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process, 2004, 13(4): 600–612
Yin L, Wei X, Sun Y, et al. A 3D facial expression database for facial behavior research. In: IEEE 7th International Conference on Automatic Face and Gesture Recognition, Southampton, UK, April 2006. IEEE Computer Society TC PAMI, 2006. 211–216
Zhu J, Vai M I, Mak P U. A new enhanced nearest feature space (ENFS) classifier for Gabor wavelets features-based face recognition. ICBA 2004. Lect Notes Comput Sci, 2004, 3072:124–131
Farell B. “Same”-“different” judgments: A review of current controversies in perceptual comparisons. Psychol Bull, 1985, 98(3): 419–456
Bamber D. Reaction times and error rates for “same”- “different” judgments of multi-dimension stimuli. Percept Psychophys, 1969, 6: 169–174
Stewart N, Brown G D A. Similarity and dissimilarity as evidence in perceptual categorization. J Math Psychol, 2005, 49(5): 403–409
Tversky A. Features of similarity. Psychol Rev, 1977, 84: 327–352
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the National Basic Research Program of China (Grant No. 2006CB303101), the National Natural Science Foundation of China (Grant Nos. 60433030, 30600182 and 30500157), and the Royal Society
Rights and permissions
About this article
Cite this article
Chen, W., Liu, C., Lander, K. et al. Comparison of human face matching behavior and computational image similarity measure. Sci. China Ser. F-Inf. Sci. 52, 316–321 (2009). https://doi.org/10.1007/s11432-009-0044-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11432-009-0044-6