Abstract
A key challenge in building face recognition systems — biologically-inspired or otherwise — is evaluating performance. While much of face recognition research has traditionally used posed photographs for evaluation, recent efforts have emerged to build more naturalistic, unconstrained test sets by collecting large numbers of face images from the internet (e.g. the “Labeled Faces in the Wild”(LFW) test set [1]). While such efforts represent a large step forward in the direction of realism, the nature of posed photographs from the internet arguably represents an incomplete sampling of the range of variation in view, lighting, etc. found in the real world. Here, we evaluate a family of large-scale biologically-inspired vision algorithms that has previously proven to perform well on a variety of object and face recognition test sets [2], and show that members of this family perform at a level of performance that is comparable with current state-of-the-art approaches on the LFW challenge. As a counterpoint to internet-photo based approaches, we use synthetic (rendered) face images where the amount of view variation is controllable and known by design. We show that while there is gross agreement between the LFW benchmark and synthetic benchmarks, the synthetic benchmarks reveal a substantially greater degree of tolerance to view variation than is apparent from the LFW benchmark in models containing deeper hierarchies. Furthermore, such an approach yields important insights into which axes of variation are most challenging. These results suggest that parametric synthetic benchmarks can play an important role in guiding the progress of biologically-inspired vision systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled Faces in the Wild. TR UMass (2007)
Pinto, N., Doukhan, D., DiCarlo, J.J., Cox, D.D.: A high-throughput screening approach to discovering good forms of biologically inspired visual representation. PLoS Comput. Biol. (2009)
Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybernetics (1980)
Serre, T., Wolf, L., Bileschi, S., Riesenhuber, M., Poggio, T.: Robust object recognition with cortex-like mechanisms. In: PAMI (2007)
Mutch, J., Lowe, D.G.: Object class recognition and localization using sparse features with limited receptive fields. In: IJCV (2008)
Pinto, N., Cox, D.D., DiCarlo, J.J.: Why is Real-World Visual Object Recognition Hard. PLoS Comput. Biol. (2008)
Pinto, N., DiCarlo, J.J., Cox, D.D.: Establishing Good Benchmarks and Baselines for Face Recognition. In: ECCV (2008)
Jarrett, K., Kavukcuoglu, K., Ranzato, M., LeCun, Y.: What is the best multi-stage architecture for object recognition? In: ICCV (2009)
ORL Face Set (2010), http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html (accessed July 15, 2010)
Yale Face Set (2010), http://cvc.yale.edu (accessed July 15, 2010)
CVL Face Set (2010), http://www.lrv.fri.uni-lj.si/facedb.html (accessed July 15, 2010)
AR Face Set (2010), http://www2.ece.ohio-state.edu/~aleix/ardatabase.html (accessed July 15, 2010)
Phillips, P., Moon, H., Rizvi, S., Rauss, P.: The FERET evaluation methodology for face-recognition algorithms. In: PAMI (2000)
Gross, R., Matthews, I., Cohn, J., Kanade, T., Baker, S.: Multi-PIE. Image and Vision Computing (2009)
Pinto, N., DiCarlo, J.J., Cox, D.D.: How far can you get with a modern face recognition test set using only simple features? In: CVPR (2009)
Geisler, W.S., Albrecht, D.G.: Cortical neurons: isolation of contrast gain control. Vision Research (1992)
Rolls, E.T., Deco, G.: Computational neuroscience of vision. Oxford University Press (2002)
Taigman, Y., Wolf, L., Hassner, T., Tel-Aviv, I.: Multiple one-shots for utilizing class label information. In: BMVC (2009)
FaceGen (2010), singularinversions.com (accessed July 15, 2010)
POV-Ray Raytracer (2010), www.povray.org (accessed July 15, 2010)
Schölkopf, B., Smola, A.: Learning with kernels: Support vector machines, regularization, optimization, and beyond. The MIT Press (2002)
Rifkin, R., Klautau, A.: In defense of one-vs-all classification. In: JMLR (2004)
Kumar, N., Berg, A.C., Belhumeur, P.N., Nayar, S.K.: Attribute and Simile Classifiers for Face Verification. In: ICCV (2009)
Wolf, L., Hassner, T., Taigman, Y.: Similarity Scores Based on Background Samples. In: Zha, H., Taniguchi, R.-i., Maybank, S. (eds.) ACCV 2009. LNCS, vol. 5995, pp. 88–97. Springer, Heidelberg (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Pinto, N., Cox, D. (2012). An Evaluation of the Invariance Properties of a Biologically-Inspired System for Unconstrained Face Recognition. In: Suzuki, J., Nakano, T. (eds) Bio-Inspired Models of Network, Information, and Computing Systems. BIONETICS 2010. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 87. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32615-8_48
Download citation
DOI: https://doi.org/10.1007/978-3-642-32615-8_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32614-1
Online ISBN: 978-3-642-32615-8
eBook Packages: Computer ScienceComputer Science (R0)