Abstract
Neural networks in the visual system may be performing sparse coding of learnt local features that are qualitatively very similar to the receptive fields of simple cells in the primary visual cortex, V1. In conventional sparse coding, the data are described as a combination of elementary features involving both additive and subtractive components. However, the fact that features can ‘cancel each other out’ using subtraction is contrary to the intuitive notion of combining parts to form a whole. Thus, it has recently been argued forcefully for completely non-negative representations. This paper presents Non-Negative Sparse Coding (NNSC) applied to the learning of facial features for face recognition and a comparison is made with the other part-based techniques, Non-negative Matrix Factorization (NMF) and Local-Non-negative Matrix Factorization (LNMF). The NNSC approach has been tested on the Aleix–Robert (AR), the Face Recognition Technology (FERET), the Yale B, and the Cambridge ORL databases, respectively. In doing so, we have compared and evaluated the proposed NNSC face recognition technique under varying expressions, varying illumination, occlusion with sunglasses, occlusion with scarf, and varying pose. Tests were performed with different distance metrics such as the L 1-metric, L 2-metric, and Normalized Cross-Correlation (NCC). All these experiments involved a large range of basis dimensions. In general, NNSC was found to be the best approach of the three part-based methods, although it must be observed that the best distance measure was not consistent for the different experiments.
References
Hubel D.H., Wiesel T.N. (1968) Receptive fields and functional architecture of monkey striate cortex. J. Physiol. 195, 215–243
Olshausen A., Field D.J. (1996) Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381, 607–609
Bell A.J., Sejnowski T.J. (1997) The “Independent Components” of natural scenes are edge filters. Vis. Res. 37: 3327–3338
Lee D.D., Seung H.S. (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401,788–791
Hoyer, P.O.: Non-Negative Sparse Coding. In: Proceedings of IEEE Workshop on Neural Networks for Signal Processing, pp. 557–565 (2002)
Li S.Z., Hou X.W., Zhang H.J., Cheng Q.S. (2001) Learning spatially localized, parts-based representation. IEEE Comput. Vis. Pattern Recognit. 1, 207–212
Martinez A., Benavente R. The AR face database. Technical report 24, Computer Vision Center (CVC), Barcelona, Spain (1998)
Phillips P.J., Wechsler H., Huang J., Rauss P. (1998) The FERET database and evaluation procedure for face-recognition algorithms. Image Vis. Comput. 16, 295–306
Georghiades A.S., Belhumeur P.N., Kriegman D.J. (2001) From few to many: illumination cones models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intell. 23, 643–660
ORL Database of Faces. AT&T Laboratories, Cambridge, UK. Web address: http://www.orl.co.uk/facedatabase.html
Hoyer, P.O.: Probabilistic Models of Early Vision. Ph.D. Dissertation, Department of Computer Science, Helsinki University of Technology, Finland (2002)
Hafed Z.M., Levine M.D. (2001) Face recognition using the discrete cosine transform. Int. J. Comput. Vis. 43, 167–188
Gandhi M. Aging adult human faces. M. Eng. Thesis, Dept. Elect. Eng., McGill University, Montreal, Canada (2004)
Guillamet, D., Vitria, J.: Determining a Suitable Metric when using Non-Negative Matrix Factorization. In: Proceedings of the 16th International Conference Pattern Recognition, vol. 2, pp. 128–131 (2002)
Penev P.S., Atick J.J. (1996) Local feature analysis: a general statistical theory for object representation. Neural Syst. 7, 477–500
Moghaddam B., Pentland A.P. (1997) Probabilistic visual learning of object representation. IEEE Trans. Pattern Anal. Mach. Intell. 19, 696–710
Turk, M.A., Pentland, A.P.: Face Recognition using Eigenfaces. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 586–591 (1991)
Gross, R., Shi, J., Cohn, J.F.: Quo vadis Face Recognition?, Technical Report, Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA (2001)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Shastri, B.J., Levine, M.D. Face recognition using localized features based on non-negative sparse coding. Machine Vision and Applications 18, 107–122 (2007). https://doi.org/10.1007/s00138-006-0052-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-006-0052-0