Abstract
In this paper, we propose a new general framework to obtain more distinctive local invariant features by projecting the original feature descriptors into low-dimensional feature space, while simultaneously incorporating also class information. In the resulting feature space, the features from different objects project to separate areas, while locally the metric relations between features corresponding to the same object are preserved. The low-dimensional feature embedding is obtained by a modified version of classical Multidimensional Scaling, which we call supervised Multidimensional Scaling (sMDS). Experimental results on a database containing images of several different objects with large variation in scale, viewpoint, illumination conditions and background clutter support the view that embedding class information into the feature representation is beneficial and results in more accurate object recognition.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Lowe D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 12(60), 91–110 (2004)
Bay H., Ess A., Tuytelaars T., Van Gool L.: SURF: speeded up robust features. Comput. Vis. Image Underst. (CVIU) 110(3), 346–359 (2008)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 20–25 (2005)
Tuytelaars T., Mikolajczyk K.: Local invariant feature detectors: a survey. Found. Trends Comput. Graph. Vis. 3(3), 177–280 (2007)
Murase H., Nayar S.: Visual learning and recognition of 3-D objects from appearance. Int. J. Comput. Vis. 14(1), 5–24 (1995)
Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: Proceedings of ECCV Workshop on Statistical Learning in Computer Vision, pp. 1–22 (2004)
Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in videos. In: Proceedings of the International Conference on Computer Vision, pp. 1470–1477 (2003)
Cox T., Cox M.: Multidimensional Scaling, 2nd edn. Chapman and Hall/CRC, Boca Raton (2000)
Jolliffe I.: Principal Component Analysis. Springer, Berlin (1986)
Ke Y., Sukthankar R.: PCA-SIFT: a more distinctive representation for local image descriptors. Proc. IEEE Confer. Comput. Vis. Pattern Recogn. 2, 506–513 (2004)
Grauman K., Darrell T.: The pyramid match kernel: discriminative classification with sets of image features. Proc. IEEE Int. Confer. Comput. Vis. 2, 1458–1465 (2005)
van Gemert, J.C., Geusebroek, J.M., Veenman, C.J., Smeulders, A.W.M.: Kernel codebooks for scene categorization. In: Proceedings of European Conference Computer Vision (2008)
Hua, G., Brown, M., Winder, S.: Discriminant embedding for local image descriptors. In: Proceedings of IEEE International Conference on Computer Vision, pp. 1–8 (2007)
Belhumeur P.N., Hespanha J.P., Kriegman D.J.: Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Trans. PAMI 19(7), 711–720 (1997)
Torgeson W.: Multidimensional scaling: I. Theory Method. Psychometrika 17, 401–419 (1952)
Mardia K., Kent J., Bibby J.: Multivariate Analysis. Academic Press, New York (1979)
Wandell B., Brewer A.A., Dougherty R.F.: Visual field map clusters in human cortex. Phil. Trans. R. Soc. Lond. 360, 693–707 (2005)
Gower J.: Adding a point to vector diagrams in multivariate analysis. Biometrica 55, 582–585 (1968)
Sammon J.W. Jr: A nonlinear mapping for data structure analysis. IEEE Trans. Comput. C-18(5), 401–409 (1969)
Tipping, M.E.: Topographic Mapping and Feed-Forward Neural Networks. Ph.D. thesis, Aston University, Birmingham, UK (1996)
Tipping M.E., Lowe D.: Shadow targets: a novel algorithm for topographic projection by radial basis function network. Proc. Int. Conf. Artif. Neural Netw. 440, 7–12 (1997)
Hartman E.J., Keeler J.D., Kowalski J.W.: Layered neural networks with Gaussian hidden units as universal approximations. Neural Comput. 2(2), 210–215 (1990)
Park J., Sandberg I.W.: Approximation and radial basis function networks. Neural Comput. 5(2), 305–316 (1993)
Nabney I.T.: Netlab—Algorithms for Pattern Recognition. Springer, Berlin (2003)
Pinz A.: Object categorization. Found. Trends Comput. Graph. Vis. 1(4), 255–353 (2005)
Yan S., Xu D., Zhang B., Zhang H., Yang Q.: Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans. PAMI 29(1), 40–51 (2007)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Raytchev, B., Kikutsugi, Y., Tamaki, T. et al. Embedding class information into local invariant features by low-dimensional retinotopic mapping. Machine Vision and Applications 24, 407–418 (2013). https://doi.org/10.1007/s00138-012-0415-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-012-0415-7