Abstract
In this expository article, we justify the use of sparse local descriptors for correspondence, and illustrate a systematic method for their design. Correspondence is the process that allows using image data to infer properties of the “scene,” where the scene can refer to a specific object or landscape, or can be abstracted into a category label to take into account intra-class variability. As the generality increases, the complexity of nuisance factors does too, so global pixel-level correspondence is not viable, and one has to settle instead for sparse descriptors. These should be co-designed with the classifier, and for a given classifier family, one can design the descriptors to be invariant to uninformative nuisances that are explicitly modeled, insensitive to other nuisances that are not explicitly modeled, and maximally discriminative, relative to the chosen family of classifiers. Existing descriptors are interpreted in this framework, where their limitations are illustrated, together with pointers on how to improve them.
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
Alvarez, L., Guichard, F., Lions, P.L., Morel, J.M.: Axioms and fundamental equations of image processing. Arch. Rational Mechanics 123 (1993)
Ayvaci, A., Raptis, M., Soatto, S.: Sparse occlusion detection with optical flow. Intl. J. of Comp. Vision (2012)
Ayvaci, A., Soatto, S.: Detachable object detection. IEEE Trans. on Patt. Anal. and Mach. Intell. (2011)
Berg, A., Malik, J.: Geometric blur for template matching. In: Proc. CVPR (2001)
Bruna, J., Mallat, S.: Classification with scattering operators. In: Proc. IEEE Conf. on Comp. Vision and Pattern Recogn. (2011)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley (1991)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. IEEE Conf. on Comp. Vision and Pattern Recogn. (2005)
Guillemin, V., Pollack, A.: Differential Topology. Prentice-Hall (1974)
Huang, J., Mumford, D.: Statistics of natural images and models. In: Proc. CVPR, pp. 541–547 (1999)
Jin, H., Favaro, P., Soatto, S.: Real-time feature tracking and outlier rejection with changes in illumination. In: Proc. of the Intl. Conf. on Computer Vision, pp. 684–689 (2001)
Kendall, D.G.: Shape manifolds, procrustean metrics and complex projective spaces. Bull. London Math. Soc. 16 (1984)
Keogh, E.J., Pazzani, M.J.: Dynamic time warping with higher order features. In: Proceedings of the 2001 SIAM Intl. Conf. on Data Mining (2001)
Lee, T., Soatto, S.: Video-based descriptors for object recognition. Image and Vision Computing (2011)
Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV (1999)
Ma, Y., Soatto, S., Kosecka, J., Sastry, S.: An invitation to 3D vision, from images to geometric models. Springer (2003)
Meltzer, J., Yang, M.-H., Gupta, R., Soatto, S.: Multiple view feature descriptors from image sequences via kernel principal component analysis. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 215–227. Springer, Heidelberg (2004)
Milnor, J.: Morse Theory. Annals of Mathematics Studies no. 51. Princeton University Press (1969)
Poggio, T.: How the ventral stream should work. Technical report, Nature Precedings (2011)
Soatto, S.: On the distance between non-stationary time series. In: Chiuso, A., Ferrante, A., Pinzoni, S. (eds.) Modeling, Estimation and Control. LNCIS, vol. 364, pp. 285–299. Springer, Heidelberg (2007)
Soatto, S.: Actionable information in vision. In: Proc. of the Intl. Conf. on Comp. Vision (October 2009)
Soatto, S.: Steps Toward a Theory of Visual Information. Technical Report UCLA-CSD100028 (September 13, 2010), http://arxiv.org/abs/1110.2053
Soatto, S., Yezzi, A.J., Jin, H.: Tales of shape and radiance in multiview stereo. In: Intl. Conf. on Comp. Vision, pp. 974–981 (October 2003)
Sundaramoorthi, G., Petersen, P., Varadarajan, V.S., Soatto, S.: On the set of images modulo viewpoint and contrast changes. In: Proc. IEEE Conf. on Comp. Vision and Pattern Recogn. (June 2009)
Tola, E., Lepetit, V., Fua, P.: A fast local descriptor for dense matching. In: Proc. CVPR. Citeseer (2008)
Tomasi, C., Shi, J.: Good features to track. In: IEEE Computer Vision and Pattern Recognition (1994)
Valente, L., Tsai, R., Soatto, S.: Information gathering control via exploratory path panning. In: Proc. of the Conf. on Information Sciences and Systems (CISS) (March 2012)
Vedaldi, A., Soatto, S.: Features for recognition: viewpoint invariance for non-planar scenes. In: Proc. of the Intl. Conf. of Comp. Vision, pp. 1474–1481 (October 2005)
Wnuk, K., Soatto, S.: Multiple instance filtering. In: Proc. of NIPS (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Soatto, S., Dong, J. (2014). Visual Correspondence, the Lambert-Ambient Shape Space and the Systematic Design of Feature Descriptors. In: Cipolla, R., Battiato, S., Farinella, G. (eds) Registration and Recognition in Images and Videos. Studies in Computational Intelligence, vol 532. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-44907-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-44907-9_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-44906-2
Online ISBN: 978-3-642-44907-9
eBook Packages: EngineeringEngineering (R0)