Abstract
Extracting features from an image is the first step in many computer vision applications. Traditionally, features represent physical or visual primitives such as edges and corners. In this paper, we augment the definition to include any attributes that conveniently describe the correlation and contextual relation between the primitive and its neighbors. The augmentation allows us to design a more detailed probability distribution model. If the distribution model is differentiable with respect to each attribute of a feature, a simple local search will find a feature set that is a local maximum in the joint probability distribution. Therefore, the final representation is free from noise and aliasing that perturbs the representation away from the local maximum. We can apply the approach to many low level vision tasks. In this paper, we demonstrate our approach with sub-pixel contour representation and surface reconstruction problems.
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
Aramini, M.: Efficient image magnification by bicubic spline interpolation, http://members.bellatlantic.net/vze2vrva/design.html
Baker, S., Kanade, T.: Limits on super-resolution and how to break them. PAMI 24(9), 1167–1183 (2002)
Ballard, D.H.: Generalizing the hough transform to detect arbitrary shapes. PR 13(2), 111–122 (1981)
Besag, J.: On the statistical analysis of dirty pictures. J. Royal Statistical Soc., Ser. B 48, 259–302 (1986)
Bishop, C., Blake, A., Marthi, B.: Super-resolution enhancement of video. In: Proc. Artificial Intelligence and Statistics, Key West, Florida (2003) (to appear)
Black, M.J., Sapiro, G., Marimont, D., Heeger, D.: Robust anisotropic diffusion. IP 7(3), 421–432 (1998)
Blake, A., Zisserman, A.: Visual Reconstruction. MIT Press, Cambridge (1987)
Canny, J.F.: A computational approach to edge-detection. PAMI 8, 679–700 (1986)
Davies, R.H., Twining, C.J., Cootes, T.F., Waterton, J.C., Taylor, C.J.: A minimum description length approach to statistical shape modeling. MedImg 21(5), 525–537 (2002)
Elad, M., Feuer, A.: Super-resolution reconstruction of image sequences. PAMIÂ 21(9), 817 (1999)
Faugeras, O.D., Keriven, R.: Variational-principles, surface evolution, pdes, level set methods, and the stereo problem. IP 7(3), 336–344 (1998)
Geiger, D., Girosi, F.: Parallel and deterministic algorithms from MRF’s: Surface reconstruction. PAMI 13(5), 401–412 (1991)
Geman, S., Geman, D.: Stochastic relaxation, Gibbs distribution, and the Bayesian restoration of images. PAMI 6(6), 721–741 (1984)
Hansen, M.W., Higgins, W.E.: Relaxation methods for supervised image segmentation. PAMI 19(9), 949–962 (1997)
Hueckel, M.: A local visual operator which recognizes edges and lines. JACM 20(4), 634–647 (1973)
Hummel, R.A., Zucker, S.W.: On the foundations of relaxation labeling processes. PAMI 5(3), 267–287 (1983)
Jain, A.K., Farrokhnia, F.: Unsupervised texture segmentation using Gabor filters. PR 24(12), 1167–1186 (1991)
Kass, M., Witkin, A.P., Terzopoulos, D.: Snakes: Active contour models. IJCV 1(4), 321–331 (1988)
Kimia, B.B., Tannenbaum, A.R., Zucker, S.W.: Shapes, shocks, and deformations i: The components of 2-dimensional shape and the reaction-diffusion space. IJCV 15(3), 189–224 (1995)
Kittler, J.V., Illingworth, J.: Relaxation labelling algorithms – a review. IVC 3, 206–216 (1985)
Kubota, T.: Robust feature extraction: A new framework for visual information processing. Technical Report CSCE TR-2002-015, Department of Computer Science and Engineering, University of South Carolina (2002)
Lowe, D.G.: Perceptual organization and visual recognition. Kluwer Academic Publisher, Hingham (1985); 02043
Mumford, D., Shah, J.: Boundary detection by minimizing functionals. In: CVPR 1985, San Francisco, CA, pp. 22–26 (1985)
Nguyen, N., Milanfar, P., Golub, G.: A computationally efficient superresolution image reconstruction algorithm. IP 10(4), 573–583 (2001)
Papachristou, P., Petrou, M., Kittler, J.V.: Edge postprocessing using probabilistic relaxation. SMC-B 30(3), 383–402 (2000)
Freeman, W.T., Haddon, J.A., Pasztor, E.C.: Example-based super-resolution. IEEE Computer Graphics and Applications 22(2), 56–65 (2002)
Rosenfeld, A., Hummel, R.A., Zucker, S.W.: Scene labeling by relaxation operations. SMC 6(6), 420–433 (1976)
Sarkar, S., Boyer, K.L.: Perceptual organization in computer vision: A review and a proposal for a classificatory structure. SMC 23(2), 382–399 (1993)
Schultz, R.R., Stevenson, R.L.: A bayesian approach to image expansion for improved definition. IP 3(3), 233–242 (1994)
Sethian, J.A.: Level Set Methods: evolving interfaces in geometry, fluid dynamics, computer vision, and material science. Cambridge University Press, New York (1996)
Shan, Y., Boon, G.W.: Sub-pixel location of edges with non-uniform blurring: a finite closed-form approach. IVC 18(13), 1015–1023 (2000)
Smith, S.M., Brady, J.M.: Susan: A new approach to low-level image processing. IJCV 23(1), 45–78 (1997)
Wilson, R.C., Hancock, E.R.: Structural matching by discrete relaxation. PAMI 19(6), 634–648 (1997)
Worthington, P.L., Hancock, E.R.: Needle map recovery using robust regularizers. IVC 17(8), 545–557 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kubota, T. (2003). Contextual and Non-combinatorial Approach to Feature Extraction. In: Rangarajan, A., Figueiredo, M., Zerubia, J. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2003. Lecture Notes in Computer Science, vol 2683. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45063-4_30
Download citation
DOI: https://doi.org/10.1007/978-3-540-45063-4_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40498-9
Online ISBN: 978-3-540-45063-4
eBook Packages: Springer Book Archive