What Do Features Tell about Images?
According to the Marr paradigm , visual processing is performed by low-level feature detection followed by higher level task dependent processing. In this case, any two images exhibiting identical features will yield the same result of the visual processing. The set of images exhibiting identical features form an equivalence class: a metameric class . We choose from this class the (in some precise sense) simplest image as a representative. The complexity of this simplest image may in turn be used for analyzing the information content of features. We show examples of images reconstructed from various scale-space features, and show that a low number of simple differential features carries sufficient information for reconstructing images close to identical to the human observer. The paper presents direct methods for reconstruction of minimal variance representatives, and variational methods for computation of maximum entropy and maximum a posteriori representatives based on priors for natural images. Finally, conclusions on the information content in blobs and edges are indicated.
KeywordsFeature Strength Natural Image Edge Point Image Code Simple Image
Unable to display preview. Download preview PDF.
- 1.J.H. Elder and S.W. Zucker. Scale space localization, blur, and contour-based image coding. In CVPR96, pages 27–34, 1996.Google Scholar
- 3.J. Huang, A.B. Lee, and D. Mumford. Statistics of range images. In CVPR00, pages I:324–331, 2000.Google Scholar
- 5.Peter Johansen, Mads Nielsen, and Ole F Olsen. Branch points in one-dimensional gaussian scale-space. JMIV, 2000. To appear.Google Scholar
- 7.J.J. Koenderink and A.J. van Doorn. Metamerism in complete sets of image operators. In AIU96, pages 113–129, 1996.Google Scholar
- 8.T. Lindeberg. On scale selection for differential operators. In ISRN KTH, 1993.Google Scholar
- 10.D. Marr. Vision: A computational investigation into the human representation and processing of visual information. In W.H. Freeman, 1982.Google Scholar
- 11.K.S. Pedersen and M. Nielsen. The hausdorff dimension and scale-space normalization of natural images. JVCIR, 11(2):266–277, June 2000.Google Scholar
- 14.A.P. Witkin. Scale space filtering: A new approach to multi-scale descriptions. In IU84, pages 79–95, 1984.Google Scholar
- 15.Y.N. Wu, S.C. Zhu, and X.W. Liu. Equivalence of julesz and gibbs texture ensembles. In ICCV99, pages 1025–1032, 2000.Google Scholar
- 16.S.C. Zhu, Y. Wu, and D. Mumford. Minimax entorpy principles and its application to texture modeling. NeurComp, 9(8):1627–1660, 1997.Google Scholar