Towards a Primal Sketch of Real World Scenes in Early Vision
The problem of symbolic representation of intensity variations in gray-value pictures of real scenes is studied. The goal is to relate the responses of a filter bank of different gradient filters to the structure of the picture which is determined by the physics of the image generation process. A simple criterion is proposed for the selection of a suitable center frequency of the involved band-pass filters. The gradient vectors of the image function give the direction of maximal intensity changes with high resolution (8 bit) which can be used for an invariant shape description by corner points of a contour. The picture is segmented by closed contour lines into regions which form a topographic representation in the picture domain.
Unable to display preview. Download preview PDF.
- 1.Marr, D.: Vision. W.H. Freeman and Comp., San Francisco, CA, 1982Google Scholar
- 2.Korn, A.: Combination of Different Spatial Frequency Filters for Modeling Edges and Surfaces in Gray-Value Pictures. Proc.2nd Int. Technical Symposium on Optical and Electro-Optical Applied Science and Engineering, Cannes, Dec. 2–6, 1985, SPIE, Vol. 595, 22–30Google Scholar
- 3.Nagel, H.-H.: Principles of (Low-Level) Computer Vision. In “Fundamentals in Computer Understanding: Speech, Vision, and Natural Language”, J.P. Haton (Ed.), Cambridge University Press, Cambridge/UK 113–139 (1987)Google Scholar
- 4.Canny, J.F.: Finding Edges and Lines in Images. Artif. Intell. Lab., Mass. Inst. Technol., Cambridge, MA, Tech. Rep. AI-TR-720, June 1983.Google Scholar
- 7.Campbell, F.W. and Robson, J.G.: Applications of Fourier analysis to the visibility of gratings, J. Physiol. (London) 197, 551–566 (1968)Google Scholar
- 8.Frisby, J. P., Seeing, Illusion, Brain and Mind. Oxford University Press, Oxford, 1979Google Scholar
- 9.Torre, v., and Poggio T.A., On Edge Detection. IEEE Trans. Pattern Analysis and Machine Intelligence PAMI-8 (1986) 147–163Google Scholar
- 10.Asada, H., and Brady, M.: The curvature primal sketch. IEEE Trans. Pattern Analysis and Machine Intelligence PAMI-8, 2–14 (1986)Google Scholar