Towards a generalized primal sketch
Seeing is probably the leading goal of Computer Vision. Yet, what to see may be more difficult to analyze as it is mainly application-dependent. Hence, if we commonly accept to represent a scene by means of a set of pixels (picture elements), independently of the acquisition process, or the pixels topology, treatments applied on such elements differ greatly according to the approaches. Similarly, biological vision is in agreement with the “sampling” principle of the scene; yet, subsequent treatments are not clearly defined but “global” functions leading to cortical specializations.
KeywordsImpulse Noise Central Pixel Visual Data Binary Mask Kernel Blur
Unable to display preview. Download preview PDF.
- Jolion, J.-M.: Multi-resolution analysis of contrast in digital images (in french). Traitement du Signal 11, 245–255 (1994).Google Scholar
- Canning, J., Kim, J.J., Rosenfeld, A.: Symbolic pixel labeling for curvilinear feature detection. DARPA Image Understanding Workshop, Los Angeles, 242–256 (1987).Google Scholar
- Duperthuy, C.: A directional approach to 3 x 3 binary masks for texture discrimination (in french). Research Report RR-9601, Laboratoire Reconnaissance de Formes et Vision (1996).Google Scholar
- Bergen, J.R., Landy, M.S.: Computational Modeling of Visual Texture Segregation. In: Landy M.S., Movshon J.A. (eds.): Computational Models of Visual Processing. Bradford Book, MIT Press, 1991 (pp. 253–271 ).Google Scholar