Part-Based Strategies for Visual Categorisation and Object Recognition
Approaches to object recognition that rely on structural, or part-based, descriptions have a long-standing tradition in research on both computer and biological vision. Originally developed in the field of computer graphics, Binford (1971) was among the first to suggest that similar representations might be used by biological systems for object recognition. According to this author, such representations could be based on certain three-dimensional (3D) part primitives termed “generalized cones”.
KeywordsObject Recognition Category Learning Representational Format Binary Attribute General Recognition Theory
Unable to display preview. Download preview PDF.
- Ashby FG (1989) Stochastic general recognition theory. In: Vickers D, Smith PL (Eds) Human information processing: measures, mechanisms, and models. Elsevier, Amsterdam, pp 435–457Google Scholar
- Biederman I (1981) On the semantics of a glance at a scene. In: Kubovy M, Pomerantz RJ (Eds) Perceptual organization. Erlbaum, Hillsdale NJ, pp 213–253Google Scholar
- Binford T (1971) Visual perception by computer. Proceedings, IEEE conference on systems and control. Miami, FLGoogle Scholar
- Palmer SE (1975) The effects of contextual scenes on the identification of objects. Mem Cogn 3:519–526Google Scholar
- Rosch E (1978) Principles of categorization. In: Rosch E, Lloyd B (Eds) Cognition and categorization. Erlbaum, Hillsdale NJ, pp 27–48Google Scholar
- Ullman S, Sali E (2000) Object classification using a fragment-based representation. In: Lee SW, Bülthoff HH (Eds) Biologically motivated computer vision. Springer, Berlin Heidelberg New York, pp 73–87Google Scholar