Nelson, R. C. and Selinger, A. (1998). Large-scale tests of a keyed, appearance-based 3-D object recognition system. Vision Research, 38:2469--2488.  Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
(Coarse Coding of Shape Fragments) + (Retinotopy) =.. - Edelman (1999) (Correct)
....as the predominant and the most successful algorithmic approach to recognition in computer vision. The idea behind CoF representing an object by a collection of fragments that are data driven, not generic, and are positioned roughly, not precisely recurs in several such methods. ffl (Nelson and Selinger, 1998) start by detecting contour segments, then determine whether their relative arrangement approximates that of a model object. Because none of the individual segment shapes or locations are critical to the successful description of the entire shape, this method does not suffer from the brittleness ....
....of the entire shape, this method does not suffer from the brittleness associated with the symbolic structural models of recognition. Moreover, the tolerance to moderate variation in the segment shape and location data allows this method to categorize novel members of familiar object classes (Nelson and Selinger, 1998). the holistic Chorus of Prototypes and the standard structuralist schemes. ffl (Burl et al. 1998) combine local photometry (shape primitives that are basically templates for small snippets of images) with global geometry (the probabilistic quantification of spatial relations between pairs ....
Nelson, R. C. and Selinger, A. (1998). Large-scale tests of a keyed, appearance-based 3-D object recognition system. Vision Research, 38:2469--2488.
On the Representation of Object Structure in Human Vision.. - Edelman, Newell (1998) (Correct)
.... is iteratively refined by considering mutual constraints based on relative locations of simple template like features in an image (Amit and Geman, 1997) Likewise, encoding the rough structure of objects in image coordinates can support object recognition in the presence of occlusion and clutter (Nelson and Selinger, 1998). The latter system can also perform categorization of novel instances of familiar classes. Importantly, it represents object structure explicitly, making it, in principle, capable of reasoning about object parts a serious challenge for holistic methods such as Chorus, but not, we believe, for ....
Nelson, R. C. and Selinger, A. (1998). Large-scale tests of a keyed, appearance-based 3-D object recognition system. Vision Research, 38:2469--2488.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC