We discuss a variety of object recognition experiments in which human subjects were presented with realistically rendered images of computer-generated three-dimensional objects, with tight control over stimulus shape, surface properties, illumination, and viewpoint, as well as subjects' prior exposure to the stimulus objects. In all experiments recognition performance was: (1) consistently viewpoint dependent; (2) only partially aided by binocular stereo and other depth information, (3) specific to viewpoints that were familiar; (4) systematically disrupted by rotation in depth more than by deforming the two-dimensional images of the stimuli. These results are consistent with recently advanced computational theories of recognition based on view interpolation.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7204 |
| Date | 01 April 1994 |
| Creators | Buelthoff, Heinrich H., Edelman, Shimon Y., Tarr, Michael J. |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 19 p., 509767 bytes, 1124249 bytes, application/octet-stream, application/pdf |
| Relation | AIM-1479, CBCL-096 |
Page generated in 0.002 seconds