Converging evidence has shown that human object recognition depends on familiarity with the images of an object. Further, the greater the similarity between objects, the stronger is the dependence on object appearance, and the more important two- dimensional (2D) image information becomes. These findings, however, do not rule out the use of 3D structural information in recognition, and the degree to which 3D information is used in visual memory is an important issue. Liu, Knill, & Kersten (1995) showed that any model that is restricted to rotations in the image plane of independent 2D templates could not account for human performance in discriminating novel object views. We now present results from models of generalized radial basis functions (GRBF), 2D nearest neighbor matching that allows 2D affine transformations, and a Bayesian statistical estimator that integrates over all possible 2D affine transformations. The performance of the human observers relative to each of the models is better for the novel views than for the familiar template views, suggesting that humans generalize better to novel views from template views. The Bayesian estimator yields the optimal performance with 2D affine transformations and independent 2D templates. Therefore, models of 2D affine matching operations with independent 2D templates are unlikely to account for human recognition performance.
|Original language||English (US)|
|Title of host publication||Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997|
|Publisher||Neural information processing systems foundation|
|Number of pages||7|
|ISBN (Print)||0262100762, 9780262100762|
|State||Published - 1998|
|Event||11th Annual Conference on Neural Information Processing Systems, NIPS 1997 - Denver, CO, United States|
Duration: Dec 1 1997 → Dec 6 1997
|Name||Advances in Neural Information Processing Systems|
|Other||11th Annual Conference on Neural Information Processing Systems, NIPS 1997|
|Period||12/1/97 → 12/6/97|
Bibliographical noteFunding Information:
DK was supported by a grant from the National Science Foundation, contract number SBR-9631682. We thank Ronen Basri, David Jacobs, David Knill, Michael Langer, Pascal Mamassian, Bosco Tjan, Daphna Weinshall, the anonymous reviewers and in particular, John Oliensis, for many helpful discussions. Weinshall pointed out to us the Werman–Weinshall theorem. Part of this work was presented at the Hong Kong International Workshop on ‘Theoretical Aspects of Neural Computation,’ Hong Kong University of Science and Technology, 1997; European Conference on Visual Perception (ECVP), Helsinki, Finland, 1997; ‘Neural Information Processing’ (NIPS), Denver, Colorado, 1997; and ‘International Conference on Computer Vision’ (ICCV), Mumbai, India, 1998.