2D Observers for Human 3D Object Recognition?

Part of Advances in Neural Information Processing Systems 10 (NIPS 1997)

Bibtex Metadata Paper


Zili Liu, Daniel Kersten


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(cid:173) dimensional (2D) image information becomes. These findings, how(cid:173) ever, do not rule out the use of 3D structural information in recog(cid:173) nition, 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 perfor(cid:173) mance in discriminating novel object views. We now present results from models of generalized radial basis functions (GRBF), 2D near(cid:173) est 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 estima(cid:173) tor 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.