2D Observers in 3D Object Recognition

Converging evidence has shown that human object recognition de-pends on the observers ' familiarity with objects ' appearance. The more similar the objects are, the stronger this dependence is, and the more important two-dimensional (2D) image information is to discriminate these objects from one another. The degree to which 3D structural information is used, however, still remains an area of strong debate. Previously, we showed that all models that allow rotations in the image plane of independent 2D templates could not account for human performance in discriminating novel object views as a result of 3D rotations. We now present results from models of generalized radial basis functions (GRBF), 2D closest template matching that allows 2D ane transformations of in-dependent 2D templates, and Bayesian statistical estimator that integrates over all possible 2D ane transformations. The per-formance of the human observers relative to each of the models is better for the novel views than for the learned template views, a result unpredicted if the human observers employed up to 2D ane transformations to independent 2D templates. The Bayesian estimator yields provably the optimal performance among all mod-els of 2D ane transformations with independent 2D templates. Therefore, no models of 2D ane operations with independent 2D templates account for the human observers ' performance. We sug-gest that the human observers used 3D structural information of the objects, which is also supported by the improved performance as the objects ' 3D structural regularity increased.