ausblenden:
Schlagwörter:
-
Zusammenfassung:
The role of bilateral symmetry in face recognition is investigated in two psychophysics experiments using a same/different paradigm. The results of Experiment 1 confirm the hypothesis that the ability to identify mirror symmetric patterns is used for viewpoint generalization by approximating the view symmetric to the learned view
by its mirror reversed image. The results of Experiment 2 show that the match between this virtual view and the test image is performed directly between the images. Performance drops dramatically if the symmetry between the intensity patterns of the learning and the test view is disturbed by an asymmetric illumination, although the symmetry
between the spatial arrangement of high-level features is retained. A simple image based model can explain important aspects of the data and we show how this model can be extended towards a general algorithm for image comparison. Experimental results and the model are discussed in terms of their relation to existing approaches to object recognition.