An integrated approach to the study of object features in visual recognition

Author: Intrator Nathan   Edelman Shimon   Bulthoff Heinrich  

Publisher: Informa Healthcare

ISSN: 0954-898X

Source: Network: Computation in Neural Systems, Vol.6, Iss.4, 1995-11, pp. : 603-618

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

We propose to assess the relevance of theories of synaptic modification as models of feature extraction in human vision, by using masks derived from synaptic weight patterns to occlude parts of the stimulus images in psychophysical experiments. In the experiment, we found that a mask derived from principal component analysis of object images was more effective in reducing the generalization performance of human subjects than a mask derived from another method of feature extraction (BCM), based on higher-order statistics of the images.