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

Nathan Intrator, Shimon Edelman, Heinrich H. Bulthoff

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish
Pages (from-to)603-618
Number of pages16
JournalNetwork: Computation in Neural Systems
Volume6
Issue number4
DOIs
Publication statusPublished - 1995

Bibliographical note

Funding Information:
We thank Erik Sklar and Josh Gold for assistance in running the some of the experiments, and the simulation study. This work was supported in part by the National Science Foundation, the Office of Naval Research, and the Army Research Office.

ASJC Scopus subject areas

  • Neuroscience (miscellaneous)

Fingerprint

Dive into the research topics of 'An integrated approach to the study of object features in visual recognition'. Together they form a unique fingerprint.

Cite this