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

Nathan Intrator; Shimon Edelman; Heinrich H. Bulthoff

doi:10.1088/0954-898X_6_4_005

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

Nathan Intrator, Shimon Edelman, Heinrich H. Bulthoff

Research output: Contribution to journal › Article › peer-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 language	English
Pages (from-to)	603-618
Number of pages	16
Journal	Network: Computation in Neural Systems
Volume	6
Issue number	4
DOIs	https://doi.org/10.1088/0954-898X_6_4_005
Publication status	Published - 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)

Access to Document

10.1088/0954-898X_6_4_005

Cite this

@article{29c471afa7d146b7bf2df008d655e2f6,

title = "An integrated approach to the study of object features in visual recognition",

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.",

author = "Nathan Intrator and Shimon Edelman and Bulthoff, {Heinrich H.}",

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.",

year = "1995",

doi = "10.1088/0954-898X_6_4_005",

language = "English",

volume = "6",

pages = "603--618",

journal = "Network: Computation in Neural Systems",

issn = "0954-898X",

publisher = "Informa Healthcare",

number = "4",

}

TY - JOUR

T1 - An integrated approach to the study of object features in visual recognition

AU - Intrator, Nathan

AU - Edelman, Shimon

AU - Bulthoff, Heinrich H.

N1 - 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.

PY - 1995

Y1 - 1995

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=36149037077&partnerID=8YFLogxK

U2 - 10.1088/0954-898X_6_4_005

DO - 10.1088/0954-898X_6_4_005

M3 - Article

AN - SCOPUS:36149037077

SN - 0954-898X

VL - 6

SP - 603

EP - 618

JO - Network: Computation in Neural Systems

JF - Network: Computation in Neural Systems

IS - 4

ER -

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

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this