Distributed associated memories and data fusion

H. Wechsler; George L Zimmerman

doi:10.1016/0893-6080(88)90101-3

Distributed associated memories and data fusion

H. Wechsler, George L Zimmerman

Electrical Engineering

Research output: Contribution to journal › Conference article › peer-review

Abstract

We suggest using distributed associative memory (DAM) to integrate visual information from multiple cues or sources for performing invariant object recognition. We assume that the output of the sources vary consistently for a given input. We perform a series of experiments whose goal is to assess our approach to the data fusion problem. The database is made up of 15 classes of colored polyhedral objects. Each object in the database underwent a specific linear transformation and was correctly identified. The same applies to occlusion and noise. Our results show that for points close to the central locations of the objects being viewed the response is correct.

Original language	English (US)
Pages (from-to)	59
Number of pages	1
Journal	Neural Networks
Volume	1
Issue number	1 SUPPL
DOIs	https://doi.org/10.1016/0893-6080(88)90101-3
State	Published - 1988
Event	International Neural Network Society 1988 First Annual Meeting - Boston, MA, USA Duration: Sep 6 1988 → Sep 10 1988

Access

10.1016/0893-6080(88)90101-3

OpenUrl availability

Full text

Cite this

@article{337af024a1f34af3b00781b377a84160,

title = "Distributed associated memories and data fusion",

abstract = "We suggest using distributed associative memory (DAM) to integrate visual information from multiple cues or sources for performing invariant object recognition. We assume that the output of the sources vary consistently for a given input. We perform a series of experiments whose goal is to assess our approach to the data fusion problem. The database is made up of 15 classes of colored polyhedral objects. Each object in the database underwent a specific linear transformation and was correctly identified. The same applies to occlusion and noise. Our results show that for points close to the central locations of the objects being viewed the response is correct.",

author = "H. Wechsler and Zimmerman, {George L}",

year = "1988",

doi = "10.1016/0893-6080(88)90101-3",

language = "English (US)",

volume = "1",

pages = "59",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Limited",

number = "1 SUPPL",

note = "International Neural Network Society 1988 First Annual Meeting ; Conference date: 06-09-1988 Through 10-09-1988",

}

TY - JOUR

T1 - Distributed associated memories and data fusion

AU - Wechsler, H.

AU - Zimmerman, George L

PY - 1988

Y1 - 1988

N2 - We suggest using distributed associative memory (DAM) to integrate visual information from multiple cues or sources for performing invariant object recognition. We assume that the output of the sources vary consistently for a given input. We perform a series of experiments whose goal is to assess our approach to the data fusion problem. The database is made up of 15 classes of colored polyhedral objects. Each object in the database underwent a specific linear transformation and was correctly identified. The same applies to occlusion and noise. Our results show that for points close to the central locations of the objects being viewed the response is correct.

AB - We suggest using distributed associative memory (DAM) to integrate visual information from multiple cues or sources for performing invariant object recognition. We assume that the output of the sources vary consistently for a given input. We perform a series of experiments whose goal is to assess our approach to the data fusion problem. The database is made up of 15 classes of colored polyhedral objects. Each object in the database underwent a specific linear transformation and was correctly identified. The same applies to occlusion and noise. Our results show that for points close to the central locations of the objects being viewed the response is correct.

UR - http://www.scopus.com/inward/record.url?scp=0024178606&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024178606&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(88)90101-3

DO - 10.1016/0893-6080(88)90101-3

M3 - Conference article

AN - SCOPUS:0024178606

SN - 0893-6080

VL - 1

SP - 59

JO - Neural Networks

JF - Neural Networks

IS - 1 SUPPL

T2 - International Neural Network Society 1988 First Annual Meeting

Y2 - 6 September 1988 through 10 September 1988

ER -

Distributed associated memories and data fusion

Abstract

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this