2-D Invariant Object Recognition Using Distributed Associative Memory

Harry Wechsler; George Lee Zimmerman

doi:10.1109/34.9104

2-D Invariant Object Recognition Using Distributed Associative Memory

Harry Wechsler, George Lee Zimmerman

Research output: Contribution to journal › Article › peer-review

66 Scopus citations

Abstract

This paper describes an approach to two-dimensional object recognition. Complex-log conformai mapping is combined with a distributed associative memory to create a system which recognizes objects regardless of changes in rotation or scale. Recalled information from the memorized database is used to classify an object, reconstruct the memorized version of the object, and estimate the magnitude of changes in scale or rotation. The system response is resistant to moderate amounts of noise and occlusion. Several experiments, using real, gray scale images, are presented to show the feasibility of our approach.

Original language	English (US)
Pages (from-to)	811-821
Number of pages	11
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	10
Issue number	6
DOIs	https://doi.org/10.1109/34.9104
State	Published - Nov 1988
Externally published	Yes

Bibliographical note

Funding Information:
Manuscript received November 5, 1986; revised October 27, 1987. Recommended for acceptance by C. Brown. This work was supported in part by the National Science Foundation under Grant ECS-83 10057 and by a grant from the Microelectronics and Information Science (MEIS) Center of the University of Minnesota.

Keywords

Complex-log mapping
distributed associative memory
invariance
pattern recognition
space variant filtering

Publisher link

10.1109/34.9104

Find It

Find It at U of M Libraries

Cite this

@article{9d2e492b44f84898849e65c8a7198d80,

title = "2-D Invariant Object Recognition Using Distributed Associative Memory",

abstract = "This paper describes an approach to two-dimensional object recognition. Complex-log conformai mapping is combined with a distributed associative memory to create a system which recognizes objects regardless of changes in rotation or scale. Recalled information from the memorized database is used to classify an object, reconstruct the memorized version of the object, and estimate the magnitude of changes in scale or rotation. The system response is resistant to moderate amounts of noise and occlusion. Several experiments, using real, gray scale images, are presented to show the feasibility of our approach.",

keywords = "Complex-log mapping, distributed associative memory, invariance, pattern recognition, space variant filtering",

author = "Harry Wechsler and Zimmerman, {George Lee}",

note = "Funding Information: Manuscript received November 5, 1986; revised October 27, 1987. Recommended for acceptance by C. Brown. This work was supported in part by the National Science Foundation under Grant ECS-83 10057 and by a grant from the Microelectronics and Information Science (MEIS) Center of the University of Minnesota.",

year = "1988",

month = nov,

doi = "10.1109/34.9104",

language = "English (US)",

volume = "10",

pages = "811--821",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "6",

}

TY - JOUR

T1 - 2-D Invariant Object Recognition Using Distributed Associative Memory

AU - Wechsler, Harry

AU - Zimmerman, George Lee

N1 - Funding Information: Manuscript received November 5, 1986; revised October 27, 1987. Recommended for acceptance by C. Brown. This work was supported in part by the National Science Foundation under Grant ECS-83 10057 and by a grant from the Microelectronics and Information Science (MEIS) Center of the University of Minnesota.

PY - 1988/11

Y1 - 1988/11

N2 - This paper describes an approach to two-dimensional object recognition. Complex-log conformai mapping is combined with a distributed associative memory to create a system which recognizes objects regardless of changes in rotation or scale. Recalled information from the memorized database is used to classify an object, reconstruct the memorized version of the object, and estimate the magnitude of changes in scale or rotation. The system response is resistant to moderate amounts of noise and occlusion. Several experiments, using real, gray scale images, are presented to show the feasibility of our approach.

AB - This paper describes an approach to two-dimensional object recognition. Complex-log conformai mapping is combined with a distributed associative memory to create a system which recognizes objects regardless of changes in rotation or scale. Recalled information from the memorized database is used to classify an object, reconstruct the memorized version of the object, and estimate the magnitude of changes in scale or rotation. The system response is resistant to moderate amounts of noise and occlusion. Several experiments, using real, gray scale images, are presented to show the feasibility of our approach.

KW - Complex-log mapping

KW - distributed associative memory

KW - invariance

KW - pattern recognition

KW - space variant filtering

UR - http://www.scopus.com/inward/record.url?scp=0024104192&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024104192&partnerID=8YFLogxK

U2 - 10.1109/34.9104

DO - 10.1109/34.9104

M3 - Article

AN - SCOPUS:0024104192

SN - 0162-8828

VL - 10

SP - 811

EP - 821

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 6

ER -

2-D Invariant Object Recognition Using Distributed Associative Memory

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this