Pattern Recognition by Using an Associative Memory

Sik-Sang Yau, C. C. Yang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

The purpose of this paper is to present a simple template-matching pattern recognition technique by using any general-purpose associative memory. The input patterns for recognition may have wide variations, provided that the distinct features of individual pattern classes can be extracted. Each pattern class is allowed to have deviations in size, style, orientation, etc. within certain limits. This pattern recognition technique is extremely efficient in handwritten character recognition, which is used for illustration in this paper. Because each input pattern is processed with all the pattern classes simultaneously, the speed of this pattern recognition technique is very high. It is found that most input patterns are recognized within first comparison process and no input patterns require more than two comparison processes for their recognition.

Original languageEnglish (US)
Pages (from-to)944-947
Number of pages4
JournalIEEE Transactions on Electronic Computers
VolumeEC-15
Issue number6
DOIs
StatePublished - 1966
Externally publishedYes

Fingerprint

Associative Memory
Pattern Recognition
Pattern recognition
Data storage equipment
Template matching
Character recognition
Template Matching
Character Recognition
Deviation
Distinct
Class

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Software
  • Theoretical Computer Science

Cite this

Pattern Recognition by Using an Associative Memory. / Yau, Sik-Sang; Yang, C. C.

In: IEEE Transactions on Electronic Computers, Vol. EC-15, No. 6, 1966, p. 944-947.

Research output: Contribution to journalArticle

@article{c4e1977a4e0d45f6a72db496fbbd0b7a,
title = "Pattern Recognition by Using an Associative Memory",
abstract = "The purpose of this paper is to present a simple template-matching pattern recognition technique by using any general-purpose associative memory. The input patterns for recognition may have wide variations, provided that the distinct features of individual pattern classes can be extracted. Each pattern class is allowed to have deviations in size, style, orientation, etc. within certain limits. This pattern recognition technique is extremely efficient in handwritten character recognition, which is used for illustration in this paper. Because each input pattern is processed with all the pattern classes simultaneously, the speed of this pattern recognition technique is very high. It is found that most input patterns are recognized within first comparison process and no input patterns require more than two comparison processes for their recognition.",
author = "Sik-Sang Yau and Yang, {C. C.}",
year = "1966",
doi = "10.1109/PGEC.1966.264485",
language = "English (US)",
volume = "EC-15",
pages = "944--947",
journal = "IEEE Transactions on Computers",
issn = "0018-9340",
publisher = "IEEE Computer Society",
number = "6",

}

TY - JOUR

T1 - Pattern Recognition by Using an Associative Memory

AU - Yau, Sik-Sang

AU - Yang, C. C.

PY - 1966

Y1 - 1966

N2 - The purpose of this paper is to present a simple template-matching pattern recognition technique by using any general-purpose associative memory. The input patterns for recognition may have wide variations, provided that the distinct features of individual pattern classes can be extracted. Each pattern class is allowed to have deviations in size, style, orientation, etc. within certain limits. This pattern recognition technique is extremely efficient in handwritten character recognition, which is used for illustration in this paper. Because each input pattern is processed with all the pattern classes simultaneously, the speed of this pattern recognition technique is very high. It is found that most input patterns are recognized within first comparison process and no input patterns require more than two comparison processes for their recognition.

AB - The purpose of this paper is to present a simple template-matching pattern recognition technique by using any general-purpose associative memory. The input patterns for recognition may have wide variations, provided that the distinct features of individual pattern classes can be extracted. Each pattern class is allowed to have deviations in size, style, orientation, etc. within certain limits. This pattern recognition technique is extremely efficient in handwritten character recognition, which is used for illustration in this paper. Because each input pattern is processed with all the pattern classes simultaneously, the speed of this pattern recognition technique is very high. It is found that most input patterns are recognized within first comparison process and no input patterns require more than two comparison processes for their recognition.

UR - http://www.scopus.com/inward/record.url?scp=11744275235&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11744275235&partnerID=8YFLogxK

U2 - 10.1109/PGEC.1966.264485

DO - 10.1109/PGEC.1966.264485

M3 - Article

AN - SCOPUS:11744275235

VL - EC-15

SP - 944

EP - 947

JO - IEEE Transactions on Computers

JF - IEEE Transactions on Computers

SN - 0018-9340

IS - 6

ER -