A Binary Neural Shape Matcher using Johnson Counters and Chain Codes

Victoria Hodge; Simon O'Keefe; Jim Austin

A Binary Neural Shape Matcher using Johnson Counters and Chain Codes

Victoria Hodge, Simon O'Keefe, Jim Austin

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we introduce a neural network-based shape matching algorithm that uses Johnson Counter codes coupled with chain codes. Shape matching is a fundamental requirement in content-based image retrieval systems. Chain codes describe shapes using sequences of numbers. They are simple and flexible. We couple this power with the efficiency and flexibility of a binary associative-memory neural network. We focus on the implementation details of the algorithm when it is constructed using the neural network. We demonstrate how the binary associative-memory neural network can index and match chain codes where the chain code elements are represented by Johnson codes.

Original language	English
Title of host publication	BICS
Publication status	Published - 10 Mar 2006
Event	Brain Inspired Cognitive Systems 2006 - Island of Lesvos, Greece Duration: 10 Oct 2006 → 14 Oct 2006

Conference

Conference	Brain Inspired Cognitive Systems 2006
Country/Territory	Greece
City	Island of Lesvos
Period	10/10/06 → 14/10/06

Bibliographical note

See also http://eprints.whiterose.ac.uk/5431/

Keywords

Neural
Associative Memory
Shape Matcher
BinaryEncoding

Access to Document

BICS_Hodge_OKeefe_Austin.pdf

Cite this

@inproceedings{5219067c730842c2822593e3d0eafd4e,

title = "A Binary Neural Shape Matcher using Johnson Counters and Chain Codes",

abstract = "In this paper, we introduce a neural network-based shape matching algorithm that uses Johnson Counter codes coupled with chain codes. Shape matching is a fundamental requirement in content-based image retrieval systems. Chain codes describe shapes using sequences of numbers. They are simple and flexible. We couple this power with the efficiency and flexibility of a binary associative-memory neural network. We focus on the implementation details of the algorithm when it is constructed using the neural network. We demonstrate how the binary associative-memory neural network can index and match chain codes where the chain code elements are represented by Johnson codes.",

keywords = "Neural, Associative Memory, Shape Matcher, BinaryEncoding",

author = "Victoria Hodge and Simon O'Keefe and Jim Austin",

note = "See also http://eprints.whiterose.ac.uk/5431/; Brain Inspired Cognitive Systems 2006 ; Conference date: 10-10-2006 Through 14-10-2006",

year = "2006",

month = mar,

day = "10",

language = "English",

booktitle = "BICS",

}

TY - GEN

T1 - A Binary Neural Shape Matcher using Johnson Counters and Chain Codes

AU - Hodge, Victoria

AU - O'Keefe, Simon

AU - Austin, Jim

N1 - See also http://eprints.whiterose.ac.uk/5431/

PY - 2006/3/10

Y1 - 2006/3/10

N2 - In this paper, we introduce a neural network-based shape matching algorithm that uses Johnson Counter codes coupled with chain codes. Shape matching is a fundamental requirement in content-based image retrieval systems. Chain codes describe shapes using sequences of numbers. They are simple and flexible. We couple this power with the efficiency and flexibility of a binary associative-memory neural network. We focus on the implementation details of the algorithm when it is constructed using the neural network. We demonstrate how the binary associative-memory neural network can index and match chain codes where the chain code elements are represented by Johnson codes.

AB - In this paper, we introduce a neural network-based shape matching algorithm that uses Johnson Counter codes coupled with chain codes. Shape matching is a fundamental requirement in content-based image retrieval systems. Chain codes describe shapes using sequences of numbers. They are simple and flexible. We couple this power with the efficiency and flexibility of a binary associative-memory neural network. We focus on the implementation details of the algorithm when it is constructed using the neural network. We demonstrate how the binary associative-memory neural network can index and match chain codes where the chain code elements are represented by Johnson codes.

KW - Neural

KW - Associative Memory

KW - Shape Matcher

KW - BinaryEncoding

M3 - Conference contribution

BT - BICS

T2 - Brain Inspired Cognitive Systems 2006

Y2 - 10 October 2006 through 14 October 2006

ER -