Number Recognition Using Inductive Learning on Spiral Architecture

Xiangjian He; Tom Hintz; Qiang Wu; Lihong Zheng

Number Recognition Using Inductive Learning on Spiral Architecture

Xiangjian He, Tom Hintz, Qiang Wu, Lihong Zheng

Research output: Book chapter/Published conference paper › Conference paper › peer-review

22 Downloads (Pure)

Abstract

In this paper, a number recognition algorithm on Spiral Architectureis proposed. This algorithm employs RULES-3 inductive learning method and template matching technique. The algorithm starts from a collection of samples of numbers from number plates. Edge maps of the samples are then detected based on Spiral Architecture. A set of rules are extracted using these samples by RULES-3. The rules describe the frequencies of 9 different edge masks appearing in the samples. Each mask is a cluster of 7 hexagonal pixels. In order to recognize a number plate, all numbers are tested one by one using the extracted rules. The number recognition is achieved by counting the frequencies of the 9 masks.

Original language	English
Title of host publication	International Conference On Computer Vision (VISION'05)
Editors	Hamid R Arabnia
Place of Publication	U.S.A
Publisher	CSREA Press
Pages	58-64
Number of pages	7
ISBN (Electronic)	1932415653
Publication status	Published - 2005
Event	International Conference on Computer Vision - Las Vegas, USA, New Zealand Duration: 20 Jun 2005 → 23 Jun 2005

Conference

Conference	International Conference on Computer Vision
Country/Territory	New Zealand
Period	20/06/05 → 23/06/05

Access to Document

20100318105157471.pdfAccepted author manuscript, 1.35 MB

Cite this

@inproceedings{cd15e146f47c4344bd7319b272e98c6a,

title = "Number Recognition Using Inductive Learning on Spiral Architecture",

abstract = "In this paper, a number recognition algorithm on Spiral Architectureis proposed. This algorithm employs RULES-3 inductive learning method and template matching technique. The algorithm starts from a collection of samples of numbers from number plates. Edge maps of the samples are then detected based on Spiral Architecture. A set of rules are extracted using these samples by RULES-3. The rules describe the frequencies of 9 different edge masks appearing in the samples. Each mask is a cluster of 7 hexagonal pixels. In order to recognize a number plate, all numbers are tested one by one using the extracted rules. The number recognition is achieved by counting the frequencies of the 9 masks.",

keywords = "Open access version available, Hexagonal structure, Inductive learning, Number recognition, Spiral architecture, Template matching",

author = "Xiangjian He and Tom Hintz and Qiang Wu and Lihong Zheng",

note = "Imported on 03 May 2017 - DigiTool details were: publisher = U.S.A: CSREA Press, 2005. editor/s (773b) = Hamid R Arabnia; Event dates (773o) = 20-23 June, 2005; Parent title (773t) = International Conference on Computer Vision.; International Conference on Computer Vision ; Conference date: 20-06-2005 Through 23-06-2005",

year = "2005",

language = "English",

pages = "58--64",

editor = "Arabnia, {Hamid R}",

booktitle = "International Conference On Computer Vision (VISION'05)",

publisher = "CSREA Press",

}

TY - GEN

T1 - Number Recognition Using Inductive Learning on Spiral Architecture

AU - He, Xiangjian

AU - Hintz, Tom

AU - Wu, Qiang

AU - Zheng, Lihong

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = U.S.A: CSREA Press, 2005. editor/s (773b) = Hamid R Arabnia; Event dates (773o) = 20-23 June, 2005; Parent title (773t) = International Conference on Computer Vision.

PY - 2005

Y1 - 2005

N2 - In this paper, a number recognition algorithm on Spiral Architectureis proposed. This algorithm employs RULES-3 inductive learning method and template matching technique. The algorithm starts from a collection of samples of numbers from number plates. Edge maps of the samples are then detected based on Spiral Architecture. A set of rules are extracted using these samples by RULES-3. The rules describe the frequencies of 9 different edge masks appearing in the samples. Each mask is a cluster of 7 hexagonal pixels. In order to recognize a number plate, all numbers are tested one by one using the extracted rules. The number recognition is achieved by counting the frequencies of the 9 masks.

AB - In this paper, a number recognition algorithm on Spiral Architectureis proposed. This algorithm employs RULES-3 inductive learning method and template matching technique. The algorithm starts from a collection of samples of numbers from number plates. Edge maps of the samples are then detected based on Spiral Architecture. A set of rules are extracted using these samples by RULES-3. The rules describe the frequencies of 9 different edge masks appearing in the samples. Each mask is a cluster of 7 hexagonal pixels. In order to recognize a number plate, all numbers are tested one by one using the extracted rules. The number recognition is achieved by counting the frequencies of the 9 masks.

KW - Open access version available

KW - Hexagonal structure

KW - Inductive learning

KW - Number recognition

KW - Spiral architecture

KW - Template matching

M3 - Conference paper

SP - 58

EP - 64

BT - International Conference On Computer Vision (VISION'05)

A2 - Arabnia, Hamid R

PB - CSREA Press

CY - U.S.A

T2 - International Conference on Computer Vision

Y2 - 20 June 2005 through 23 June 2005

ER -

Number Recognition Using Inductive Learning on Spiral Architecture

Abstract

Conference

Access to Document

Fingerprint

Cite this