# Pattern recognition

Joseph O’Rourke, Godfried Toussaint

Research output: Chapter in Book/Report/Conference proceedingChapter

### Abstract

Introduction The two fundamental problems in a pattern recognition system are feature extraction (shape measurement) and classification. The problem of extracting a vector of shape measurements from a digital image can be further decomposed into three subproblems. The first is the image segmentation problem, i.e., the separation of objects of interest from their background. The cluster analysis methods discussed in Section 54.1 are useful here. The second subproblem is that of finding the objects in the segmented image. An example is the location of text lines in a document as illustrated in Section 54.2. The final subproblem is extracting the shape information from the objects detected. Here there are many tools available depending on the properties of the objects that are to be classified. The Hough transform (Section 54.2), polygonal approximation (Section 54.3), shape measurement (Section 54.4), and polygon decomposition (Section 54.6), are some of the favorite tools used here. Important to many of these tasks is finding a nice viewpoint from which extraction is robust and efficient (Section 54.5). Proximity graphs, discussed in Section 54.2, are used extensively for both cluster analysis and shape measurement.

Original language English (US) Handbook of Discrete and Computational Geometry, Third Edition CRC Press 1421-1450 30 9781498711425 9781498711395 https://doi.org/10.1201/9781315119601 Published - Jan 1 2017

### Fingerprint

Pattern Recognition
Pattern recognition
Shape Measurement
Cluster analysis
Pattern recognition systems
Hough transforms
Cluster Analysis
Image segmentation
Feature extraction
Polygon Decomposition
Proximity Graphs
Polygonal Approximation
Decomposition
Hough Transform
Digital Image
Image Segmentation
Feature Extraction
Object
Line

### ASJC Scopus subject areas

• Computer Science(all)
• Mathematics(all)

### Cite this

O’Rourke, J., & Toussaint, G. (2017). Pattern recognition. In Handbook of Discrete and Computational Geometry, Third Edition (pp. 1421-1450). CRC Press. https://doi.org/10.1201/9781315119601

Pattern recognition. / O’Rourke, Joseph; Toussaint, Godfried.

Handbook of Discrete and Computational Geometry, Third Edition. CRC Press, 2017. p. 1421-1450.

Research output: Chapter in Book/Report/Conference proceedingChapter

O’Rourke, J & Toussaint, G 2017, Pattern recognition. in Handbook of Discrete and Computational Geometry, Third Edition. CRC Press, pp. 1421-1450. https://doi.org/10.1201/9781315119601
O’Rourke J, Toussaint G. Pattern recognition. In Handbook of Discrete and Computational Geometry, Third Edition. CRC Press. 2017. p. 1421-1450 https://doi.org/10.1201/9781315119601
O’Rourke, Joseph ; Toussaint, Godfried. / Pattern recognition. Handbook of Discrete and Computational Geometry, Third Edition. CRC Press, 2017. pp. 1421-1450
@inbook{8bbea17058b649a0a7836aa54b270fc1,
title = "Pattern recognition",
abstract = "Introduction The two fundamental problems in a pattern recognition system are feature extraction (shape measurement) and classification. The problem of extracting a vector of shape measurements from a digital image can be further decomposed into three subproblems. The first is the image segmentation problem, i.e., the separation of objects of interest from their background. The cluster analysis methods discussed in Section 54.1 are useful here. The second subproblem is that of finding the objects in the segmented image. An example is the location of text lines in a document as illustrated in Section 54.2. The final subproblem is extracting the shape information from the objects detected. Here there are many tools available depending on the properties of the objects that are to be classified. The Hough transform (Section 54.2), polygonal approximation (Section 54.3), shape measurement (Section 54.4), and polygon decomposition (Section 54.6), are some of the favorite tools used here. Important to many of these tasks is finding a nice viewpoint from which extraction is robust and efficient (Section 54.5). Proximity graphs, discussed in Section 54.2, are used extensively for both cluster analysis and shape measurement.",
author = "Joseph O’Rourke and Godfried Toussaint",
year = "2017",
month = "1",
day = "1",
doi = "10.1201/9781315119601",
language = "English (US)",
isbn = "9781498711395",
pages = "1421--1450",
booktitle = "Handbook of Discrete and Computational Geometry, Third Edition",
publisher = "CRC Press",

}

TY - CHAP

T1 - Pattern recognition

AU - O’Rourke, Joseph

AU - Toussaint, Godfried

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Introduction The two fundamental problems in a pattern recognition system are feature extraction (shape measurement) and classification. The problem of extracting a vector of shape measurements from a digital image can be further decomposed into three subproblems. The first is the image segmentation problem, i.e., the separation of objects of interest from their background. The cluster analysis methods discussed in Section 54.1 are useful here. The second subproblem is that of finding the objects in the segmented image. An example is the location of text lines in a document as illustrated in Section 54.2. The final subproblem is extracting the shape information from the objects detected. Here there are many tools available depending on the properties of the objects that are to be classified. The Hough transform (Section 54.2), polygonal approximation (Section 54.3), shape measurement (Section 54.4), and polygon decomposition (Section 54.6), are some of the favorite tools used here. Important to many of these tasks is finding a nice viewpoint from which extraction is robust and efficient (Section 54.5). Proximity graphs, discussed in Section 54.2, are used extensively for both cluster analysis and shape measurement.

AB - Introduction The two fundamental problems in a pattern recognition system are feature extraction (shape measurement) and classification. The problem of extracting a vector of shape measurements from a digital image can be further decomposed into three subproblems. The first is the image segmentation problem, i.e., the separation of objects of interest from their background. The cluster analysis methods discussed in Section 54.1 are useful here. The second subproblem is that of finding the objects in the segmented image. An example is the location of text lines in a document as illustrated in Section 54.2. The final subproblem is extracting the shape information from the objects detected. Here there are many tools available depending on the properties of the objects that are to be classified. The Hough transform (Section 54.2), polygonal approximation (Section 54.3), shape measurement (Section 54.4), and polygon decomposition (Section 54.6), are some of the favorite tools used here. Important to many of these tasks is finding a nice viewpoint from which extraction is robust and efficient (Section 54.5). Proximity graphs, discussed in Section 54.2, are used extensively for both cluster analysis and shape measurement.

UR - http://www.scopus.com/inward/record.url?scp=85052680165&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052680165&partnerID=8YFLogxK

U2 - 10.1201/9781315119601

DO - 10.1201/9781315119601

M3 - Chapter

AN - SCOPUS:85052680165

SN - 9781498711395

SP - 1421

EP - 1450

BT - Handbook of Discrete and Computational Geometry, Third Edition

PB - CRC Press

ER -