Selectively filtering image features using a percentage occupancy hit-or-miss transform

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

The Hit-or-Miss Transform (HMT) is a well known morphological transform which can be used for template matching and other applications. Recent developments in this area include extensions of the HMT which have employed a variety of techniques in order to improve the noise robustness of the transform. Rank order filters feature heavily in these approaches, and recently, a novel design tool, known as a PO plot, has been introduced. This tool can be used to determine the optimum rank parameter when using these extensions of the HMT to locate features in noisy data. In this paper, the properties of the PO plot are exploited in such a way that an extension of the HMT, known as a POHMT, can be used as a discriminatory filter which selectively marks or discards features in an image. This paper summarises the POHMT, and the PO plot, before demonstrating how these can be used to implement a discriminatory filter. This filter is then shown to produce promising results when applied to the problem of selectively detecting dice in images.
LanguageEnglish
Number of pages6
DOIs
Publication statusPublished - 3 Jul 2012
EventIET Image Processing Conference 2012 - London, United Kingdom
Duration: 3 Jul 20124 Jul 2012

Conference

ConferenceIET Image Processing Conference 2012
CountryUnited Kingdom
CityLondon
Period3/07/124/07/12

Fingerprint

Mathematical transformations
Template matching

Keywords

  • transforms
  • filtering theory
  • object detection
  • image matching

Cite this

Murray, Paul ; Marshall, Stephen. / Selectively filtering image features using a percentage occupancy hit-or-miss transform. Paper presented at IET Image Processing Conference 2012, London, United Kingdom.6 p.
@conference{032047944b8342f3a2b90b85048d63a6,
title = "Selectively filtering image features using a percentage occupancy hit-or-miss transform",
abstract = "The Hit-or-Miss Transform (HMT) is a well known morphological transform which can be used for template matching and other applications. Recent developments in this area include extensions of the HMT which have employed a variety of techniques in order to improve the noise robustness of the transform. Rank order filters feature heavily in these approaches, and recently, a novel design tool, known as a PO plot, has been introduced. This tool can be used to determine the optimum rank parameter when using these extensions of the HMT to locate features in noisy data. In this paper, the properties of the PO plot are exploited in such a way that an extension of the HMT, known as a POHMT, can be used as a discriminatory filter which selectively marks or discards features in an image. This paper summarises the POHMT, and the PO plot, before demonstrating how these can be used to implement a discriminatory filter. This filter is then shown to produce promising results when applied to the problem of selectively detecting dice in images.",
keywords = "transforms, filtering theory, object detection, image matching",
author = "Paul Murray and Stephen Marshall",
year = "2012",
month = "7",
day = "3",
doi = "10.1049/cp.2012.0427",
language = "English",
note = "IET Image Processing Conference 2012 ; Conference date: 03-07-2012 Through 04-07-2012",

}

Murray, P & Marshall, S 2012, 'Selectively filtering image features using a percentage occupancy hit-or-miss transform' Paper presented at IET Image Processing Conference 2012, London, United Kingdom, 3/07/12 - 4/07/12, . https://doi.org/10.1049/cp.2012.0427

Selectively filtering image features using a percentage occupancy hit-or-miss transform. / Murray, Paul; Marshall, Stephen.

2012. Paper presented at IET Image Processing Conference 2012, London, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Selectively filtering image features using a percentage occupancy hit-or-miss transform

AU - Murray, Paul

AU - Marshall, Stephen

PY - 2012/7/3

Y1 - 2012/7/3

N2 - The Hit-or-Miss Transform (HMT) is a well known morphological transform which can be used for template matching and other applications. Recent developments in this area include extensions of the HMT which have employed a variety of techniques in order to improve the noise robustness of the transform. Rank order filters feature heavily in these approaches, and recently, a novel design tool, known as a PO plot, has been introduced. This tool can be used to determine the optimum rank parameter when using these extensions of the HMT to locate features in noisy data. In this paper, the properties of the PO plot are exploited in such a way that an extension of the HMT, known as a POHMT, can be used as a discriminatory filter which selectively marks or discards features in an image. This paper summarises the POHMT, and the PO plot, before demonstrating how these can be used to implement a discriminatory filter. This filter is then shown to produce promising results when applied to the problem of selectively detecting dice in images.

AB - The Hit-or-Miss Transform (HMT) is a well known morphological transform which can be used for template matching and other applications. Recent developments in this area include extensions of the HMT which have employed a variety of techniques in order to improve the noise robustness of the transform. Rank order filters feature heavily in these approaches, and recently, a novel design tool, known as a PO plot, has been introduced. This tool can be used to determine the optimum rank parameter when using these extensions of the HMT to locate features in noisy data. In this paper, the properties of the PO plot are exploited in such a way that an extension of the HMT, known as a POHMT, can be used as a discriminatory filter which selectively marks or discards features in an image. This paper summarises the POHMT, and the PO plot, before demonstrating how these can be used to implement a discriminatory filter. This filter is then shown to produce promising results when applied to the problem of selectively detecting dice in images.

KW - transforms

KW - filtering theory

KW - object detection

KW - image matching

UR - http://conferences.theiet.org/ipr/index.cfm

U2 - 10.1049/cp.2012.0427

DO - 10.1049/cp.2012.0427

M3 - Paper

ER -