Weed and crop discrimination using image analysis and artificial intelligence methods

Matthew Aitkenhead, I. A. Dalgetty, Christopher Mullins, Allan James Stuart McDonald, Norval James Colin Strachan

Research output: Contribution to journalArticle

106 Citations (Scopus)

Abstract

Development of a visual method of discriminating between crop seedlings and weeds is an important and necessary step towards the automation of non-chemical weed control systems in agriculture, and towards the reduction in chemical use through spot spraying. Two methods were applied to recognise carrot (Daucus carota L.) seedlings from those of ryegrass (Lolium perenne) and Fat Hen (Chenopodium album) using digital imaging. The first method involved the use of a simple morphological characteristic measurement of leaf shape (perimeter(2)/area), which had varying effectiveness (between 52 and 74%) in discriminating between the two types of plant, with the variation dependent on plant size. The second involved a self-organising neural network more biologically plausible than many commonly used NN methods. While the latter did not give results as good as those required for commercial purposes, it showed that a neural network-based methodology exists which allows the system to learn and discriminate between species to an accuracy exceeding 75% without predefined plant descriptions being necessary. (C) 2003 Elsevier Science B.V. All rights reserved.

Original languageEnglish
Pages (from-to)157-171
Number of pages14
JournalComputers and Electronics in Agriculture
Volume39
Issue number3
DOIs
Publication statusPublished - Aug 2003

Keywords

  • image analysis
  • neural network
  • plant species discrimination
  • plant morphology
  • machine vision
  • shape-analysis
  • identification
  • vehicle
  • network
  • fields

Cite this

Weed and crop discrimination using image analysis and artificial intelligence methods. / Aitkenhead, Matthew; Dalgetty, I. A.; Mullins, Christopher; McDonald, Allan James Stuart; Strachan, Norval James Colin.

In: Computers and Electronics in Agriculture, Vol. 39, No. 3, 08.2003, p. 157-171.

Research output: Contribution to journalArticle

Aitkenhead, Matthew ; Dalgetty, I. A. ; Mullins, Christopher ; McDonald, Allan James Stuart ; Strachan, Norval James Colin. / Weed and crop discrimination using image analysis and artificial intelligence methods. In: Computers and Electronics in Agriculture. 2003 ; Vol. 39, No. 3. pp. 157-171.
@article{ebf9ac0adfff4aad8ed4688570dd30b6,
title = "Weed and crop discrimination using image analysis and artificial intelligence methods",
abstract = "Development of a visual method of discriminating between crop seedlings and weeds is an important and necessary step towards the automation of non-chemical weed control systems in agriculture, and towards the reduction in chemical use through spot spraying. Two methods were applied to recognise carrot (Daucus carota L.) seedlings from those of ryegrass (Lolium perenne) and Fat Hen (Chenopodium album) using digital imaging. The first method involved the use of a simple morphological characteristic measurement of leaf shape (perimeter(2)/area), which had varying effectiveness (between 52 and 74{\%}) in discriminating between the two types of plant, with the variation dependent on plant size. The second involved a self-organising neural network more biologically plausible than many commonly used NN methods. While the latter did not give results as good as those required for commercial purposes, it showed that a neural network-based methodology exists which allows the system to learn and discriminate between species to an accuracy exceeding 75{\%} without predefined plant descriptions being necessary. (C) 2003 Elsevier Science B.V. All rights reserved.",
keywords = "image analysis, neural network, plant species discrimination, plant morphology, machine vision, shape-analysis, identification, vehicle, network, fields",
author = "Matthew Aitkenhead and Dalgetty, {I. A.} and Christopher Mullins and McDonald, {Allan James Stuart} and Strachan, {Norval James Colin}",
year = "2003",
month = "8",
doi = "10.1016/S0168-1699(03)00076-0",
language = "English",
volume = "39",
pages = "157--171",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Weed and crop discrimination using image analysis and artificial intelligence methods

AU - Aitkenhead, Matthew

AU - Dalgetty, I. A.

AU - Mullins, Christopher

AU - McDonald, Allan James Stuart

AU - Strachan, Norval James Colin

PY - 2003/8

Y1 - 2003/8

N2 - Development of a visual method of discriminating between crop seedlings and weeds is an important and necessary step towards the automation of non-chemical weed control systems in agriculture, and towards the reduction in chemical use through spot spraying. Two methods were applied to recognise carrot (Daucus carota L.) seedlings from those of ryegrass (Lolium perenne) and Fat Hen (Chenopodium album) using digital imaging. The first method involved the use of a simple morphological characteristic measurement of leaf shape (perimeter(2)/area), which had varying effectiveness (between 52 and 74%) in discriminating between the two types of plant, with the variation dependent on plant size. The second involved a self-organising neural network more biologically plausible than many commonly used NN methods. While the latter did not give results as good as those required for commercial purposes, it showed that a neural network-based methodology exists which allows the system to learn and discriminate between species to an accuracy exceeding 75% without predefined plant descriptions being necessary. (C) 2003 Elsevier Science B.V. All rights reserved.

AB - Development of a visual method of discriminating between crop seedlings and weeds is an important and necessary step towards the automation of non-chemical weed control systems in agriculture, and towards the reduction in chemical use through spot spraying. Two methods were applied to recognise carrot (Daucus carota L.) seedlings from those of ryegrass (Lolium perenne) and Fat Hen (Chenopodium album) using digital imaging. The first method involved the use of a simple morphological characteristic measurement of leaf shape (perimeter(2)/area), which had varying effectiveness (between 52 and 74%) in discriminating between the two types of plant, with the variation dependent on plant size. The second involved a self-organising neural network more biologically plausible than many commonly used NN methods. While the latter did not give results as good as those required for commercial purposes, it showed that a neural network-based methodology exists which allows the system to learn and discriminate between species to an accuracy exceeding 75% without predefined plant descriptions being necessary. (C) 2003 Elsevier Science B.V. All rights reserved.

KW - image analysis

KW - neural network

KW - plant species discrimination

KW - plant morphology

KW - machine vision

KW - shape-analysis

KW - identification

KW - vehicle

KW - network

KW - fields

U2 - 10.1016/S0168-1699(03)00076-0

DO - 10.1016/S0168-1699(03)00076-0

M3 - Article

VL - 39

SP - 157

EP - 171

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

IS - 3

ER -