Plant species identification using Elliptic Fourier leaf shape analysis

João Camargo Neto, George E. Meyer, David D. Jones, Ashok K Samal

Research output: Contribution to journalArticle

194 Citations (Scopus)

Abstract

Elliptic Fourier (EF) and discriminant analyses were used to identify young soybean (Glycine max (L.) merrill), sunflower (Helianthus pumilus), redroot pigweed (Amaranthus retroflexus) and velvetleaf (Abutilon theophrasti Medicus) plants, based on leaf shape. Chain encoded, Elliptic Fourier harmonic functions were generated based on leaf boundary. A complexity index of the leaf shape was computed using the variation between consecutive EF functions. Principle component analysis was used to select the Fourier coefficients with the best discriminatory power. Canonical discriminant analysis was used to develop species identification models based on leaf shapes extracted from plant color images during the second and third weeks after germination. The classification results showed that plant species during the third week were successfully identified with an average of correct classification rate of 89.4%. The discriminant model correctly classified on average: 77.9% of redroot pigweed, 93.8% of sunflower, 89.4% of velvetleaf and 96.5% of soybean. Using all of the leaves extracted from the second and the third weeks, the overall classification accuracy was 89.2%. The discriminant model correctly classified 76.4% of redroot pigweed, 93.6% of sunflower, 81.6% of velvetleaf, 91.5% of soybean leaf extracted from trifoliolate and 90.9% of soybean unifoliolate leaves. The Elliptic Fourier shape feature analysis could be an important and accurate tool for weed species identification and mapping.

Original languageEnglish (US)
Pages (from-to)121-134
Number of pages14
JournalComputers and Electronics in Agriculture
Volume50
Issue number2
DOIs
StatePublished - Feb 2006

Fingerprint

shape analysis
Abutilon theophrasti
soybean
Harmonic functions
leaves
soybeans
Helianthus annuus
Discriminant analysis
Amino acids
taxonomy
Identification (control systems)
Color
Amaranthus retroflexus
Helianthus
species identification
plant species
discriminant analysis
weed
Glycine max
germination

Keywords

  • Discriminant analysis
  • Elliptic Fourier
  • Leaves
  • Machine vision
  • Shape features

ASJC Scopus subject areas

  • Forestry
  • Agronomy and Crop Science
  • Computer Science Applications
  • Horticulture

Cite this

Plant species identification using Elliptic Fourier leaf shape analysis. / Neto, João Camargo; Meyer, George E.; Jones, David D.; Samal, Ashok K.

In: Computers and Electronics in Agriculture, Vol. 50, No. 2, 02.2006, p. 121-134.

Research output: Contribution to journalArticle

Neto, João Camargo ; Meyer, George E. ; Jones, David D. ; Samal, Ashok K. / Plant species identification using Elliptic Fourier leaf shape analysis. In: Computers and Electronics in Agriculture. 2006 ; Vol. 50, No. 2. pp. 121-134.
@article{9527e4754f1640e2953432a28b87beca,
title = "Plant species identification using Elliptic Fourier leaf shape analysis",
abstract = "Elliptic Fourier (EF) and discriminant analyses were used to identify young soybean (Glycine max (L.) merrill), sunflower (Helianthus pumilus), redroot pigweed (Amaranthus retroflexus) and velvetleaf (Abutilon theophrasti Medicus) plants, based on leaf shape. Chain encoded, Elliptic Fourier harmonic functions were generated based on leaf boundary. A complexity index of the leaf shape was computed using the variation between consecutive EF functions. Principle component analysis was used to select the Fourier coefficients with the best discriminatory power. Canonical discriminant analysis was used to develop species identification models based on leaf shapes extracted from plant color images during the second and third weeks after germination. The classification results showed that plant species during the third week were successfully identified with an average of correct classification rate of 89.4{\%}. The discriminant model correctly classified on average: 77.9{\%} of redroot pigweed, 93.8{\%} of sunflower, 89.4{\%} of velvetleaf and 96.5{\%} of soybean. Using all of the leaves extracted from the second and the third weeks, the overall classification accuracy was 89.2{\%}. The discriminant model correctly classified 76.4{\%} of redroot pigweed, 93.6{\%} of sunflower, 81.6{\%} of velvetleaf, 91.5{\%} of soybean leaf extracted from trifoliolate and 90.9{\%} of soybean unifoliolate leaves. The Elliptic Fourier shape feature analysis could be an important and accurate tool for weed species identification and mapping.",
keywords = "Discriminant analysis, Elliptic Fourier, Leaves, Machine vision, Shape features",
author = "Neto, {Jo{\~a}o Camargo} and Meyer, {George E.} and Jones, {David D.} and Samal, {Ashok K}",
year = "2006",
month = "2",
doi = "10.1016/j.compag.2005.09.004",
language = "English (US)",
volume = "50",
pages = "121--134",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Plant species identification using Elliptic Fourier leaf shape analysis

AU - Neto, João Camargo

AU - Meyer, George E.

AU - Jones, David D.

AU - Samal, Ashok K

PY - 2006/2

Y1 - 2006/2

N2 - Elliptic Fourier (EF) and discriminant analyses were used to identify young soybean (Glycine max (L.) merrill), sunflower (Helianthus pumilus), redroot pigweed (Amaranthus retroflexus) and velvetleaf (Abutilon theophrasti Medicus) plants, based on leaf shape. Chain encoded, Elliptic Fourier harmonic functions were generated based on leaf boundary. A complexity index of the leaf shape was computed using the variation between consecutive EF functions. Principle component analysis was used to select the Fourier coefficients with the best discriminatory power. Canonical discriminant analysis was used to develop species identification models based on leaf shapes extracted from plant color images during the second and third weeks after germination. The classification results showed that plant species during the third week were successfully identified with an average of correct classification rate of 89.4%. The discriminant model correctly classified on average: 77.9% of redroot pigweed, 93.8% of sunflower, 89.4% of velvetleaf and 96.5% of soybean. Using all of the leaves extracted from the second and the third weeks, the overall classification accuracy was 89.2%. The discriminant model correctly classified 76.4% of redroot pigweed, 93.6% of sunflower, 81.6% of velvetleaf, 91.5% of soybean leaf extracted from trifoliolate and 90.9% of soybean unifoliolate leaves. The Elliptic Fourier shape feature analysis could be an important and accurate tool for weed species identification and mapping.

AB - Elliptic Fourier (EF) and discriminant analyses were used to identify young soybean (Glycine max (L.) merrill), sunflower (Helianthus pumilus), redroot pigweed (Amaranthus retroflexus) and velvetleaf (Abutilon theophrasti Medicus) plants, based on leaf shape. Chain encoded, Elliptic Fourier harmonic functions were generated based on leaf boundary. A complexity index of the leaf shape was computed using the variation between consecutive EF functions. Principle component analysis was used to select the Fourier coefficients with the best discriminatory power. Canonical discriminant analysis was used to develop species identification models based on leaf shapes extracted from plant color images during the second and third weeks after germination. The classification results showed that plant species during the third week were successfully identified with an average of correct classification rate of 89.4%. The discriminant model correctly classified on average: 77.9% of redroot pigweed, 93.8% of sunflower, 89.4% of velvetleaf and 96.5% of soybean. Using all of the leaves extracted from the second and the third weeks, the overall classification accuracy was 89.2%. The discriminant model correctly classified 76.4% of redroot pigweed, 93.6% of sunflower, 81.6% of velvetleaf, 91.5% of soybean leaf extracted from trifoliolate and 90.9% of soybean unifoliolate leaves. The Elliptic Fourier shape feature analysis could be an important and accurate tool for weed species identification and mapping.

KW - Discriminant analysis

KW - Elliptic Fourier

KW - Leaves

KW - Machine vision

KW - Shape features

UR - http://www.scopus.com/inward/record.url?scp=30344459978&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=30344459978&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2005.09.004

DO - 10.1016/j.compag.2005.09.004

M3 - Article

AN - SCOPUS:30344459978

VL - 50

SP - 121

EP - 134

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

IS - 2

ER -