SEEDLING DISCRIMINATION USING SHAPE FEATURES DERIVED FROM A DISTANCE TRANSFORM

Thomas Mosgaard Giselsson, Rasmus Nyholm Jørgensen, Henrik Midtiby

Research output: Contribution to conference without publisher/journalPaperResearch

162 Downloads (Pure)

Abstract

One branch of general image processing research deals with 2D object classification where classes are categorized by different features of the objects such as area, perimeter, elongation, color and texture. When dealing with plant specie classification some of the widely used and well known object features are less useful because the task is to categorize soft objects in outdoor scenes. A general feature set for robust description of soft objects such as plants in an early growth stage is, to our knowledge non existing. We propose a novel way of parametrizing a distance transformation of an object silhouette that may prove to posses value in object classification.
The method approximate the distance distribution of an object with a high degree Legendre polynomial where the polynomial coefficients constitutes a feature set. This feature set will be referred to as Legendre Polynomial Feature Set (LPFS). The method have been tested through a discrimination task where two similar plant species were to be divided into their respective classes. Since the LPFS feature set is meant to be used with a classification algorithm, the performance assessment is the classification accuracy of 4 different classifiers (kNN, Naive-Bayes, Linear SVM, Non-linear SVM). A set of well known features is used for comparison. This feature set will be referred to as Standard Feature Set (SFS). The used dataset consisted of 139 samples of Corn Flower (Centaura cyanus L.) and 63 samples of Night Shade (Solanum nigrum L.).
The highest achieved discrimination accuracy with the LPFS feature set was 98.75 % and contained 10 numerical features. The SFS feature set achieved an accuracy of 87.1 % using 22 features. The results show the LPFS feature set can compete with the SFS feature set. Further testing is needed to reveal the true value of the LPFS feature set.
Original languageEnglish
Publication date2012
Number of pages7
Publication statusPublished - 2012
EventInternational Conference of Agricultural Engineering - Valencia, Spain
Duration: 8. Jul 201212. Jul 2012

Conference

ConferenceInternational Conference of Agricultural Engineering
CountrySpain
CityValencia
Period08/07/201212/07/2012

Cite this

Mosgaard Giselsson, T., Jørgensen, R. N., & Midtiby, H. (2012). SEEDLING DISCRIMINATION USING SHAPE FEATURES DERIVED FROM A DISTANCE TRANSFORM. Paper presented at International Conference of Agricultural Engineering, Valencia, Spain.
Mosgaard Giselsson, Thomas ; Jørgensen, Rasmus Nyholm ; Midtiby, Henrik. / SEEDLING DISCRIMINATION USING SHAPE FEATURES DERIVED FROM A DISTANCE TRANSFORM. Paper presented at International Conference of Agricultural Engineering, Valencia, Spain.7 p.
@conference{e23523e71b464173a42f2deb07a61ec5,
title = "SEEDLING DISCRIMINATION USING SHAPE FEATURES DERIVED FROM A DISTANCE TRANSFORM",
abstract = "One branch of general image processing research deals with 2D object classification where classes are categorized by different features of the objects such as area, perimeter, elongation, color and texture. When dealing with plant specie classification some of the widely used and well known object features are less useful because the task is to categorize soft objects in outdoor scenes. A general feature set for robust description of soft objects such as plants in an early growth stage is, to our knowledge non existing. We propose a novel way of parametrizing a distance transformation of an object silhouette that may prove to posses value in object classification.The method approximate the distance distribution of an object with a high degree Legendre polynomial where the polynomial coefficients constitutes a feature set. This feature set will be referred to as Legendre Polynomial Feature Set (LPFS). The method have been tested through a discrimination task where two similar plant species were to be divided into their respective classes. Since the LPFS feature set is meant to be used with a classification algorithm, the performance assessment is the classification accuracy of 4 different classifiers (kNN, Naive-Bayes, Linear SVM, Non-linear SVM). A set of well known features is used for comparison. This feature set will be referred to as Standard Feature Set (SFS). The used dataset consisted of 139 samples of Corn Flower (Centaura cyanus L.) and 63 samples of Night Shade (Solanum nigrum L.).The highest achieved discrimination accuracy with the LPFS feature set was 98.75 {\%} and contained 10 numerical features. The SFS feature set achieved an accuracy of 87.1 {\%} using 22 features. The results show the LPFS feature set can compete with the SFS feature set. Further testing is needed to reveal the true value of the LPFS feature set.",
keywords = "Object discrimination, Machine learning, Feature generation, Precision weeding",
author = "{Mosgaard Giselsson}, Thomas and J{\o}rgensen, {Rasmus Nyholm} and Henrik Midtiby",
year = "2012",
language = "English",
note = "null ; Conference date: 08-07-2012 Through 12-07-2012",

}

Mosgaard Giselsson, T, Jørgensen, RN & Midtiby, H 2012, 'SEEDLING DISCRIMINATION USING SHAPE FEATURES DERIVED FROM A DISTANCE TRANSFORM', Paper presented at International Conference of Agricultural Engineering, Valencia, Spain, 08/07/2012 - 12/07/2012.

SEEDLING DISCRIMINATION USING SHAPE FEATURES DERIVED FROM A DISTANCE TRANSFORM. / Mosgaard Giselsson, Thomas; Jørgensen, Rasmus Nyholm; Midtiby, Henrik.

2012. Paper presented at International Conference of Agricultural Engineering, Valencia, Spain.

Research output: Contribution to conference without publisher/journalPaperResearch

TY - CONF

T1 - SEEDLING DISCRIMINATION USING SHAPE FEATURES DERIVED FROM A DISTANCE TRANSFORM

AU - Mosgaard Giselsson, Thomas

AU - Jørgensen, Rasmus Nyholm

AU - Midtiby, Henrik

PY - 2012

Y1 - 2012

N2 - One branch of general image processing research deals with 2D object classification where classes are categorized by different features of the objects such as area, perimeter, elongation, color and texture. When dealing with plant specie classification some of the widely used and well known object features are less useful because the task is to categorize soft objects in outdoor scenes. A general feature set for robust description of soft objects such as plants in an early growth stage is, to our knowledge non existing. We propose a novel way of parametrizing a distance transformation of an object silhouette that may prove to posses value in object classification.The method approximate the distance distribution of an object with a high degree Legendre polynomial where the polynomial coefficients constitutes a feature set. This feature set will be referred to as Legendre Polynomial Feature Set (LPFS). The method have been tested through a discrimination task where two similar plant species were to be divided into their respective classes. Since the LPFS feature set is meant to be used with a classification algorithm, the performance assessment is the classification accuracy of 4 different classifiers (kNN, Naive-Bayes, Linear SVM, Non-linear SVM). A set of well known features is used for comparison. This feature set will be referred to as Standard Feature Set (SFS). The used dataset consisted of 139 samples of Corn Flower (Centaura cyanus L.) and 63 samples of Night Shade (Solanum nigrum L.).The highest achieved discrimination accuracy with the LPFS feature set was 98.75 % and contained 10 numerical features. The SFS feature set achieved an accuracy of 87.1 % using 22 features. The results show the LPFS feature set can compete with the SFS feature set. Further testing is needed to reveal the true value of the LPFS feature set.

AB - One branch of general image processing research deals with 2D object classification where classes are categorized by different features of the objects such as area, perimeter, elongation, color and texture. When dealing with plant specie classification some of the widely used and well known object features are less useful because the task is to categorize soft objects in outdoor scenes. A general feature set for robust description of soft objects such as plants in an early growth stage is, to our knowledge non existing. We propose a novel way of parametrizing a distance transformation of an object silhouette that may prove to posses value in object classification.The method approximate the distance distribution of an object with a high degree Legendre polynomial where the polynomial coefficients constitutes a feature set. This feature set will be referred to as Legendre Polynomial Feature Set (LPFS). The method have been tested through a discrimination task where two similar plant species were to be divided into their respective classes. Since the LPFS feature set is meant to be used with a classification algorithm, the performance assessment is the classification accuracy of 4 different classifiers (kNN, Naive-Bayes, Linear SVM, Non-linear SVM). A set of well known features is used for comparison. This feature set will be referred to as Standard Feature Set (SFS). The used dataset consisted of 139 samples of Corn Flower (Centaura cyanus L.) and 63 samples of Night Shade (Solanum nigrum L.).The highest achieved discrimination accuracy with the LPFS feature set was 98.75 % and contained 10 numerical features. The SFS feature set achieved an accuracy of 87.1 % using 22 features. The results show the LPFS feature set can compete with the SFS feature set. Further testing is needed to reveal the true value of the LPFS feature set.

KW - Object discrimination

KW - Machine learning

KW - Feature generation

KW - Precision weeding

M3 - Paper

ER -

Mosgaard Giselsson T, Jørgensen RN, Midtiby H. SEEDLING DISCRIMINATION USING SHAPE FEATURES DERIVED FROM A DISTANCE TRANSFORM. 2012. Paper presented at International Conference of Agricultural Engineering, Valencia, Spain.