Automated Wheat Disease Classification Under Controlled and Uncontrolled Image Acquisition

Punnarai Siricharoen, Scotney Bryan, Philip Morrow, Gerard Parr

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper presents a practical classification system for recognising diseased wheat leaves and consists of a number of components. Pre-processing is performed to adjust the orientation of the primary leaf in the image using a Fourier Transform. A Wavelet Transform is then applied to partially remove low frequency information or background in the image. Subsequently, the dis- eased regions of the primary leaf are segmented out as blobs using Otsu’s thresholding. The disease blobs are normalised and then radially partitioned into sub-regions (using a Radial Pyramid) representing radial development of many diseases. Finally, global features are computed for different pyramid layers and combined to create a feature descriptor for training a linear SVM classifier. The system is evaluated by classifying three types of wheat leaf disease: non- diseased, Yellow Rust and Septoria. The classification accuracies are slightly over 95% and 79% for images captured under controlled and uncontrolled con- ditions, respectively.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages456-464
Volume9164
DOIs
Publication statusPublished - 4 Jul 2015

Fingerprint

Image acquisition
Wavelet transforms
Fourier transforms
Classifiers
Processing

Keywords

  • Wheat disease recognition
  • radial pyramid
  • rotation using Fourier

Cite this

Siricharoen, Punnarai ; Bryan, Scotney ; Morrow, Philip ; Parr, Gerard. / Automated Wheat Disease Classification Under Controlled and Uncontrolled Image Acquisition. Unknown Host Publication. Vol. 9164 2015. pp. 456-464
@inproceedings{fd0e76e033524bb1ad202f1c4a603692,
title = "Automated Wheat Disease Classification Under Controlled and Uncontrolled Image Acquisition",
abstract = "This paper presents a practical classification system for recognising diseased wheat leaves and consists of a number of components. Pre-processing is performed to adjust the orientation of the primary leaf in the image using a Fourier Transform. A Wavelet Transform is then applied to partially remove low frequency information or background in the image. Subsequently, the dis- eased regions of the primary leaf are segmented out as blobs using Otsu’s thresholding. The disease blobs are normalised and then radially partitioned into sub-regions (using a Radial Pyramid) representing radial development of many diseases. Finally, global features are computed for different pyramid layers and combined to create a feature descriptor for training a linear SVM classifier. The system is evaluated by classifying three types of wheat leaf disease: non- diseased, Yellow Rust and Septoria. The classification accuracies are slightly over 95{\%} and 79{\%} for images captured under controlled and uncontrolled con- ditions, respectively.",
keywords = "Wheat disease recognition, radial pyramid, rotation using Fourier",
author = "Punnarai Siricharoen and Scotney Bryan and Philip Morrow and Gerard Parr",
year = "2015",
month = "7",
day = "4",
doi = "10.1007/978-3-319-20801-5_50",
language = "English",
volume = "9164",
pages = "456--464",
booktitle = "Unknown Host Publication",

}

Automated Wheat Disease Classification Under Controlled and Uncontrolled Image Acquisition. / Siricharoen, Punnarai; Bryan, Scotney; Morrow, Philip; Parr, Gerard.

Unknown Host Publication. Vol. 9164 2015. p. 456-464.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Automated Wheat Disease Classification Under Controlled and Uncontrolled Image Acquisition

AU - Siricharoen, Punnarai

AU - Bryan, Scotney

AU - Morrow, Philip

AU - Parr, Gerard

PY - 2015/7/4

Y1 - 2015/7/4

N2 - This paper presents a practical classification system for recognising diseased wheat leaves and consists of a number of components. Pre-processing is performed to adjust the orientation of the primary leaf in the image using a Fourier Transform. A Wavelet Transform is then applied to partially remove low frequency information or background in the image. Subsequently, the dis- eased regions of the primary leaf are segmented out as blobs using Otsu’s thresholding. The disease blobs are normalised and then radially partitioned into sub-regions (using a Radial Pyramid) representing radial development of many diseases. Finally, global features are computed for different pyramid layers and combined to create a feature descriptor for training a linear SVM classifier. The system is evaluated by classifying three types of wheat leaf disease: non- diseased, Yellow Rust and Septoria. The classification accuracies are slightly over 95% and 79% for images captured under controlled and uncontrolled con- ditions, respectively.

AB - This paper presents a practical classification system for recognising diseased wheat leaves and consists of a number of components. Pre-processing is performed to adjust the orientation of the primary leaf in the image using a Fourier Transform. A Wavelet Transform is then applied to partially remove low frequency information or background in the image. Subsequently, the dis- eased regions of the primary leaf are segmented out as blobs using Otsu’s thresholding. The disease blobs are normalised and then radially partitioned into sub-regions (using a Radial Pyramid) representing radial development of many diseases. Finally, global features are computed for different pyramid layers and combined to create a feature descriptor for training a linear SVM classifier. The system is evaluated by classifying three types of wheat leaf disease: non- diseased, Yellow Rust and Septoria. The classification accuracies are slightly over 95% and 79% for images captured under controlled and uncontrolled con- ditions, respectively.

KW - Wheat disease recognition

KW - radial pyramid

KW - rotation using Fourier

U2 - 10.1007/978-3-319-20801-5_50

DO - 10.1007/978-3-319-20801-5_50

M3 - Conference contribution

VL - 9164

SP - 456

EP - 464

BT - Unknown Host Publication

ER -