Texture and shape attribute selection for plant disease monitoring in a mobile cloud-based environment

Punnarai Siricharoen, Scotney Bryan, Philip Morrow, Gerard Parr

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

1 Citation (Scopus)

Abstract

We focus on feature extraction and selection to best represent texture and shape properties of plant diseases in an image- based leaf monitoring system implemented in a mobile-cloud environment. A number of textural and region-based features are aggregated from previous studies; also we introduce mean and peak indices of histogram-of-shape as disease property representations along with the proposed and enhanced shape features based on diseased regions. A total of 260 colour-based attributes and 163 shape attributes are searched to find the best potential features based on different aspects: probability of feature error, correlation, targeted-class relevancy and the separability quality of a feature. Experimental results show that the best selected feature set which combines colour-based and shape features yields high classification accuracy on wheat disease images captured by a smartphone camera and also provides insights into potential sets of features to be further implemented as a lightweight standalone mobile application.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages489-493
Number of pages5
DOIs
Publication statusPublished - 19 Aug 2016
Event2016 IEEE International Conference on Image Processing (ICIP) - Phoenix, AZ, USA
Duration: 19 Aug 2016 → …

Conference

Conference2016 IEEE International Conference on Image Processing (ICIP)
Period19/08/16 → …

Fingerprint

Textures
Monitoring
Feature extraction
Color
Smartphones
Cameras

Keywords

  • Histogram of shape features
  • textural features
  • feature selection

Cite this

@inproceedings{d662fa38a552470a8066c22946e081a6,
title = "Texture and shape attribute selection for plant disease monitoring in a mobile cloud-based environment",
abstract = "We focus on feature extraction and selection to best represent texture and shape properties of plant diseases in an image- based leaf monitoring system implemented in a mobile-cloud environment. A number of textural and region-based features are aggregated from previous studies; also we introduce mean and peak indices of histogram-of-shape as disease property representations along with the proposed and enhanced shape features based on diseased regions. A total of 260 colour-based attributes and 163 shape attributes are searched to find the best potential features based on different aspects: probability of feature error, correlation, targeted-class relevancy and the separability quality of a feature. Experimental results show that the best selected feature set which combines colour-based and shape features yields high classification accuracy on wheat disease images captured by a smartphone camera and also provides insights into potential sets of features to be further implemented as a lightweight standalone mobile application.",
keywords = "Histogram of shape features, textural features, feature selection",
author = "Punnarai Siricharoen and Scotney Bryan and Philip Morrow and Gerard Parr",
year = "2016",
month = "8",
day = "19",
doi = "10.1109/ICIP.2016.7532405",
language = "English",
isbn = "978-1-4673-9961-6",
pages = "489--493",
booktitle = "Unknown Host Publication",

}

Siricharoen, P, Bryan, S, Morrow, P & Parr, G 2016, Texture and shape attribute selection for plant disease monitoring in a mobile cloud-based environment. in Unknown Host Publication. pp. 489-493, 2016 IEEE International Conference on Image Processing (ICIP), 19/08/16. https://doi.org/10.1109/ICIP.2016.7532405

Texture and shape attribute selection for plant disease monitoring in a mobile cloud-based environment. / Siricharoen, Punnarai; Bryan, Scotney; Morrow, Philip; Parr, Gerard.

Unknown Host Publication. 2016. p. 489-493.

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

TY - GEN

T1 - Texture and shape attribute selection for plant disease monitoring in a mobile cloud-based environment

AU - Siricharoen, Punnarai

AU - Bryan, Scotney

AU - Morrow, Philip

AU - Parr, Gerard

PY - 2016/8/19

Y1 - 2016/8/19

N2 - We focus on feature extraction and selection to best represent texture and shape properties of plant diseases in an image- based leaf monitoring system implemented in a mobile-cloud environment. A number of textural and region-based features are aggregated from previous studies; also we introduce mean and peak indices of histogram-of-shape as disease property representations along with the proposed and enhanced shape features based on diseased regions. A total of 260 colour-based attributes and 163 shape attributes are searched to find the best potential features based on different aspects: probability of feature error, correlation, targeted-class relevancy and the separability quality of a feature. Experimental results show that the best selected feature set which combines colour-based and shape features yields high classification accuracy on wheat disease images captured by a smartphone camera and also provides insights into potential sets of features to be further implemented as a lightweight standalone mobile application.

AB - We focus on feature extraction and selection to best represent texture and shape properties of plant diseases in an image- based leaf monitoring system implemented in a mobile-cloud environment. A number of textural and region-based features are aggregated from previous studies; also we introduce mean and peak indices of histogram-of-shape as disease property representations along with the proposed and enhanced shape features based on diseased regions. A total of 260 colour-based attributes and 163 shape attributes are searched to find the best potential features based on different aspects: probability of feature error, correlation, targeted-class relevancy and the separability quality of a feature. Experimental results show that the best selected feature set which combines colour-based and shape features yields high classification accuracy on wheat disease images captured by a smartphone camera and also provides insights into potential sets of features to be further implemented as a lightweight standalone mobile application.

KW - Histogram of shape features

KW - textural features

KW - feature selection

U2 - 10.1109/ICIP.2016.7532405

DO - 10.1109/ICIP.2016.7532405

M3 - Conference contribution

SN - 978-1-4673-9961-6

SP - 489

EP - 493

BT - Unknown Host Publication

ER -