4 Citations (Scopus)
57 Downloads (Pure)


We present an application that demonstrates a proof of concept system for automated in-the-field monitoring of disease in wheat crops. Such in-situ applications are required to be robust in the presence of clutter, provide rapid and accurate analysis and are able to operate at scale. We propose a processing pipeline that detects key wheat diseases in cluttered field imagery. First, we describe and evaluate a high dimensional texture descriptor combined with a randomised forest approach for automated primary leaf recognition. Second, we show that a combined nearest neighbour classifier and voting system applied to segmented leaf regions can robustly determine the presence and type of disease. The system has been tested on a real-world database of images of wheat leaves captured in-the-field using a standard smart phone.
Original languageEnglish
Title of host publication2015 IEEE International Conference on Image Processing (ICIP 2015)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages5
ISBN (Electronic)9781479983391
ISBN (Print)9781479983407
Publication statusE-pub ahead of print - 27 Sep 2015
EventInternational Conference on Image processing 2015 (ICIP 2015) - QUebec, Canada
Duration: 27 Sep 201530 Sep 2015


ConferenceInternational Conference on Image processing 2015 (ICIP 2015)


  • ecological informatics
  • log-Gabor filter
  • randomised forests
  • nearest neighbour voting

Fingerprint Dive into the research topics of 'Towards automating visual in-field monitoring of crop health'. Together they form a unique fingerprint.

Cite this