Publication

Hyper-spectral frequency selection for the classification of vegetation diseases

Dijkstra, K., van de Loosdrecht, J., Schomaker, L. & Wiering, M., 28-Apr-2017, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 2017 ed. Bruges (Belgium): ESANN, p. 483-488 6 p.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Reducing the use of pesticides by early visual detection of diseases in precision agriculture is important. Because of the color similarity between potato-plant diseases, narrow band hyper-spectral imaging is required. Payload constraints on unmanned aerial vehicles require reduction of spectral bands. Therefore, we present a methodology for per-patch classification combined with hyper-spectral band selection. In controlled experiments performed on a set of individual leaves, we measure the performance of five classifiers and three dimensionality-reduction methods with three patch sizes. With the best-performing classifier an error rate of 1.5% is achieved for distinguishing two important potato-plant diseases
Original languageEnglish
Title of host publicationEuropean Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Place of PublicationBruges (Belgium)
PublisherESANN
Pages483-488
Number of pages6
Edition2017
ISBN (Print)978-287587039-1
Publication statusPublished - 28-Apr-2017
EventESANN 2017 - 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - Bruges, Belgium
Duration: 26-Apr-201728-Nov-2017

Conference

ConferenceESANN 2017 - 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
CountryBelgium
CityBruges
Period26/04/201728/11/2017

Event

ESANN 2017 - 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

26/04/201728/11/2017

Bruges, Belgium

Event: Conference

    Keywords

  • Machine Learning, Computer Vision, Hyper-spectral

View graph of relations

Download statistics

No data available

ID: 41744145