Crop conditional Convolutional Neural Networks for massive multi-crop plant disease classification over cell phone acquired images taken on real field conditions

dc.contributor.authorPicon, Artzai
dc.contributor.authorSeitz, Maximiliam
dc.contributor.authorAlvarez-Gila, Aitor
dc.contributor.authorMohnke, Patrick
dc.contributor.authorOrtiz-Barredo, Amaia
dc.contributor.authorEchazarra, Jone
dc.contributor.institutionTecnalia Research & Innovation
dc.contributor.institutionCOMPUTER_VISION
dc.contributor.institutionVISUAL
dc.date.issued2019-12
dc.descriptionPublisher Copyright: © 2019 Elsevier B.V.
dc.description.abstractConvolutional Neural Networks (CNN) have demonstrated their capabilities on the agronomical field, especially for plant visual symptoms assessment. As these models grow both in the number of training images and in the number of supported crops and diseases, there exist the dichotomy of (1) generating smaller models for specific crop or, (2) to generate a unique multi-crop model in a much more complex task (especially at early disease stages) but with the benefit of the entire multiple crop image dataset variability to enrich image feature description learning. In this work we first introduce a challenging dataset of more than one hundred-thousand images taken by cell phone in real field wild conditions. This dataset contains almost equally distributed disease stages of seventeen diseases and five crops (wheat, barley, corn, rice and rape-seed) where several diseases can be present on the same picture. When applying existing state of the art deep neural network methods to validate the two hypothesised approaches, we obtained a balanced accuracy (BAC=0.92) when generating the smaller crop specific models and a balanced accuracy (BAC=0.93) when generating a single multi-crop model. In this work, we propose three different CNN architectures that incorporate contextual non-image meta-data such as crop information onto an image based Convolutional Neural Network. This combines the advantages of simultaneously learning from the entire multi-crop dataset while reducing the complexity of the disease classification tasks. The crop-conditional plant disease classification network that incorporates the contextual information by concatenation at the embedding vector level obtains a balanced accuracy of 0.98 improving all previous methods and removing 71% of the miss-classifications of the former methods.en
dc.description.statusPeer reviewed
dc.format.extent1
dc.format.extent2570400
dc.identifier.citationPicon , A , Seitz , M , Alvarez-Gila , A , Mohnke , P , Ortiz-Barredo , A & Echazarra , J 2019 , ' Crop conditional Convolutional Neural Networks for massive multi-crop plant disease classification over cell phone acquired images taken on real field conditions ' , Computers and Electronics in Agriculture , vol. 167 , 105093 , pp. 105093 . https://doi.org/10.1016/j.compag.2019.105093
dc.identifier.doi10.1016/j.compag.2019.105093
dc.identifier.issn0168-1699
dc.identifier.otherresearchoutputwizard: 11556/904
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85075749603&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofComputers and Electronics in Agriculture
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subject.keywordsConvolutional neural network
dc.subject.keywordsDeep learning
dc.subject.keywordsContextual meta-data
dc.subject.keywordsContextual meta-data conditional neural network
dc.subject.keywordsCrop protection
dc.subject.keywordsMulti-label classification
dc.subject.keywordsMulti-crop classification
dc.subject.keywordsImage processing
dc.subject.keywordsPlant disease
dc.subject.keywordsEarly pest
dc.subject.keywordsDisease identification
dc.subject.keywordsPrecision agriculture
dc.subject.keywordsPhyto-pathology
dc.subject.keywordsConvolutional neural network
dc.subject.keywordsDeep learning
dc.subject.keywordsContextual meta-data
dc.subject.keywordsContextual meta-data conditional neural network
dc.subject.keywordsCrop protection
dc.subject.keywordsMulti-label classification
dc.subject.keywordsMulti-crop classification
dc.subject.keywordsImage processing
dc.subject.keywordsPlant disease
dc.subject.keywordsEarly pest
dc.subject.keywordsDisease identification
dc.subject.keywordsPrecision agriculture
dc.subject.keywordsPhyto-pathology
dc.subject.keywordsForestry
dc.subject.keywordsAgronomy and Crop Science
dc.subject.keywordsComputer Science Applications
dc.subject.keywordsHorticulture
dc.subject.keywordsSDG 2 - Zero Hunger
dc.titleCrop conditional Convolutional Neural Networks for massive multi-crop plant disease classification over cell phone acquired images taken on real field conditionsen
dc.typejournal article
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
1-s2.0-S0168169919309329-main.pdf
Size:
2.45 MB
Format:
Adobe Portable Document Format