1. Early detection of the fungal disease 'apple scab' using SWIR hyperspectral imaging
- Author
-
Nathalie Gorretta, Ana Herrero, Maroua Nouri, Jean-Michel Roger, Aoife Gowen, Information – Technologies – Analyse Environnementale – Procédés Agricoles (UMR ITAP), Centre international d'études supérieures en sciences agronomiques (Montpellier SupAgro)-Centre national du machinisme agricole, du génie rural, des eaux et forêts (CEMAGREF), Ingénierie des Agro-polymères et Technologies Émergentes (UMR IATE), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-Institut National de la Recherche Agronomique (INRA)-Université Montpellier 2 - Sciences et Techniques (UM2)-Centre international d'études supérieures en sciences agronomiques (Montpellier SupAgro)-Université de Montpellier (UM)-Institut national d’études supérieures agronomiques de Montpellier (Montpellier SupAgro), Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro), and University College Dublin [Dublin] (UCD)
- Subjects
0106 biological sciences ,Veterinary medicine ,Hyperspectral imaging ,biology ,Early detection ,020207 software engineering ,Spectral domain ,02 engineering and technology ,biology.organism_classification ,01 natural sciences ,Disease detection ,Close range ,Fungal disease ,Apple scab ,0202 electrical engineering, electronic engineering, information engineering ,[SDV.BV]Life Sciences [q-bio]/Vegetal Biology ,Spectral analysis ,010606 plant biology & botany - Abstract
International audience; the aim of our study is to examine the potential of SWIR hyperspectral imaging to early detect apple scab infection. Close range hyperspectral images of healthy and infected leaves were acquired daily under laboratory conditions from 2 days to 11 days after inoculation using a push-broom SWIR camera. A PLS-DA classification model was built at the advanced infection stage D11 and was applied on the infected and healthy leaves images acquired at others infection stages. This study showed that good predictions can be achieved when classifying infected leaf regions based on hyperspectral data using PLS-DA. Results suggest that the spectral domain between 1000 - 2500 nm is suited to early differentiation between infected and healthy leaves. At early infection stages, the water absorption band at 1940 nm has the major discriminatory effect
- Published
- 2019
- Full Text
- View/download PDF