Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Automatic detection of nodules in legumes by imagery in a phenotyping context

Abstract : Plant Phenotyping consists in characterizing their morphometric pa-rameters which allows correlating them to genotype expression, modulated by their environment. Particularly, nutrition and environment of plants impact significantly roots and symbiotic nodules growths. Under conditions of low mineral nitrogen in soil, legumes have the ability to fix atmospheric nitrogen symbiotically in nodules which are organs formed on the roots of the host plant. The observation of nodules and the evaluation of their characteristics are quite difficult manually, and commercial software provide currently time consuming and no accurate results. This paper proposes a fast and automated image processing technique using the skeletonization technique to determine very accurately nodule parameters, such as their number, location and size on the primary root. The results obtained will be used for the determination of other root parameters including dynamic follow of root architecture.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

https://hal.inrae.fr/hal-02741403
Déposant : Migration Prodinra <>
Soumis le : mercredi 3 juin 2020 - 01:26:57
Dernière modification le : mardi 7 juillet 2020 - 11:46:03

Identifiants

Citation

Simeng Han, Frédéric Cointault, Christophe Salon, Jean-Claude Simon. Automatic detection of nodules in legumes by imagery in a phenotyping context. 16. International Conference on Computer Analysis of Images and Patterns (CAIP 2015), Sep 2015, Valletta, Malta. ⟨10.1007/978-3-319-23117-4_12⟩. ⟨hal-02741403⟩

Partager

Métriques

Consultations de la notice

19