Deep Mangoes: from fruit detection to cultivar identification in colour images of mango trees

Abstract : This paper presents results on the detection and identification mango fruits from colour images of trees. We evaluate the behaviour and the performances of the Faster R-CNN network to determine whether it is robust enough to "detect and classify" fruits under particularly heterogeneous conditions in terms of plant cultivars, plantation scheme, and visual information acquisition contexts. The network is trained to distinguish the 'Kent', 'Keitt', and 'Boucodiekhal' mango cultivars from 3,000 representative labelled fruit annotations. The validation set composed of about 7,000 annotations was then tested with a confidence threshold of 0.7 and a Non-Maximal-Suppression threshold of 0.25. With a F1-score of 0.90, the Faster R-CNN is well suitable to the simple fruit detection in tiles of 500x500 pixels. We then combine a multi-tiling approach with a Jaccard matrix to merge the different parts of objects detected several times, and thus report the detections made at the tile scale to the native 6,000x4,000 pixel size images. Nonetheless with a F1-score of 0.56, the cultivar identification Faster R-CNN network presents some limitations for simultaneously detecting the mango fruits and identifying their respective cultivars. Despite the proven errors in fruit detection, the cultivar identification rates of the detected mango fruits are in the order of 80%. The ideal solution could combine a Mask R-CNN for the image pre-segmentation of trees and a double-stream Faster R-CNN for detecting the mango fruits and identifying their respective cultivar to provide predictions more relevant to users' expectations.
Liste complète des métadonnées

Littérature citée [37 références]  Voir  Masquer  Télécharger

https://hal.umontpellier.fr/hal-02295256
Contributeur : Frédéric Borne <>
Soumis le : mardi 24 septembre 2019 - 09:57:40
Dernière modification le : jeudi 26 septembre 2019 - 01:13:32

Fichier

DISP 19 deepmango-3.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-02295256, version 1
  • ARXIV : 1909.10939

Citation

Philippe Borianne, Frederic Borne, Julien Sarron, Emile Faye. Deep Mangoes: from fruit detection to cultivar identification in colour images of mango trees. DISP'19 - International Conference on Digital Image and Signal Processing, Apr 2019, Oxford, United Kingdom. ⟨hal-02295256⟩

Partager

Métriques

Consultations de la notice

35

Téléchargements de fichiers

18