HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Lite CNN Models for Real-Time Post-Harvest Grape Disease Detection

Abstract : Post-harvest fruit grading is a necessary step to avoid disease related loss in quality. In this paper, a hierarchical method is proposed to (1) remove the background and (2) detect images that contains grape diseases(botrytis, oidium, acid rot). Satisfying segmentation performances were obtained by the proposed Lite Unet model with 92.9% IoU score and an average speed of 0.16s/image. A pretrained MobileNet-V2 model obtained 94% F1 score on disease classification. An optimized CNN reached a score of 89% with less than 10 times less parameters. The implementation of both segmentation and classification models on low-powered device would allow for real-time disease detection at the press.
Complete list of metadata

Contributor : Luiz Angelo Steffenel Connect in order to contact the contributor
Submitted on : Wednesday, April 20, 2022 - 6:37:24 PM
Last modification on : Tuesday, April 26, 2022 - 3:37:04 AM


EAISA2022_paper_6 (1).pdf
Files produced by the author(s)


  • HAL Id : hal-03647740, version 1



Lucas Mohimont, François Alin, Nathalie Gaveau, Luiz Angelo Steffenel. Lite CNN Models for Real-Time Post-Harvest Grape Disease Detection. Workshop on Edge AI for Smart Agriculture (EAISA 2022), Jun 2022, Biarritz, France. ⟨hal-03647740⟩



Record views


Files downloads