Semantic Segmentation of Tomato Sepals on Hyperspectral Images Using Deep Learning

Zeljana Grbovic, Milica Brkic, Marko Panic, Sanja Brdar, E.M. Hogeveen-van Echtelt, A. Chauhan

Research output: Contribution to conferenceAbstract

Abstract

The segmentation of tomato sepals from hyperspectral images is a crucial step in designing an automated system for sensitivity assessment of tomato to fungal infection with minimal human intervention. Achieving highly precise segmentation of the sepal tips can drastically improve the precision of predictive models for the early assessment of risk on undesired fungal growth. In this study, we investigate the state-of-the-art deep learning architectures to identify which architecture provides the most precise segmentation of tomato sepals from hyperspectral images.
Original languageEnglish
Pages27
Number of pages1
Publication statusPublished - 25 May 2021
Event13th EFITA International Conference -
Duration: 25 May 202126 May 2021

Conference

Conference13th EFITA International Conference
Period25/05/2126/05/21

Fingerprint

Dive into the research topics of 'Semantic Segmentation of Tomato Sepals on Hyperspectral Images Using Deep Learning'. Together they form a unique fingerprint.

Cite this