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.
|Number of pages||1|
|Publication status||Published - 25 May 2021|
|Event||13th EFITA International Conference - |
Duration: 25 May 2021 → 26 May 2021
|Conference||13th EFITA International Conference|
|Period||25/05/21 → 26/05/21|