← Search

Data · dataset · 2025

CocoaSwolSet

Listed in Teesside University Research Data Repository

Description

This dataset is part of the Deep Farm project (deepfarm.eu/), funded by the European Union's ERASMUS program, which aims to bridge the skills gap and build the capacity of students and teachers in digital agriculture through the use of Artificial Intelligence (AI), Big Data, and the Internet of Things (IoT). One of the pilot projects is Deep Cacao, led in Côte d'Ivoire by ESATIC and INPHB. This project involves implementing an AI model based on neural networks to detect and prevent Swollen Shoot disease, one of the greatest threats to cocoa cultivation in Côte d'Ivoire, as early as possible.

To this end, our team has been working on setting up the CocoaSwolSet dataset. CocoaSwolSet is a dataset of images of cocoa leaves, pods, and stems. This dataset is intended to feed AI models for the early detection of one of the most devastating diseases affecting cocoa, namely Swollen Shoot Disease.

Read the rest (2 more)

It therefore consists of images of healthy cocoa plants (currently approximately 1,500 images) and images of diseased cocoa plants (currently approximately 1,000 images). The CocoaSwolSet folder contains three subfolders: "Leaves," "Stems," and "Pods." With the exception of the Leaves subfolder, the other two folders contain "Healthy" and "Diseased" folders. For the Leaves subfolder, we have the Young and Adult folders, which contain the Healthy and Diseased folders.

It should be noted that this dataset will be constantly updated as we continue to collect images of different plants. However, at this stage, we can train initial AI models for the detection of swollen shoot disease. This dataset is one of the first datasets on swollen shoot disease and is a valuable resource for training AI models in the classification or detection of the disease.

Links

Where it is published

Catalogue records · 1

Topics

Inferred from text
Disease 75% · Image 65%
Provenance · 1 source records, 8 field assertions
SourceKeyLast seenRaw
Teesside University Research Data Repositoryoai:data.mendeley.com/hvwth9dsfd.215 h agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
concepts[disease].local:disease:diseaseenrichment · researchdata tees ac ukkeyword-concept-rules@1.0.0title+description (75%)
concepts[field].local:field:earth-environmentalmapping · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
concepts[modality].local:modality:imageenrichment · researchdata tees ac ukkeyword-concept-rules@1.0.0title+description (65%)
descriptionsource · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0/metadata/dc/description
licensesource · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0/metadata/dc/rights
publication_datesource · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
titlesource · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0/metadata/dc/title