Datasets on plant diseases, pests detection & miscellaneous

[cmbadgujar10]

• PlantVillage-Dataset : https://github.com/spMohanty/PlantVillage-Dataset
• Rice Leaf Diseases Dataset : https://archive.ics.uci.edu/ml/datasets/Rice+Leaf+Diseases
• Plant Disease Symptoms : https://www.digipathos-rep.cnptia.embrapa.br/
• Plant Diseases Dataset : https://www.kaggle.com/vipoooool/new-plant-diseases-dataset/
• PlantVillage dataset : https://github.com/MarkoArsenovic/DeepLearning_PlantDiseases
• Northern leaf blight : https://osf.io/p67rz/
• Insects : http://www.nbair.res.in/insectpests/pestsearch.php
• Crop : http://www.icgroupcas.cn/website_bchtk/index.html
• PlantDoc dataset : https://github.com/pratikkayal/PlantDoc-Object-Detection-Dataset
• Northern Leaf Blight (NLB) dataset for Maize : https://bisque.cyverse.org/client_service/browser?resource=/data_service/dataset
• Apple leaf disease : https://www.kaggle.com/c/plantpathology-2020-fgvc7
• Insect Pest Recognition : https://github.com/xpwu95/IP102
• Tomato pest: https://data.mendeley.com/datasets/s62zm6djd2/1
• LEM+ dataset: https://doi.org/10.1016/j.dib.2020.106553
• Soybean images dataset: https://doi.org/10.1016/j.dib.2021.107756
• fortunella margarita images : https://doi.org/10.1016/j.dib.2021.107293
• Vegetable crops early stage of growth : https://doi.org/10.1016/j.dib.2022.108035
• Pomegranate fruits: https://doi.org/10.1016/j.dib.2021.107249
• Food crops and weed images: https://doi.org/10.1016/j.dib.2020.105833
• FruitNet: Indian fruits image dataset: https://doi.org/10.1016/j.dib.2021.107686
• Fuji apple: https://doi.org/10.1016/j.dib.2021.107629
• Soybean seed data: https://doi.org/10.1016/j.dib.2018.12.090
• Cassava whitefly count: https://doi.org/10.1016/j.dib.2022.107911
• Downy mildew symptoms on Merlot grape variety: https://doi.org/10.1016/j.dib.2021.107250
• Chinese medicinal blossoms: https://doi.org/10.1016/j.dib.2021.107655
• Arabica coffee leaf images dataset: https://doi.org/10.1016/j.dib.2021.107142
• Dataset of necrotized cassava root: https://doi.org/10.1016/j.dib.2020.106170
• Medjool dates: https://doi.org/10.1016/j.dib.2021.107116

[amogh7joshi]

Hi Chetan and thanks for the addition of the dataset information.

These datasets would be fantastic as a contribution to AgML. Right off the bat, I can see that we already have some of them (PlantVillage, PlantDoc, Fuji Apple, Soybean, and perhaps some more which I haven't checked out in detail).

If you (or any other contributor) would like to begin adding these datasets, why don't you add a comment on this threat with the link to it so I can verify that it would be a new contribution and the work doesn't go to waste. This will help grow AgML without creating duplicate datasets.

Thanks for the contribution!

[andreaceruti]

Hi @amogh7joshi there is a dataset on grape bunches avaliable here. It is both on object detection and instance segmentation. I have taken the images with instance mask and translated their annotation in JSON annotation as your standard. You can see the COCO annotations on my repo.
Also for the other images with annotations for object detection only, I have seen that someone translated the WGISD annotations in Pascal VOC standard (XML) so it should be not so difficult to adapt them in JSON.

[amogh7joshi]

@andreaceruti, thanks for the information! We've actually been looking into the WGISD dataset, so this is super useful. If you could make a new pull request with metadata for the dataset that would also be super helpful. I'll be updating a CONTRIBUTING.md file on the main branch of the repository later today, which should detail exactly how you can go about adding the metadata.

Edit: The contributing guidelines have been added, see the CONTRIBUTING.md file.

Let me know if you have any questions.

[masonearles]

@andreaceruti @amogh7joshi @BadChetan19 Were you able to upload these datasets into AgML?

More generally, the question of dataset contributions is a hugely important one for building the AgML community. Please join the conversation at Issue #33

[ctyeong]

@cmbadgujar10 Please also add "Riseholme-2021 Dataset": https://github.com/ctyeong/Riseholme-2021

[amogh7joshi]

Hi @ctyeong, this dataset has been added to AgML and will be released with it in the latest version soon.