https://link.springer.com/content/pdf/10.1007/s11831-018-9266-3.pdf

1. The Swedish Leaf Dataset (Soderkvist et al.) : The dataset contains scanned images of 15 tree species with 75 leaves per species, against a plain background.
2. The Flavia Dataset : 1907 leaf images of 32 different species and 50–77 images per species. The leaves were collected from 32 common plants in the Yangtze Delta (where Shanghai is) of China.
3. The ICL dataset : Isolated leaf images of 220 plant species, with individual images ranging from 26 to 1078 per species.
4. The UCI Machine Repository (Pedro et al.) : 340 species, each with 10 leaves.
5. The Austrian Federal Forest Dataset : 134 leaf photos of Austrian 5 broad trees with the plain background.
6. The Smithsonian Leaf Dataset : 343 leaves from 93 species.
7. Leaf Snap Dataset : high-quality images taken of pressed leaves from the Smithsonian collection. 7719 Field images consist of ‘‘typical’’ images taken by mobile devices (mostly iPhones) in outdoor environments. These images contain varying amounts of blur, noise, illumination patterns, and shadows.
8. The Middle European Wood Database : for experiments to do with the recognition of woods by shape of their leaves.
9. PlantNet : wild plant species collected from Western Europe and North America and contains 10,000 plant species.
10. A Database of Leaf Images: Practice towards Plant Conservation with Plant Pathology https://data.mendeley.com/datasets/hb74ynkjcn/1 :Tensorflow's public data https://knowyourdata-tfds.withgoogle.com/#tab=STATS&dataset=plant_leaves

Leaf-dieses Dataset

https://www.kaggle.com/vipoooool/new-plant-diseases-dataset

https://www.kaggle.com/emmarex/plantdisease