Solanaceae OCR test set

All Solanaceae preserved specimen images are from GBIF

Description

Please load the file url_taxon_gbifID.csv to obtain the image_url, taxon, gbif_id.
All raw data JSON files in DwC standard have been saved in separate folders with taxon names specified

To run the notebook, please install packages including pytesseract, PIL, and thefuzz

Name		Name	Last commit message	Last commit date
Latest commit History 10 Commits
solanaceae		solanaceae
README.md		README.md
def_ocr.ipynb		def_ocr.ipynb
sample_1.png		sample_1.png
sample_1.txt		sample_1.txt
sample_2.png		sample_2.png
sample_2.txt		sample_2.txt