Dataset · hezarai
Persian license plate recognition
hezarai/persian-license-plate-v1
Labeled dataset of Persian license plate images and text for OCR tasks.
What's inside
Contains 1K to 10K pairs of Persian license plate images and their text transcripts (Farsi). Provided by Amirkabir University of Technology, labeled by the authors, and split into train, validation, and test sets.
What you can do with it
- Training and fine-tuning OCR models for Persian license plate characters
- Testing automated number plate recognition (ANPR) systems
- Building image-to-text pipelines for specific fonts and alphabets
- Tasks
- Image → text
- Languages
- Persian
- Size
- 1K–10K rows
- Downloads this month
- 777
- Likes
- 13
Models trained on it
How to load it
from datasets import load_dataset
ds = load_dataset("hezarai/persian-license-plate-v1")