YongWookHa/swin-transformer-ocr

swin-transformer custom for OCR

44
/ 100
Emerging

This project helps you accurately convert handwritten or printed text from images into digital text. You provide cropped images, each containing a word or sentence, along with their corresponding text labels for training. The output is a highly accurate text transcription of new images. It's ideal for developers or researchers building custom OCR solutions, especially for specific handwriting styles or unique fonts.

117 stars. No commits in the last 6 months.

Use this if you need to train a robust Optical Character Recognition (OCR) model on your own dataset of images with text, especially for specialized fonts or handwriting.

Not ideal if you're looking for a ready-to-use OCR application for general document scanning without custom training.

handwritten-text-recognition document-digitization custom-ocr image-to-text computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

117

Forks

20

Language

Python

License

MIT

Category

latex-ocr-tools

Last pushed

Feb 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YongWookHa/swin-transformer-ocr"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.