FreeAIRepo
Vision & OCR

fh2019ustc/DocTr

The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.

Python
Stars
445
Forks
59
Open issues
17
Last push
3mo ago

About DocTr

DocTr is a free, open-source computer vision tool by fh2019ustc, written mainly in Python. The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021. It has 445 GitHub stars and 59 forks, and was last updated 3mo ago. GitHub doesn't detect a standard license, so check the repository before using it commercially.

License
Not detected
Language
Python
Stars
445
Last update
3mo ago
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not stated
Self-hostable
Not stated

Similar free tools

All Vision & OCR tools →

DocTr FAQ

Is DocTr free?

Yes. DocTr is open source and free to use. GitHub doesn't detect a standard license, so check the repository before using it commercially.

Does DocTr run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does DocTr need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is DocTr still maintained?

It was last updated 3mo ago. Check recent issues on GitHub to judge how active it is.

What are alternatives to DocTr?

Similar free, open-source tools include PaddleOCR, Umi-OCR, tesseract, liteparse.

Related topics