| microsoft/ailab |
7,515 |
|
0 |
0 |
almost 3 years ago |
0 |
|
83 |
mit |
C# |
| Experience, Learn and Code the latest breakthrough innovations with Microsoft AI |
| clovaai/donut |
4,651 |
|
0 |
0 |
over 2 years ago |
10 |
November 14, 2022 |
157 |
mit |
Python |
| Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022 |
| Layout-Parser/layout-parser |
4,107 |
|
0 |
4 |
over 2 years ago |
11 |
April 06, 2022 |
100 |
apache-2.0 |
Python |
| A Unified Toolkit for Deep Learning Based Document Image Analysis |
| dmMaze/BallonsTranslator |
1,730 |
|
0 |
0 |
about 2 years ago |
0 |
|
76 |
gpl-3.0 |
Python |
| 深度学习辅助漫画翻译工具, 支持一键机翻和简单的图像/文本编辑 | Yet another computer-aided comic/manga translation tool powered by deeplearning |
| bgshih/crnn |
1,670 |
|
0 |
0 |
about 7 years ago |
0 |
|
85 |
mit |
Lua |
| Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition. |
| kha-white/manga-ocr |
1,172 |
|
0 |
3 |
over 2 years ago |
12 |
August 27, 2023 |
17 |
apache-2.0 |
Python |
| Optical character recognition for Japanese text, with the main focus being Japanese manga |
| bgshih/aster |
628 |
|
0 |
0 |
about 5 years ago |
0 |
|
77 |
mit |
Python |
| Recognizing cropped text in natural images. |
| robertknight/ocrs |
568 |
|
0 |
0 |
about 2 years ago |
0 |
|
6 |
apache-2.0 |
Rust |
| A modern OCR engine (extracts text from images), written in Rust |
| AlibabaResearch/AdvancedLiterateMachinery |
464 |
|
0 |
0 |
over 2 years ago |
0 |
|
41 |
apache-2.0 |
C++ |
| A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Alibaba DAMO Academy. |
| baudm/parseq |
429 |
|
0 |
0 |
over 2 years ago |
0 |
|
34 |
apache-2.0 |
Python |
| Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022) |
