Sierkinhane / Crnn_chinese_characters_rec
(CRNN) Chinese Characters Recognition.
Stars: ✭ 1,259
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Crnn chinese characters rec
Handwriting Ocr
OCR software for recognition of handwritten text
Stars: ✭ 411 (-67.36%)
Mutual labels: recognition, ocr
Deep Text Recognition Benchmark
Text recognition (optical character recognition) with deep learning methods.
Stars: ✭ 2,665 (+111.68%)
Mutual labels: recognition, ocr
Aster
Recognizing cropped text in natural images.
Stars: ✭ 626 (-50.28%)
Mutual labels: recognition, ocr
Korean-OCR-Model-Design-based-on-Keras-CNN
Korean OCR Model Design(한글 OCR 모델 설계)
Stars: ✭ 34 (-97.3%)
Mutual labels: ocr, recognition
Cnn lstm ctc ocr for icpr
Forked from weinman/cnn_lstm_ctc_ocr for the ICPR MTWI 2018 challenge 1
Stars: ✭ 62 (-95.08%)
Mutual labels: recognition, ocr
Php Apache Tika
Apache Tika bindings for PHP: extract text and metadata from documents, images and other formats
Stars: ✭ 76 (-93.96%)
Mutual labels: ocr
Dbnet Lite.pytorch
A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization
Stars: ✭ 69 (-94.52%)
Mutual labels: ocr
Epic Kitchens 55 Action Models
EPIC-KITCHENS-55 baselines for Action Recognition
Stars: ✭ 68 (-94.6%)
Mutual labels: recognition
Ccpd
[ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition
Stars: ✭ 1,252 (-0.56%)
Mutual labels: recognition
Vokaturiandroid
Emotion recognition by speech in android.
Stars: ✭ 79 (-93.73%)
Mutual labels: recognition
Sar tf
This is an implementation of Show, Attend and Read with tensorflow
Stars: ✭ 70 (-94.44%)
Mutual labels: ocr
Ctpn
Detecting Text in Natural Image with Connectionist Text Proposal Network (ECCV'16)
Stars: ✭ 1,220 (-3.1%)
Mutual labels: ocr
Crnn With Stn
implement CRNN in Keras with Spatial Transformer Network
Stars: ✭ 83 (-93.41%)
Mutual labels: ocr
Crnn
Convolutional recurrent neural network for scene text recognition or OCR in Keras
Stars: ✭ 68 (-94.6%)
Mutual labels: ocr
Papermerge
Open Source Document Management System for Digital Archives (Scanned Documents)
Stars: ✭ 1,177 (-6.51%)
Mutual labels: ocr
Ai Reading Materials
Some of the ML and DL related reading materials, research papers that I've read
Stars: ✭ 79 (-93.73%)
Mutual labels: ocr
Characters Recognition
A Chinese characters recognition repository based on convolutional recurrent networks.
Performance
Recognize characters in pictures
Dev Environments
- WIN 10 or Ubuntu 16.04
- PyTorch 1.2.0 (may fix ctc loss) with cuda 10.0 🔥
- yaml
- easydict
- tensorboardX
Data
Synthetic Chinese String Dataset
- Download the dataset
- Edit lib/config/360CC_config.yaml DATA:ROOT to you image path
DATASET:
ROOT: 'to/your/images/path'
-
Download the labels (password: eaqb)
-
Put char_std_5990.txt in lib/dataset/txt/
-
And put train.txt and test.txt in lib/dataset/txt/
eg. test.txt
20456343_4045240981.jpg 89 201 241 178 19 94 19 22 26 656
20457281_3395886438.jpg 120 1061 2 376 78 249 272 272 120 1061
...
Or your own data
- Edit lib/config/OWN_config.yaml DATA:ROOT to you image path
DATASET:
ROOT: 'to/your/images/path'
-
And put your train_own.txt and test_own.txt in lib/dataset/txt/
eg. test_own.txt
20456343_4045240981.jpg 你好啊!祖国!
20457281_3395886438.jpg 晚安啊!世界!
...
note: fixed-length training is supported. yet you can modify dataloader to support random length training.
Train
[run] python train.py --cfg lib/config/360CC_config.yaml
or [run] python train.py --cfg lib/config/OWN_config.yaml
#### loss curve
```angular2html
[run] cd output/360CC/crnn/xxxx-xx-xx-xx-xx/
[run] tensorboard --logdir log
loss overview(first epoch)
Demo
[run] python demo.py --image_path images/test.png --checkpoint output/checkpoints/mixed_second_finetune_acc_97P7.pth
References
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].