Text-Detection-Recognition

setup

If you want to run evaluation on COCO-Text dataset, download and unizip train2014.zip to ./COCO directory.
Then run the following script.

python eval_on_coco_text.py

If you just want ocr on images, run ctpn_crnn_pytorch.py.
PyTorch version of CRNN yields much better result than Tensorflow version.

python ctpn_crnn_pytorch.py

For implementation detail or experiment results, refer to the report.

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
COCO		COCO
CRNN_Tensorflow @ b06b4d3		CRNN_Tensorflow @ b06b4d3
crnn.pytorch @ c00c6d9		crnn.pytorch @ c00c6d9
ocr_data		ocr_data
ocr_result		ocr_result
text-detection-ctpn @ af07bd2		text-detection-ctpn @ af07bd2
.gitattributes		.gitattributes
.gitignore		.gitignore
.gitmodules		.gitmodules
20180624_Text-Detection-Recognition.pdf		20180624_Text-Detection-Recognition.pdf
LICENSE		LICENSE
README.md		README.md
ctpn_crnn_pytorch.py		ctpn_crnn_pytorch.py
ctpn_crnn_tensorflow.py		ctpn_crnn_tensorflow.py
dummy.py		dummy.py
eval_on_coco_text.py		eval_on_coco_text.py