deep ocr

See README_en.md for English installation documentation.

ubuntuvirtualenv

git clone https://github.com/JinpengLI/deep_ocr.git ~/deep_ocr
virtualenv ~/deep_ocr_env
source ~/deep_ocr_env/bin/activate
pip install -r ~/deep_ocr/requirements.txt
cd ~/deep_ocr && python setup.py install

source ~/deep_ocr_env/bin/activate && cd ~/deep_ocr && ./bin/deep_ocr_reco data/holiday_notification.jpg -v -d

.

tesseract

$ tesseract -l chi_sim data/test_data.png out_test_data

 v 3 (T) T ' 2t
 v (2) T '2'L (3) 
:v () v

reco_chars.pycaffetesseract

$ python reco_chars.py

caffe

Deep Convolutional Network for Handwritten Chinese Character Recognition

http://yuhao.im/files/Zhang_CNNChar.pdf

Docker

dockerUbuntu 14.04

https://www.docker.com/

deep_ocr_workspace.zip (https://pan.baidu.com/s/1nvz2wrB https://pan.baidu.com/s/1qYPKH3Y )

md5sum

$ md5sum deep_ocr_workspace.zip
ffeda7ea6604e7b8835c05a33fa0459e  deep_ocr_workspace.zip
$ md5sum deep_ocr_workspace.z01
ea66796c2bbdb2bec9b7ee28eb44012d  deep_ocr_workspace.z01

(~/deep_ocr_workspace)

cat deep_ocr_workspace.z* > unsplit_deep_ocr_workspace.zip
unzip unsplit_deep_ocr_workspace.zip -d ~/

zipdeep_ocr ~/deep_ocr_workspace

cpu

docker pull jinpengli/deep_ocr_cpu_docker:latest

docker container

docker run -ti --volume=${HOME}/deep_ocr_workspace:/workspace jinpengli/deep_ocr_cpu_docker:latest /bin/bash
cd /opt/deep_ocr
git pull origin master

volumemountcontainer

python /opt/deep_ocr/reco_chars.py

========

export WORKSPACE=/workspace
deep_ocr_id_card_reco --img $DEEP_OCR_ROOT/data/id_card_img.jpg             --debug_path /tmp/debug             --cls_sim ${WORKSPACE}/data/chongdata_caffe_cn_sim_digits_64_64             --cls_ua ${WORKSPACE}/data/chongdata_train_ualpha_digits_64_64

...
ocr res:
============================================================
name

============================================================
address
4

============================================================
month
12
============================================================
minzu

============================================================
year
1654
============================================================
sex

============================================================
id
1X21441114X221243X
============================================================
day
20