This is my graduate project. Although I don't think it's useful, it's still a good learning material for OPENCV.
This project try to retify the qr code on cylinder surface, so that normal scanner could recognize the distorted qr code. However, there are still many problems here. I may fix them in the future.
System: Ubuntu 16.04
Building Step:
sudo apt install -y qt5-default qtcreator cmake cmake-gui
sudo apt install -y build-essential libgtk2.0-dev libavcodec-dev
sudo apt install -y libavformat-dev libjpeg.dev libtiff4.dev libswscale-dev libjasper-dev
cd cylinder_qrcode/opencv
tar -Jxvf opencv-3.4.1.tar.xz -C .
mkdir opencv_build
cd opencv_build
cmake -D CMAKE_BUILD_TYPE=Release -D CMAKE_INSTALL_PREFIX=/usr/local ../opencv-3.4.1
make -j4
sudo make install
Then the opencv3 and qt5 would be installed in your system successfully. After installing the requirements, cd to the source directory to build the source code:
cd cylinder_qrcode/src
qmake
make
./cylinder
You would see the following simple qt GUI now:
Click Browse to select qr code picture in cylinder_qrcode/datas, and press run, then the result may be:
The result picture may not seen to be great sometimes, so you may need to change the following parameters to get better result:
- Blur Block Size
- Thresh Block Size
- Thresh Block Delta
Detail documentation could be found in: https://gitee.com/fsfzp888/cylinder_qrcode/tree/master/docs
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。