OAID / Ysqfastfd
Licence: apache-2.0
A fast binary library for face detection and face landmark detection in images. No float point operations, especially suit for low cost Arm CPUs, The highest accuracy on FDDB among non deep learning methods
Stars: ✭ 196
YSQ face detect algorithm demo on ARM (Linux) platform.
Performance on ARM platform
Test on Allwinner R40 (ARM32) and Rockchip RK3399 (ARM64)
Allwinner R40 A7 platform
Rockchip RK3399 A72 platform
Platform preparation :
- ARM32 platform hardware board
- Ubuntu 16.04 with GTK3 library
- USB camera (480P/720P), YUYV
Build
Check the gtk+ devel library is installed
sudo apt install build-essential vim-gtk libgtk-3-0 libgtk-3-dev libegl1-mesa-dev
Build the runtime shared libraries
cd YSQfastfd
make -j4
run the demo
chmod +x ./run.sh
./run.sh
NOTE :
- Type key 'q' to quit the display window.
- Type key 's' to show the landmark info.
- Type key 'p' to save the face picture.
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].