人脸识别引擎SeetaFace编译 ubuntu

00.SeetaFace简介

SeetaFace Engine is an open source C++ face recognition engine, which can run on CPU with no third-party dependence. It contains three key parts, i.e., SeetaFace Detection, SeetaFace Alignment and SeetaFace Identification, which are necessary and sufficient for building a real-world face recognition applicaiton system.

01.下载SeetaFace

git clone https://github.com/seetaface/SeetaFaceEngine.git

02.安装依赖

安装opencv2

源码编译安装或者sudo apt-get install libopencv-dev

03.工具

构建工具CMake 3.1.0 or higher is required.

而ubuntu官方源版本太低

sudo add-apt-repository ppa:george-edison55/cmake-3.x
sudo apt-get update
sudo apt-get install cmake

（可选）解压工具

sudo apt-get install unrar

04.编译

cd FaceDetection;mkdir build;cd build;
cmake ..; make -j${npoc}

同样方式编译FaceAlignment与FaceIdentification

编译FaceAlignment时报错：

缺face_detection.h，无法连接seeta_facedet_lib

解决：从FaceDetection中拷贝

编译FaceIdentification时报错：

1.缺失face_detection.h与face_alignment.h

将FaceDetection与FaceAlignment include文件夹下的对应文件硬链接（或拷贝，不要用软链接可能找不到）到FaceIdentification include

2.test_face_verification.cpp.o对许多函数未定义的引用

修改src/test/CMakeLists.txt文件，增加编译时对于前面两个库的引用

将之前生成的libseeta_facedet_lib,libseeta_fa_lib硬链接build文件夹中，然后在CMakeLists.txt文件中添加下面一行，表明在build文件夹下查找链接库

link_directories(${PROJECT_BINARY_DIR})

在循环中的语句target_link_libraries(${BIN} viplnet ${OpenCV_LIBS})中添加两个库：

target_link_libraries(${BIN} viplnet ${OpenCV_LIBS} seeta_facedet_lib seeta_fa_lib)

3.model/seeta_fr_v1.0.bin not found ：解压缩model中的两个文件

unrar  x  seeta_fr_v1.0.part1.rar  #合并压缩只需指定第一部分

05.测试

test程序（facedet_test、fa_test、src/test/test_face_recognizer.bin、src/test/test_face_verification.bin）

运行时段错误，修改test代码中文件的路径或改成传参的形式，或者将所需的文件硬链接到正确的文件夹。