源码位置:https://github.com/comhaqs/face_find.git 分支: develop_libfacedetection
之前的人脸检测使用的是opencv的人脸检测功能,识别率低,基本无法使用。网上查找的时候有几个库,一个是MTCNN相关库,使用的是鹅厂的ncnn,不过看issues里是说ncnn只针对arm处理器做了优化,PC端效率低,所以就没有测试。另一个是libfacedetection,纯粹C++编写,故使用了该库,
bool face_recognition::train(unsigned char *p_data, int width, int height){
try {
if(!mp_model || !mp_cascade){
return false;
}
cv::Mat bgr(cv::Size(width, height), CV_8UC3);
bgr.data = p_data;
// DETECT_BUFFER_SIZE为0x20000这个不能改,libfacedetection固定死了
static unsigned char * pBuffer = (unsigned char *)malloc(DETECT_BUFFER_SIZE);
// 这里跟opencv的不同,是使用非灰度图像,不要尝试传灰度图像,不然会识别错误
auto pResults = facedetect_cnn(pBuffer, (unsigned char*)(bgr.ptr(0)), bgr.cols, bgr.rows, (int)bgr.step);
if(nullptr != pResults){
for(int i = 0; i < *pResults; ++i){
short * p = ((short*)(pResults+1))+142*i;
int x = p[0];
int y = p[1];
int w = p[2];
int h = p[3];
int confidence = p[4];
// 这个角度暂时没有使用到
// int angle = p[5];
if(90 > confidence){
continue;
}
cv::Rect r(x,y,w,h);
bool flag_find_face = false;
std::string name;
// 复制出检测出来的人脸,然后转换成灰度图片,不转换会报错
cv::Mat desc;
bgr(r).copyTo(desc);
cv::Mat gray_desc;
gray_desc.create(desc.size(), desc.type());
cv::cvtColor(desc, gray_desc, cv::COLOR_BGR2GRAY);
int index = -1;
double condi = 0.0;
// 实际总会返回一个检测结果,置信度暂时不知道怎么使用
mp_model->predict(gray_desc, index, condi);
if(0 > index){
}else{
auto iter = m_index_to_name.find(index);
if(m_index_to_name.end() == iter){
LOG_WARN("找不到对应人脸信息;序号:"<second<<"; 可信度:"<second % static_cast(condi) % confidence).str();
flag_find_face = true;
}
}
if(flag_find_face){
cv::rectangle(bgr, r, CV_RGB(0, 255, 0), 2);
cv::putText(bgr, name, Point(r.x + 0.5 * r.width, r.y - 5), cv::FONT_HERSHEY_COMPLEX_SMALL, 1, CV_RGB(0, 255, 0));
}else{
cv::rectangle(bgr, r, CV_RGB(255, 0, 0), 2);
}
}
}
} catch(const std::exception& e){
LOG_ERROR("发生错误:"<
整个类代码如下:
#include
#include
#include
#include
using namespace cv;
using namespace cv::face;
#define DETECT_BUFFER_SIZE 0x20000
face_recognition::face_recognition()
{
}
void face_recognition::start(){
try{
Ptr p_model = LBPHFaceRecognizer::create();
// 获取训练图片集合
std::vector infos;
if(!find_face_info(infos, "./face")){
return;
}
std::vector images;
std::vector labels;
for(auto& p_info : infos){
for(auto& f : p_info->files){
// 这里记得是IMREAD_GRAYSCALE,即灰度图片,不然会报错
images.push_back(imread(f, cv::IMREAD_GRAYSCALE));
labels.push_back(p_info->index);
}
m_index_to_name.insert(std::make_pair(p_info->index, p_info->name));
}
// 训练模型
p_model->train(images, labels);
mp_model = p_model;
// 加载opencv提供的人脸检测模型,识别率比较低
std::string face_file("./haarcascade_frontalface_alt2.xml");
if(boost::filesystem::exists(face_file)){
mp_cascade = std::make_shared();
mp_cascade->load(face_file);
}else{
LOG_ERROR("找不到对应的文件检测模型文件:"< confidence){
continue;
}
cv::Rect r(x,y,w,h);
bool flag_find_face = false;
std::string name;
// 复制出检测出来的人脸,然后转换成灰度图片,不转换会报错
cv::Mat desc;
bgr(r).copyTo(desc);
cv::Mat gray_desc;
gray_desc.create(desc.size(), desc.type());
cv::cvtColor(desc, gray_desc, cv::COLOR_BGR2GRAY);
int index = -1;
double condi = 0.0;
// 实际总会返回一个检测结果,置信度暂时不知道怎么使用
mp_model->predict(gray_desc, index, condi);
if(0 > index){
}else{
auto iter = m_index_to_name.find(index);
if(m_index_to_name.end() == iter){
LOG_WARN("找不到对应人脸信息;序号:"<second<<"; 可信度:"<second % static_cast(condi) % confidence).str();
flag_find_face = true;
}
}
if(flag_find_face){
cv::rectangle(bgr, r, CV_RGB(0, 255, 0), 2);
cv::putText(bgr, name, Point(r.x + 0.5 * r.width, r.y - 5), cv::FONT_HERSHEY_COMPLEX_SMALL, 1, CV_RGB(0, 255, 0));
}else{
cv::rectangle(bgr, r, CV_RGB(255, 0, 0), 2);
}
}
}
} catch(const std::exception& e){
LOG_ERROR("发生错误:"< files;
if(!find_file_from_folder(files, folder_src)){
return false;
}
cv::CascadeClassifier cascade;
cascade.load("./haarcascade_frontalface_alt2.xml");
for(auto& p : files){
cv::Mat src = cv::imread(p);
if(nullptr == src.data){
LOG_ERROR("文件无法正常读取:"< rect;
cascade.detectMultiScale(gray, rect, 1.1, 3, 0);
if(rect.empty()){
LOG_WARN("没有检测到人脸:"<
& infos, const std::string& folder){
std::vector all_folders;
if(!find_folder_from_folder(all_folders, boost::filesystem::system_complete(folder).string())){
return false;
}
int index = 1;
for(auto& d : all_folders){
std::vector files;
if (!find_file_from_folder(files, d)) {
continue;
}
auto path = boost::filesystem::system_complete(d);
auto parent_folder = path.parent_path().string();
auto name = path.string().substr(parent_folder.size() + 1);
auto p_info = std::make_shared();
p_info->index = index++;
p_info->name = name;
for(auto& f : files){
p_info->files.push_back(f);
}
infos.push_back(p_info);
}
return true;
}
bool face_recognition::find_file_from_folder(std::vector& files, const std::string& folder, const std::string& extend){
boost::filesystem::path path_folder(folder);
if(!boost::filesystem::exists(path_folder)){
LOG_ERROR("文件夹路径不存在:"<path();
if (boost::filesystem::is_directory(path)) {
continue;
}
if(!extend.empty() && extend != path.extension()){
continue;
}
files.push_back(path.string());
}
return true;
}
bool face_recognition::find_folder_from_folder(std::vector& all_folders, const std::string& folder){
boost::filesystem::path path_folder(folder);
if(!boost::filesystem::exists(path_folder)){
LOG_ERROR("文件夹路径不存在:"<path();
if (!boost::filesystem::is_directory(path)) {
continue;
}
if("." == path.string() || ".." == path.string()){
continue;
}
all_folders.push_back(path.string());
}
return true;
}
libfacedetection库的人脸检测成功率还是非常高的,比较稳定,符合预期。从测试来看,使用单线程人脸检测分辨率576*324的图像平均耗时55毫秒,人脸识别模块耗时25毫秒,总耗时90毫秒,无法流畅解析视频流,故需跳帧检测,或是多线程处理,或是提高效率。另外,人脸识别模块的成功率非常烂,得找另外的库代替。默认的opencv人脸模块还是靠不住,得自己优化。