目录
1--前言
2--处理ORL数据集
3--Eigenfaces复现过程
4--Fisherfaces复现过程
5--分析
1--前言
①SYSU模式识别课程作业
②配置:基于Windows11、OpenCV4.5.5、VSCode、CMake(参考OpenCV配置方式)
③原理及源码介绍:Face Recognition with OpenCV
④数据集:ORL Database of Faces
2--处理ORL数据集
①源码:
import sys
import os.path
if __name__ == "__main__":
BASE_PATH = './ORL/att_faces/orl_faces/'
SEPARATOR = ";"
dir_txt = open("./dir.txt", 'w')
label = 0
for dirname, dirnames, filenames in os.walk(BASE_PATH):
# dirname当前路径; dirnames当前路径下所有目录名(不包含子目录);filenames当前路径下的所有文件名(不包含子目录)
for subdirname in dirnames: # 遍历每一个目录
subject_path = os.path.join(dirname, subdirname)
for filename in os.listdir(subject_path):
abs_path = "%s/%s" % (subject_path, filename)
print("%s%s%d" % (abs_path, SEPARATOR, label))
dir_txt.write(abs_path)
dir_txt.write(SEPARATOR)
dir_txt.write(str(label))
dir_txt.write("\n")
label = label + 1
dir_txt.close()
②运行及结果:
python create_csv.py
3--Eigenfaces复现过程
①源码:
// 引用依赖
#include "opencv2/core.hpp"
#include "opencv2/face.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/imgproc.hpp"
#include <iostream>
#include <fstream>
#include <sstream>
// 使用相应的命名空间
using namespace cv;
using namespace cv::face;
using namespace std;
// 标准化函数
static Mat norm_0_255(InputArray _src) {
Mat src = _src.getMat();
// Create and return normalized image:
Mat dst;
switch(src.channels()) {
case 1:
cv::normalize(_src, dst, 0, 255, NORM_MINMAX, CV_8UC1);
break;
case 3:
cv::normalize(_src, dst, 0, 255, NORM_MINMAX, CV_8UC3);
break;
default:
src.copyTo(dst);
break;
}
return dst;
}
// 读取CSV文件函数
static void read_csv(const string& filename, vector<Mat>& images, vector<int>& labels, char separator = ';') {
std::ifstream file(filename.c_str(), ifstream::in);
if (!file) {
string error_message = "No valid input file was given, please check the given filename.";
CV_Error(Error::StsBadArg, error_message);
}
string line, path, classlabel;
while (getline(file, line)) {
stringstream liness(line);
getline(liness, path, separator);
getline(liness, classlabel);
if(!path.empty() && !classlabel.empty()) {
images.push_back(imread(path, 0));
labels.push_back(atoi(classlabel.c_str()));
}
}
}
int main(int argc, const char *argv[]) {
//检查argc是否符合要求
if (argc < 2) {
cout << "usage: " << argv[0] << " <csv.ext> <output_folder> " << endl;
exit(1);
}
string output_folder = ".";
if (argc == 3) {
output_folder = string(argv[2]);
}
// CSV文件的路径
string fn_csv = string(argv[1]);
// 初始化存储imgs和labels的向量
vector<Mat> images;
vector<int> labels;
// 读取CSV文件
try {
read_csv(fn_csv, images, labels);
} catch (const cv::Exception& e) {
cerr << "Error opening file \"" << fn_csv << "\". Reason: " << e.msg << endl;
exit(1);
}
// 判断img数目是否符合要求
if(images.size() <= 1) {
string error_message = "This demo needs at least 2 images to work. Please add more images to your data set!";
CV_Error(Error::StsError, error_message);
}
// images的高度
int height = images[0].rows;
// 从训练集中选择一张图片作为测试集
Mat testSample = images[images.size() - 1];
int testLabel = labels[labels.size() - 1];
images.pop_back();
labels.pop_back();
// 创建模型,使用PCA特征脸算法
Ptr<EigenFaceRecognizer> model = EigenFaceRecognizer::create();
model->train(images, labels); // 训练模型
int predictedLabel = model->predict(testSample); // 使用测试集测试模型
// 打印准确率
string result_message = format("Predicted class = %d / Actual class = %d.", predictedLabel, testLabel);
cout << result_message << endl;
// 获取模型的特征值
Mat eigenvalues = model->getEigenValues();
// 展示特征向量
Mat W = model->getEigenVectors();
// 从训练集中获取样本均值
Mat mean = model->getMean();
// 根据argc判断进行展示或保存操作
if(argc == 2) {
imshow("mean", norm_0_255(mean.reshape(1, images[0].rows)));
} else {
imwrite(format("%s/mean.png", output_folder.c_str()), norm_0_255(mean.reshape(1, images[0].rows)));
}
// 显示或保存特征脸
for (int i = 0; i < min(10, W.cols); i++) {
string msg = format("Eigenvalue #%d = %.5f", i, eigenvalues.at<double>(i));
cout << msg << endl;
// 获取特征向量
Mat ev = W.col(i).clone();
// resize成原始大小,并归一化到0-255
Mat grayscale = norm_0_255(ev.reshape(1, height));
// 显示图像并应用Jet颜色图以获得更好的观感。
Mat cgrayscale;
applyColorMap(grayscale, cgrayscale, COLORMAP_JET);
// 根据argc判断进行展示或保存操作
if(argc == 2) {
imshow(format("eigenface_%d", i), cgrayscale);
} else {
imwrite(format("%s/eigenface_%d.png", output_folder.c_str(), i), norm_0_255(cgrayscale));
}
}
// 在一些预定义的步骤中显示或保存图像重建的过程:
for(int num_components = min(W.cols, 10); num_components < min(W.cols, 300); num_components+=15) {
// 从模型中分割特征向量
Mat evs = Mat(W, Range::all(), Range(0, num_components));
Mat projection = LDA::subspaceProject(evs, mean, images[0].reshape(1,1));
Mat reconstruction = LDA::subspaceReconstruct(evs, mean, projection);
// 归一化
reconstruction = norm_0_255(reconstruction.reshape(1, images[0].rows));
// 根据argc判断进行展示或保存操作
if(argc == 2) {
imshow(format("eigenface_reconstruction_%d", num_components), reconstruction);
} else {
imwrite(format("%s/eigenface_reconstruction_%d.png", output_folder.c_str(), num_components), reconstruction);
}
}
// 如果没有写入输出文件夹,则等待键盘输入
if(argc == 2) {
waitKey(0);
}
return 0;
}
②编译过程:
CMakeLists.txt如下:
cmake_minimum_required(VERSION 3.24) # 指定 cmake的 最小版本
project(test) # 设置项目名称
find_package(Opencv REQUIRED)
INCLUDE_DIRECTORIES(${OpenCV_INCLUDE_DIRS})
add_executable(eigenfaces_demo eigenfaces.cpp) # 生成可执行文件
target_link_libraries(eigenfaces_demo ${OpenCV_LIBS} ) # 设置target需要链接的库
mkdir build
cd build
cmake ..
cd ..
mingw32-make
③运行及结果展示:
./eigenfaces_demo.exe ./dir.txt ./Engenfaces_Result
特征图:(简单修改源程序生成的文件名,再按顺序进行拼接即可生成拼接图,拼接程序参考)
重建过程:
均值图:
4--Fisherfaces复现过程
①源码:
// 引用依赖
#include "opencv2/core.hpp"
#include "opencv2/face.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/imgproc.hpp"
#include <iostream>
#include <fstream>
#include <sstream>
// 使用相应的命名空间
using namespace cv;
using namespace cv::face;
using namespace std;
// 标准化函数
static Mat norm_0_255(InputArray _src) {
Mat src = _src.getMat();
Mat dst;
switch(src.channels()) {
case 1:
cv::normalize(_src, dst, 0, 255, NORM_MINMAX, CV_8UC1);
break;
case 3:
cv::normalize(_src, dst, 0, 255, NORM_MINMAX, CV_8UC3);
break;
default:
src.copyTo(dst);
break;
}
return dst;
}
// 读取csv文件函数
static void read_csv(const string& filename, vector<Mat>& images, vector<int>& labels, char separator = ';') {
std::ifstream file(filename.c_str(), ifstream::in);
if (!file) {
string error_message = "No valid input file was given, please check the given filename.";
CV_Error(Error::StsBadArg, error_message);
}
string line, path, classlabel;
while (getline(file, line)) {
stringstream liness(line);
getline(liness, path, separator);
getline(liness, classlabel);
if(!path.empty() && !classlabel.empty()) {
images.push_back(imread(path, 0));
labels.push_back(atoi(classlabel.c_str()));
}
}
}
int main(int argc, const char *argv[]) {
//检查argc是否符合要求
if (argc < 2) {
cout << "usage: " << argv[0] << " <csv.ext> <output_folder> " << endl;
exit(1);
}
string output_folder = ".";
if (argc == 3) {
output_folder = string(argv[2]);
}
// CSV文件的路径
string fn_csv = string(argv[1]);
// 初始化存储imgs和labels的向量
vector<Mat> images;
vector<int> labels;
// 读取CSV文件
try {
read_csv(fn_csv, images, labels);
} catch (const cv::Exception& e) {
cerr << "Error opening file \"" << fn_csv << "\". Reason: " << e.msg << endl;
exit(1);
}
// 判断img数目是否符合要求
if(images.size() <= 1) {
string error_message = "This demo needs at least 2 images to work. Please add more images to your data set!";
CV_Error(Error::StsError, error_message);
}
// images的高度
int height = images[0].rows;
// 从训练集中选择一张图片作为测试集
Mat testSample = images[images.size() - 1];
int testLabel = labels[labels.size() - 1];
images.pop_back();
labels.pop_back();
// 创建模型,使用LDA线性判别分析
Ptr<FisherFaceRecognizer> model = FisherFaceRecognizer::create();
model->train(images, labels); // 训练模型
int predictedLabel = model->predict(testSample); // 使用测试集测试模型
// 打印准确率
string result_message = format("Predicted class = %d / Actual class = %d.", predictedLabel, testLabel);
cout << result_message << endl;
// 获取模型的特征值
Mat eigenvalues = model->getEigenValues();
// 展示特征向量
Mat W = model->getEigenVectors();
// 从训练集中获取样本均值
Mat mean = model->getMean();
// 根据argc判断进行展示或保存操作
if(argc == 2) {
imshow("mean", norm_0_255(mean.reshape(1, images[0].rows)));
} else {
imwrite(format("%s/mean.png", output_folder.c_str()), norm_0_255(mean.reshape(1, images[0].rows)));
}
// 显示或保存特征脸
for (int i = 0; i < min(16, W.cols); i++) {
string msg = format("Eigenvalue #%d = %.5f", i, eigenvalues.at<double>(i));
cout << msg << endl;
// 获取特征向量
Mat ev = W.col(i).clone();
// resize成原始大小,并归一化到0-255
Mat grayscale = norm_0_255(ev.reshape(1, height));
// 显示图像并应用Jet颜色图以获得更好的观感。
Mat cgrayscale;
applyColorMap(grayscale, cgrayscale, COLORMAP_BONE);
// 根据argc判断进行展示或保存操作
if(argc == 2) {
imshow(format("fisherface_%d", i), cgrayscale);
} else {
imwrite(format("%s/fisherface_%d.png", output_folder.c_str(), i), norm_0_255(cgrayscale));
}
}
// 在一些预定义的步骤中显示或保存图像重建的过程:
for(int num_component = 0; num_component < min(16, W.cols); num_component++) {
// 从模型中分割特征向量
Mat ev = W.col(num_component);
Mat projection = LDA::subspaceProject(ev, mean, images[0].reshape(1,1));
Mat reconstruction = LDA::subspaceReconstruct(ev, mean, projection);
// 归一化
reconstruction = norm_0_255(reconstruction.reshape(1, images[0].rows));
// 根据argc判断进行展示或保存操作
if(argc == 2) {
imshow(format("fisherface_reconstruction_%d", num_component), reconstruction);
} else {
imwrite(format("%s/fisherface_reconstruction_%d.png", output_folder.c_str(), num_component), reconstruction);
}
}
// 如果没有写入输出文件夹,则等待键盘输入
if(argc == 2) {
waitKey(0);
}
return 0;
}
②编译过程:
CMakeLists.txt如下:
cmake_minimum_required(VERSION 3.24) # 指定 cmake的 最小版本
project(test) # 设置项目名称
find_package(Opencv REQUIRED)
INCLUDE_DIRECTORIES(${OpenCV_INCLUDE_DIRS})
#add_executable(eigenfaces_demo eigenfaces.cpp) # 生成可执行文件
#target_link_libraries(eigenfaces_demo ${OpenCV_LIBS} ) # 设置target需要链接的库
add_executable(fisherfaces_demo fisherfaces.cpp) # 生成可执行文件
target_link_libraries(fisherfaces_demo ${OpenCV_LIBS} ) # 设置target需要链接的库
mkdir build
cd build
cmake ..
cd ..
mingw32-make
③运行及结果展示:
./fisherfaces_demo.exe ./dir.txt ./Fisherfaces_Result
特征图:
重建过程:
均值图:
5--分析
未完待续!