openCV学习笔记（十六） —— 人脸识别 —— 程序 —— PCA特征脸Eigenfaces、重建人脸

太过爱你忘了你带给我的痛 2021-09-27 06:24 416阅读 0赞

此程序主要来源于F:\\personal\\data\\openCV\\opencv\_contrib\_3.4.1\\modules\\face\\samples\\facerec\_eigenfaces.cpp

# 流程 #

![70][]

1.  读人脸数据文件
2.  创建特征脸识别与训练
3.  识别人脸
4.  输出中间平均脸、特征脸、重建结果

# 相关图示  #

![70 1][]

![70 2][]

# 程序  #

/*
    	此程序主要来源于F:\personal\data\openCV\opencv_contrib_3.4.1\modules\face\samples\facerec_eigenfaces.cpp
    */
    #include <opencv2/opencv.hpp>
    #include <opencv2/face.hpp>
    
    //#include <fstream>
    //#include <iostream>
    
    using namespace std;
    using namespace cv;
    using namespace cv::face;
    
    Mat normal(Mat& src, Mat& dst)
    {
    	if (src.channels() == 1)
    	{
    		normalize(src, dst, 0, 255, NORM_MINMAX, CV_8UC1);
    	}
    	else
    	{
    		normalize(src, dst, 0, 255, NORM_MINMAX, CV_8UC1);
    	}
    
    	return dst;
    }
    
    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()
    {
    	string filename = ".\\face_recg\\face\\at.txt";
    
    	vector<Mat> images;
    	vector<int> labels;
    
    	//从文件中读取图像保存到向量中
    	try {
    		read_csv(filename, images, labels);
    	}
    	catch (Exception& e)
    	{
    		cerr << "Error opening file \n" << filename << "\". Reason: " << e.msg << endl;
    		exit(1);
    	}
    
    	if (images.size() <= 1)
    	{
    		cerr << "图像太少，请至少添加两个图片！" << endl;
    		exit(1);
    	}
    
    	//从第一个图像获取高度，在后面的代码里面需要用到它来重塑原来的图片大小
    	int height = images[0].rows;
    	int width = images[0].cols;
    	printf("height: %d, width: %d\n", height, width);
    
    	//最后一个人为测试样本
    	Mat testSample = images[images.size() - 1];
    	int testLabel = labels[labels.size() - 1];
    	images.pop_back();
    	labels.pop_back();
    
    	//训练
    	Ptr<EigenFaceRecognizer> model = EigenFaceRecognizer::create();
    	model->train(images, labels);
    
    	//识别
    	int predictedLabel = model->predict(testSample);
    	printf("actual label: %d, predict label: %d\n", testLabel, predictedLabel);
    
    	//获得特征值，特征向量，均值，平均脸
    	Mat eigenValues = model->getEigenValues();
    	Mat eigenVector = model->getEigenVectors();
    	Mat mean = model->getMean();
    	Mat meanFace = mean.reshape(1, height);
    
    	Mat dst;
    	dst = normal(meanFace, dst);
    	imshow("MeanFace", dst);
    
    	//特征脸
    	for (int i = 0; i < min(10, eigenVector.cols); i++)
    	{
    		Mat ev = eigenVector.col(i).clone();
    		Mat eigenFace = ev.reshape(1, height);
    
    		Mat grayScale;
    		grayScale = normal(eigenFace, grayScale);
    
    		Mat colorFace;
    		applyColorMap(grayScale, colorFace, COLORMAP_BONE);
    
    		imshow(format("eigenFace_%d", i), colorFace);
    	}
    
    	//重建人脸
    	for (int i = min(10, eigenVector.cols); i < min(300, eigenVector.cols); i += 15)
    	{
    		Mat evs = Mat(eigenVector, Range::all(), Range(0, i));
    		Mat projection = LDA::subspaceProject(evs, mean, images[0].reshape(1, 1));
    		Mat reconstruction = LDA::subspaceReconstruct(evs, mean, projection);
    
    		Mat result = reconstruction.reshape(1, height);
    		reconstruction = normal(result, reconstruction);
    		imshow(format("reco_face_%d", i), reconstruction);
    	}
    
    	waitKey(0);
    	destroyAllWindows();
    
    	return 0;
    }

[70]: /images/20210923/aa2c96f731b940c7bf588ea78bc34900.png
[70 1]: /images/20210923/13ff811dac324532ab0185bd9626fe34.png
[70 2]: /images/20210923/5545b5370421423397feea3c7d0ac84c.png