人脸识别openCV视觉工作室理解

Posted 2023-02-22

【中文标题】人脸识别openCV视觉工作室理解

【英文标题】：Face recognition openCV visual studio understanding

【发布时间】：2013-10-30 13:54:47

【问题描述】：

我有一个菜鸟问题.. 我正在尝试使用 opencCV 2.4.6 在 Visual Studio 2010 中制作人脸检测/识别程序。 我在使用来自 openCV 文档的人脸识别算法时遇到问题。 该算法本身对我有用，没有任何错误，但是我不确定我是否理解它的输出，或者它可能不是真的正确..我正在使用 AT&T 数据库进行训练和识别.. 我的 csv 文件 (at.txt) 如下所示：

C:\face\s1/1.pgm;0
C:\face\s1/2.pgm;0
C:\face\s1/3.pgm;0
C:\face\s1/4.pgm;0
C:\face\s1/5.pgm;0
C:\face\s1/6.pgm;0
C:\face\s1/7.pgm;0
C:\face\s1/8.pgm;0
C:\face\s1/9.pgm;0
C:\face\s1/10.pgm;0
C:\face\s2/1.pgm;1
C:\face\s2/2.pgm;1
C:\face\s2/3.pgm;1
C:\face\s2/4.pgm;1
C:\face\s2/5.pgm;1
C:\face\s2/6.pgm;1
C:\face\s2/7.pgm;1
C:\face\s2/8.pgm;1
C:\face\s2/9.pgm;1
C:\face\s2/10.pgm;1
C:\face\s3/1.pgm;2
C:\face\s3/2.pgm;2
C:\face\s3/3.pgm;2
C:\face\s3/4.pgm;2
C:\face\s3/5.pgm;2
C:\face\s3/6.pgm;2
C:\face\s3/7.pgm;2
C:\face\s3/8.pgm;2
C:\face\s3/9.pgm;2
C:\face\s3/10.pgm;2
C:\face\s4/1.pgm;3
C:\face\s4/2.pgm;3
C:\face\s4/3.pgm;3
C:\face\s4/4.pgm;3
C:\face\s4/5.pgm;3
C:\face\s4/6.pgm;3
C:\face\s4/7.pgm;3
C:\face\s4/8.pgm;3
C:\face\s4/9.pgm;3
C:\face\s4/10.pgm;3
C:\face\s5/1.pgm;4
C:\face\s5/2.pgm;4
C:\face\s5/3.pgm;4
C:\face\s5/4.pgm;4
C:\face\s5/5.pgm;4
C:\face\s5/6.pgm;4
C:\face\s5/7.pgm;4
C:\face\s5/8.pgm;4
C:\face\s5/9.pgm;4
C:\face\s5/10.pgm;4
C:\face\s6/1.pgm;5
C:\face\s6/2.pgm;5
C:\face\s6/3.pgm;5
C:\face\s6/4.pgm;5
C:\face\s6/5.pgm;5
C:\face\s6/6.pgm;5
C:\face\s6/7.pgm;5
C:\face\s6/8.pgm;5
C:\face\s6/9.pgm;5
C:\face\s6/10.pgm;5
C:\face\s7/1.pgm;6
C:\face\s7/2.pgm;6
C:\face\s7/3.pgm;6
C:\face\s7/4.pgm;6
C:\face\s7/5.pgm;6
C:\face\s7/6.pgm;6
C:\face\s7/7.pgm;6
C:\face\s7/8.pgm;6
C:\face\s7/9.pgm;6
C:\face\s7/10.pgm;6
C:\face\s8/1.pgm;7
C:\face\s8/2.pgm;7
C:\face\s8/3.pgm;7
C:\face\s8/4.pgm;7
C:\face\s8/5.pgm;7
C:\face\s8/6.pgm;7
C:\face\s8/7.pgm;7
C:\face\s8/8.pgm;7
C:\face\s8/9.pgm;7
C:\face\s8/10.pgm;7
C:\face\s9/1.pgm;8
C:\face\s9/2.pgm;8
C:\face\s9/3.pgm;8
C:\face\s9/4.pgm;8
C:\face\s9/5.pgm;8
C:\face\s9/6.pgm;8
C:\face\s9/7.pgm;8
C:\face\s9/8.pgm;8
C:\face\s9/9.pgm;8
C:\face\s9/10.pgm;8
C:\face\s10/1.pgm;9
C:\face\s10/2.pgm;9
C:\face\s10/3.pgm;9
C:\face\s10/4.pgm;9
C:\face\s10/5.pgm;9
C:\face\s10/6.pgm;9
C:\face\s10/7.pgm;9
C:\face\s10/8.pgm;9
C:\face\s10/9.pgm;9
C:\face\s10/10.pgm;9

我的面部识别器代码如下所示：

#include "stdafx.h"

#include "opencv2/core/core.hpp"
#include "opencv2/contrib/contrib.hpp"
#include "opencv2/highgui/highgui.hpp"

#include <iostream>
#include <fstream>
#include <sstream>

using namespace cv;
using namespace std;

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;


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(CV_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[]) 
    // Check for valid command line arguments, print usage
    // if no arguments were given.
    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]);
    
    // Get the path to your CSV.
    string fn_csv = string(argv[1]);
    // These vectors hold the images and corresponding labels.
    vector<Mat> images;
    vector<int> labels;
    // Read in the data. This can fail if no valid
    // input filename is given.
    try 
        read_csv(fn_csv, images, labels);
     catch (cv::Exception& e) 
        cerr << "Error opening file \"" << fn_csv << "\". Reason: " << e.msg << endl;
        // nothing more we can do
        exit(1);
    
    // Quit if there are not enough images for this demo.
    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(CV_StsError, error_message);
    
    // Get the height from the first image. We'll need this
    // later in code to reshape the images to their original
    // size:
    int height = images[0].rows;
    // The following lines simply get the last images from
    // your dataset and remove it from the vector. This is
    // done, so that the training data (which we learn the
    // cv::FaceRecognizer on) and the test data we test
    // the model with, do not overlap.
    Mat testSample = images[images.size() - 1];
    int testLabel = labels[labels.size() - 1];
    images.pop_back();
    labels.pop_back();
    // The following lines create an Eigenfaces model for
    // face recognition and train it with the images and
    // labels read from the given CSV file.
    // This here is a full PCA, if you just want to keep
    // 10 principal components (read Eigenfaces), then call
    // the factory method like this:
    //
    //      cv::createEigenFaceRecognizer(10);
    //
    // If you want to create a FaceRecognizer with a
    // confidence threshold (e.g. 123.0), call it with:
    //
    //      cv::createEigenFaceRecognizer(10, 123.0);
    //
    // If you want to use _all_ Eigenfaces and have a threshold,
    // then call the method like this:
    //
    //      cv::createEigenFaceRecognizer(0, 123.0);
    //
    Ptr<FaceRecognizer> model = createEigenFaceRecognizer();
    model->train(images, labels);
    // The following line predicts the label of a given
    // test image:
    int predictedLabel = model->predict(testSample);
    //
    // To get the confidence of a prediction call the model with:
    //
    //      int predictedLabel = -1;
    //      double confidence = 0.0;
    //      model->predict(testSample, predictedLabel, confidence);
    //
    string result_message = format("Predicted class = %d / Actual class = %d.", predictedLabel, testLabel);
    cout << result_message << endl;
    // Here is how to get the eigenvalues of this Eigenfaces model:
    Mat eigenvalues = model->getMat("eigenvalues");
    // And we can do the same to display the Eigenvectors (read Eigenfaces):
    Mat W = model->getMat("eigenvectors");
    // Get the sample mean from the training data
    Mat mean = model->getMat("mean");
    // Display or save:
    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)));
    
    // Display or save the Eigenfaces:
    for (int i = 0; i < min(10, W.cols); i++) 
        string msg = format("Eigenvalue #%d = %.5f", i, eigenvalues.at<double>(i));
        cout << msg << endl;
        // get eigenvector #i
        Mat ev = W.col(i).clone();
        // Reshape to original size & normalize to [0...255] for imshow.
        Mat grayscale = norm_0_255(ev.reshape(1, height));
        // Show the image & apply a Jet colormap for better sensing.
        Mat cgrayscale;
        applyColorMap(grayscale, cgrayscale, COLORMAP_JET);
        // Display or save:
        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));
        
    

    // Display or save the image reconstruction at some predefined steps:
    for(int num_components = min(W.cols, 10); num_components < min(W.cols, 300); num_components+=15) 
        // slice the eigenvectors from the model
        Mat evs = Mat(W, Range::all(), Range(0, num_components));
        Mat projection = subspaceProject(evs, mean, images[0].reshape(1,1));
        Mat reconstruction = subspaceReconstruct(evs, mean, projection);
        // Normalize the result:
        reconstruction = norm_0_255(reconstruction.reshape(1, images[0].rows));
        // Display or save:
        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);
        
    
    // Display if we are not writing to an output folder:
    if(argc == 2) 
        waitKey(0);
    
    return 0;

我的输出如下所示：

http://s15.postimg.org/xq76erurf/image.png

算法还输出图像：它们是平均图像、eigneface 图像和重建图像。据我所知，最重要的图像是重建图像。在输出中我得到的重建图像很少，但几乎所有看起来都像鬼，除了最后一个是正确重建的第一张人脸/图片。算法是否正常工作？ 为什么我没有得到其他重建的面孔呢？ 预测class= 7，实际class= 9是什么意思？

【问题讨论】：

嗨安德里亚。听起来你有很多关于机器学习的知识。我不是专家，但人脸识别是一项分类任务。在这些任务中，“这是谁的脸？”这个问题有一个正确的答案。这个正确的答案是实际的类。您的计算机的猜测是预测的类。如您所见，您的计算机预测错误:(

"都像鬼一样" ; - 没关系。将每个“幽灵”视为一个基向量，重建是所有这些“特征向量”的组合。可悲的是，预测是错误的。不知道为什么。

【参考方案1】：

看来你需要对算法有一个基本的了解。

我建议您阅读来自 Turk & Pentland 的 Wikipedia Article about Eigenfaces 和论文：Face Recognition using Eigenfaces，可以在 here 找到。

如果您能告诉我们您的目标是什么，也会有所帮助。使用这个算法，你可能走错了方向。

【讨论】：

是的，我确实这样做了，我将继续研究它。我正在尝试制作一个程序来识别已学习的面孔并将该面孔的名称显示为输出。我会朝着好的方向发展吗？

是的，你很可能。特征脸的问题在于，只有当数据库中的图像（训练图像）和您想要识别的图像（样本图像）之间的差异非常小时，您才能识别出一个人。所以它归结为你真正想做的事情。但是，如果您刚开始接触面部识别，那么 OpenCV 使用的特征脸和其他方法是一个很好的起点。