人脸识别OpenCV Visual Studio理解

Question

I have one noob question.. I'm trying to make face detection/recognition program in Visual studio 2010 using opencCV 2.4.6. I'm having troubles with face recognition algorithm taken from openCV documentation. The algorithm itself works for me without any errors, however i'm an not sure that i understand it's output or maybe it isn't really correct.. I am using AT&T database for training and recognizing.. My csv file (at.txt) looks like this:

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

My face recognizer code looks like this:

#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;
}

And my output look like this:

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

Algorithm also outputs images: which are mean image, eigneface images and reconstruction images.. The most important images as far as I know are reconstructed images..and in the output i get few reconstructed images but almost all looks like ghosts except the last one that is the first face/picture reconstructed correctly.. Is the algorithm working correctly? Why don't I get other reconstructed faces as well? What does it mean predicted class = 7, actual class = 9?

Answer 1

It seems like you need a basic understanding of the algorithm.

I recommend you to read the Wikipedia Article about Eigenfaces and the Paper: Face Recognition using Eigenfaces from Turk & Pentland which can be found here .

It would also help if you could tell us what your goal is. Maybe you are going in the wrong direction by using this algorithm.