나는 하나의 멍청한 질문이 있습니다. Visual Studio 2010에서 opencCV 2.4.6을 사용하여 얼굴 인식/인식 프로그램을 만들려고합니다. openCV 설명서에서 가져온 얼굴 인식 알고리즘에 문제가 있습니다. 알고리즘 자체가 어떤 오류도없이 작동하지만, 나는 그것이 출력인지, 아니면 실제로는 정확하지 않은지 확신 할 수 없다. 훈련을하고 인식하기 위해서 & T 데이터베이스를 사용 중이다. 내 CSV 파일 (at.txt)은 다음과 같습니다얼굴 인식 openCV Visual Studio 이해
내 얼굴을 인식 코드는 다음과 같습니다C:\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
:
#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;
}
그리고 이런 내 출력의 모양을
http://s15.postimg.org/xq76erurf/image.png
알고리즘도 이미지를 출력합니다. 평균 이미지, 대인면 이미지 및 재구성 이미지입니다. 내가 아는 한 가장 중요한 이미지는 재구성 된 이미지이고 출력에서는 재구성 된 이미지가 거의 없지만 거의 모든 것이 유령처럼 보입니다 마지막 얼굴/그림이 올바르게 재구성 된 것을 제외하고는 ... 알고리즘이 올바르게 작동하고 있습니까? 다른 재구성 된 얼굴도 왜 갖지 못합니까? 예측 클래스 = 7, 실제 클래스 = 9는 무엇을 의미합니까?
안녕하세요 Andrija. 기계 학습에 대해 많은 것을 배워야하는 것 같습니다. 나는 전문가는 아니지만 얼굴 인식은 분류 작업입니다. 이러한 작업에는 '누구의 얼굴이 누구입니까?'라는 질문에 대한 정답이 있습니다. 이 정답은 실제 수업입니다. 컴퓨터의 추측은 예측 된 클래스입니다. 보시다시피, 컴퓨터가 잘못 예측했습니다. ( – AndyG
"모두 유령처럼 보입니다"- 괜찮습니다. 각각의 '유령'을 기본 벡터로 생각하면 재구성은 모든 '고유 벡터'의 조합입니다. 예측이 잘못되었습니다. 이유가 없습니다. – berak