c++ - 人脸识别的opencv代码在visual c++中预测不正确

Question

这是我在视频中进行人脸识别的代码。它运行没有任何错误，但它是预测 大多数时候都是错误的。我正在使用 LBPH 人脸识别器来识别人脸。 我尝试使用 haar 级联，但它没有加载。所以我切换到 LBHP。请帮助我改进预测。 我正在使用大小为 500 x 500(像素)的灰度裁剪图像来训练级联分类器。

#include <opencv2/core/core.hpp>
#include <opencv2/contrib/contrib.hpp
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/objdetect/objdetect.hpp>

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

using namespace cv;
using namespace std;

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()));
    }
}
}

string g_listname_t[]= 
{
"ajay","Aasai","famiz"
};

int main(int argc, const char *argv[]) {
// Check for valid command line arguments, print usage
// if no arguments were given.
//if (argc != 4) {
//   cout << "usage: " << argv[0] << " </path/to/haar_cascade> </path/to/csv.ext> </path/to/device id>"<<endl;
//    cout << "\t </path/to/haar_cascade> -- Path to the Haar Cascade for face detection." << endl;
//    cout << "\t </path/to/csv.ext> -- Path to the CSV file with the face database." << endl;
//    cout << "\t <device id> -- The webcam device id to grab frames from." << endl;
//    exit(1);
//}
//// Get the path to your CSV:
//string fn_haar = string(argv[1]);
//string fn_csv = string(argv[2]);
//int deviceId = atoi(argv[3]);
//// Get the path to your CSV:
// please set the correct path based on your folder
string fn_haar = "lbpcascade_frontalface.xml";
string fn_csv = "reader.ext ";
int deviceId = 0;           // here is my webcam Id. 
// These vectors hold the images and corresponding labels:
vector<Mat> images;
vector<int> labels;
// Read in the data (fails if no valid input filename is given, but you'll get an error message):
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);
}
// Get the height from the first image. We'll need this
// later in code to reshape the images to their original
// size AND we need to reshape incoming faces to this size:
int im_width = images[0].cols;
int im_height = images[0].rows;
// Create a FaceRecognizer and train it on the given images:
Ptr<FaceRecognizer> model = createLBPHFaceRecognizer();
model->train(images, labels);
cout<<("Facerecognizer created");
// That's it for learning the Face Recognition model. You now
// need to create the classifier for the task of Face Detection.
// We are going to use the haar cascade you have specified in the
// command line arguments:

CascadeClassifier lbp_cascade;

if ( ! lbp_cascade.load(fn_haar) )
{
cout<<("\nlbp cascade not loaded");
} 
else
{
    cout<<("\nlbp cascade loaded");
}

 // Get a handle to the Video device:
 VideoCapture cap(deviceId);
cout<<("\nvideo device is opened");
// Check if we can use this device at all:
if(!cap.isOpened()) {
    cerr << "Capture Device ID " << deviceId << "cannot be opened." << endl;
    return -1;
}


// Holds the current frame from the Video device:
Mat frame;
for(;;) {
    cap >> frame;

    // Clone the current frame:
    Mat original = frame.clone();
    cout<<("\nframe is cloned");
    // Convert the current frame to grayscale:
    Mat gray;
    //gray = imread("G:\Picture\003.jpg",0);
    cvtColor(original, gray, CV_BGR2GRAY);
    imshow("gray image", gray);
    // And display it:
     char key1 = (char) waitKey(50);


    // Find the faces in the frame:
    cout<<("\ncolor converted");
    vector< Rect_<int> > faces;
    cout<<("\ndetecting faces");
    lbp_cascade.detectMultiScale(gray, faces);
    // At this point you have the position of the faces in
    // faces. Now we'll get the faces, make a prediction and
    // annotate it in the video. Cool or what?
    cout<<("\nfaces detected\n");
    cout<<faces.size();
    for(int i = 0; i < faces.size(); i++) 
    {
        // Process face by face:
        cout<<("\nprocessing faces");
        Rect face_i = faces[i];
        // Crop the face from the image. So simple with OpenCV C++:
        Mat face = gray(face_i);
        // Resizing the face is necessary for Eigenfaces and Fisherfaces. You can easily
        // verify this, by reading through the face recognition tutorial coming with OpenCV.
        // Resizing IS NOT NEEDED for Local Binary Patterns Histograms, so preparing the
        // input data really depends on the algorithm used.
        //
        // I strongly encourage you to play around with the algorithms. See which work best
        // in your scenario, LBPH should always be a contender for robust face recognition.
        //
        // Since I am showing the Fisherfaces algorithm here, I also show how to resize the
        // face you have just found:
        /*Mat face_resized;
        cv::resize(face, face_resized, Size(im_width, im_height), 1.0, 1.0, INTER_CUBIC);
        // Now perform the prediction, see how easy that is:
        cout<<("\nface resized");
        imshow("resized face image", face_resized);*/
        int prediction = model->predict(face);
        cout<<("\nface predicted");
        // And finally write all we've found out to the original image!
        // First of all draw a green rectangle around the detected face:
        cout<<("\nnow writing to original");
        rectangle(original, face_i, CV_RGB(0, 255,0), 1);
        // Create the text we will annotate the box with:
        string box_text;
        box_text = format( "Prediction =",prediction);
        // Get stringname
        if ( prediction >= 0 && prediction <=1 )
        {
            box_text.append( g_listname_t[prediction] );
        }
        else box_text.append( "Unknown" );
        // Calculate the position for annotated text (make sure we don't
        // put illegal values in there):
        int pos_x = std::max(face_i.tl().x - 10, 0);
        int pos_y = std::max(face_i.tl().y - 10, 0);
        // And now put it into the image:
        putText(original, box_text, Point(pos_x, pos_y), FONT_HERSHEY_PLAIN, 1.0, CV_RGB(0,255,0), 2.0);
    }
    // Show the result:
    imshow("face_recognizer", original);
    // And display it:
    char key = (char) waitKey(50);
    // Exit this loop on escape:
    if(key == 27)
        break;
}
return 0;
}

Answer 1

如果你问我，这是一个预期的结果，你展示的代码是进行识别的基本代码，在实现之前我们需要注意一些背景。

1) 训练图像的质量，你是如何裁剪它们的？ 它们是否包含除了人脸之外的任何额外信息，如果您在我们的 opencv 数据中使用 haar 分类器来裁剪人脸，那么图像往往包含比人脸更多的信息，因为与人脸相比，矩形的尺寸有点大。

2) 有可能，即使是旋转的面孔也可能被训练，因此，很难用旋转面孔的特征进行分类。

3) 有多少张图片，你用 ? 训练了识别器，它起着至关重要的作用。

第一个问题的答案，很可能是 opencv 之外的，我们对此无能为力，因为可能性很小，我们会找到一个与 haar 检测器一样好和简单的人脸检测器，因此，如果我们能够以大约 70% 的准确度进行调整，我们可以将其作为豁免。

第二个问题可以通过对训练和测试数据集进行一些预处理技术来解决。 比如，对齐正在旋转的面 点击此链接，会提出非常好的面部对齐建议。

How to align face images c++ opencv

第三个问题是用大量的样本解决的，这不是什么难事，在训练前注意对齐，这样才能提取正确的特征进行分类。

可能还有其他因素可以提高我可能错过的准确性。