main.cpp

#include <stdio.h>
#include <iostream>
#include <fstream>
#include <sstream>
#include <iterator>
#include <vector>
#include <string>
#include <map>
#include <cassert>
#include <opencv2/opencv.hpp>
#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"

using namespace cv;
using namespace std;

class CSVRow {
public:
    string const& operator[](size_t index) const
    {
        return m_data[index];
    }
    size_t size() const
    {
        return m_data.size();
    }
    void readNextRow(istream& str)
    {
        string line;
        getline(str, line);

        stringstream lineStream(line);
        string cell;

        m_data.clear();
        while (getline(lineStream, cell, ';')) {
            m_data.push_back(cell);
        }
    }
    friend istream& operator>>(istream& str, CSVRow& data)
    {
        data.readNextRow(str);
        return str;
    }

private:
    vector<string> m_data;
};

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()) {
            Mat m = imread(path, 1);
            Mat m2;
            cvtColor(m, m2, CV_BGR2GRAY);
            images.push_back(m2);
            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 != 5) {
        cout << argc << endl;
        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 </path/to/csv.ext> -- Path to the CSV file with the id to names." << 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]);
    string fn_csv_names = string(argv[3]);
    int deviceId = atoi(argv[4]);
    // 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);
    }

    ifstream file(fn_csv_names);
    CSVRow row;
    map<int, string> label_name_map;
    while (file >> row) {
        label_name_map[atoi(row[0].c_str())] = row[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 = createFisherFaceRecognizer();
    model->train(images, labels);
    // 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 haar_cascade;
    haar_cascade.load(fn_haar);
    // Get a handle to the Video device:
    VideoCapture video_stream(deviceId);
    //video_stream.open("http://192.168.20.102:8080/video?x.mjpeg");
    // Check if we can use this device at all:
    if (!video_stream.isOpened()) {
        cerr << "VideoStream or Capture Device ID " << deviceId << "cannot be opened." << endl;
        return -1;
    }

    // Holds the current frame from the Video device:
    Mat frame;
    for (;;) {
        video_stream >> frame;
        // Clone the current frame:
        Mat original = frame.clone();
        // Convert the current frame to grayscale:
        Mat gray;
        cvtColor(original, gray, CV_BGR2GRAY);
        // Find the faces in the frame:
        vector<Rect_<int> > faces;
        haar_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?
        for (int i = 0; i < faces.size(); i++) {
            // Process face by face:
            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:
            // Some variables for the predicted label and associated confidence (e.g. distance):
            int predicted_label = -1;
            double predicted_confidence = 0.0;
            model->predict(face_resized, predicted_label, predicted_confidence);
            // And finally write all we've found out to the original image!
            // First of all draw a green rectangle around the detected face:
            rectangle(original, face_i, CV_RGB(0, 255, 0), 1);
            // Create the text we will annotate the box with:
            string s = "UKNOWN";
            if (label_name_map.find(predicted_label) != label_name_map.end()) {
                s = label_name_map[predicted_label];
            }
            string box_text = format("%s with confidence %f", s.c_str(), predicted_confidence);
            // 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(20);
        // Exit this loop on escape:
        if (key == 27)
            break;
    }
    return 0;
}