blink's profile - activity

I am still quite new to OpenCV and c++ programming in general. I am doing on a project that stores image from my webcam. I was able to display camera image and detect faces somehow but I don't know how to save the images.

What should i do in order for the faces that my webcam detects gets captured and store into my computer?

Using my code below, how can i edit it to:

1. capture an image from the live cam 5 seconds after detecting face
2. save the images to a folder in jpg format

Thanks so much for any help you can provide!

my code:

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

using namespace cv;
using namespace std;

int main(int argc, char** argv)
{
    // capture from web camera init

    VideoCapture cap(0);
    cap.open(0);

    Mat img;

    // Initialize the inbuilt Harr Cascade frontal face detection
    // Below mention the path of where your haarcascade_frontalface_alt2.xml     file is located

    CascadeClassifier face_cascade;
    face_cascade.load("C:/OpenCV/sources/data/haarcascades/haarcascade_frontalface_alt2.xml");
    // i tried changing this line to match my folder in C Drive

    for (;;)
    {

        // Image from camera to Mat

        cap >> img;

        // Just resize input image if you want
        resize(img, img, Size(1000, 640));

        // Container of faces
        vector<Rect> faces;

        // Detect faces
        face_cascade.detectMultiScale(img, faces, 1.1, 2, 0 | CV_HAAR_SCALE_IMAGE, Size(140, 140));
        // error message appears here

        //Show the results
        // Draw circles on the detected faces
        for (int i = 0; i < faces.size(); i++)
        {
            Point center(faces[i].x + faces[i].width*0.5, faces[i].y + faces[i].height*0.5);
            ellipse(img, center, Size(faces[i].width*0.5, faces[i].height*0.5), 0, 0, 360, Scalar(255, 0, 255), 4, 8, 0);
        }

        // To draw rectangles around detected faces 
        /* for (unsigned i = 0; i<faces.size(); i++)
        rectangle(img,faces[i], Scalar(255, 0, 0), 2, 1);*/

        imshow("wooohooo", img);
        int key2 = waitKey(20);

    }

    return 0;
}

I am still quite new to OpenCV and c++ programming in general. I am doing on a project that stores image from my webcam. I was able to display camera image and detect faces somehow but I don't know how to save the images.

What should i do in order for the faces that my webcam detects gets captured and store into my computer?

Using my code below, how can i edit it to:

1. capture an image from the live cam 5 seconds after detecting face
2. save the images to a folder in jpg format

Thanks so much for any help you can provide!

my code:

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

using namespace cv;
using namespace std;

int main(int argc, char** argv)
{
    // capture from web camera init

    VideoCapture cap(0);
    cap.open(0);

    Mat img;

    // Initialize the inbuilt Harr Cascade frontal face detection
    // Below mention the path of where your haarcascade_frontalface_alt2.xml     file is located

    CascadeClassifier face_cascade;
    face_cascade.load("C:/OpenCV/sources/data/haarcascades/haarcascade_frontalface_alt2.xml");
    // i tried changing this line to match my folder in C Drive

    for (;;)
    {

        // Image from camera to Mat

        cap >> img;

        // Just resize input image if you want
        resize(img, img, Size(1000, 640));

        // Container of faces
        vector<Rect> faces;

        // Detect faces
        face_cascade.detectMultiScale(img, faces, 1.1, 2, 0 | CV_HAAR_SCALE_IMAGE, Size(140, 140));
        // error message appears here

        //Show the results
        // Draw circles on the detected faces
        for (int i = 0; i < faces.size(); i++)
        {
            Point center(faces[i].x + faces[i].width*0.5, faces[i].y + faces[i].height*0.5);
            ellipse(img, center, Size(faces[i].width*0.5, faces[i].height*0.5), 0, 0, 360, Scalar(255, 0, 255), 4, 8, 0);
        }

        // To draw rectangles around detected faces 
        /* for (unsigned i = 0; i<faces.size(); i++)
        rectangle(img,faces[i], Scalar(255, 0, 0), 2, 1);*/

        imshow("wooohooo", img);
        int key2 = waitKey(20);

    }

    return 0;
}

I checked the lib files that i should type into the additional dependencies and found out that opencv_world.lib already contained all the files required. That is why i don't know any ways to solve the problem. Moreover, when i try to redo teh whole project with the same coding, i got a different error which says "Severity Code Description Project File Line Suppression State Error LNK2019 unresolved external symbol".

I checked the lib files that i should type into the additional dependencies and found out that opencv_world.lib already contained all the files required. That is why i don't know any ways to solve the problem.

I did try it with opencv_world320d.lib but it did not work for some reason.

Now i got a link error that says cannot open file 'opencv_calib3d245d.lib' even though i did add the required files inside the Additional Dependencies under the Linker option. Is it because i added the wrong link path?

Now i got a link error that says cannot open file 'opencv_calib3d245d.lib' even though i did add the required files inside the Additional Dependencies under the Linker option. Is it because i added the wrong path link?

I used the codings from opencv website but it doesn't work for me. Do you need me to put up the codes to check by any chance?

I have already included the .hpp file in the "Additional Include Paths" of VS project. I did try to use #include "opencv2/face.hpp" before but it gave me more errors which include "unable to open source file". I have also tried using the full path which is "C:Users/Downloads/opencv_contrib-master/opencv_contrib-master/modules/face/include/opencv2/face.hpp"
as well but it also did not work

I am still quite new to OpenCV and i don't really know what functions am i suppose to call. Anyone can help by telling me what i should define? Thanks.

Error i got is:

identifier "createFisherFaceRecognizer" is undefined   
'createFisherFaceRecognizer'identifier not found

facerecognizer.cpp:

#include "opencv2/core.hpp"
#include "C:/OpenCV/build/include/opencv2/face.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/imgproc.hpp"
#include "opencv2/objdetect.hpp"

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

using namespace cv;
using namespace cv::face;
using namespace std;

... line which got error:

    // Create a FaceRecognizer and train it on the given images:
    Ptr<FaceRecognizer> model = createFisherFaceRecognizer();

This code works for me too. I am using OpenCV 3.2.0 with visual-studio-2017

cap >> frame means the captured image will be sent to the frame which will open in a new window

Thanks for the solution and also, i will heed your advice and look through docs. I actually did try and use codes from there before but there was error and so i kept on looking for alternatives, which is my biggest problem. I just don't understand how OpenCV works even though i read up the study materials.

I recently came across this video which shows how to write a face recognition program and i tried using his codes to study how the program works. He indicated to change one of the lines and i followed as he said. I tried changing the line but it sill showed this error.

Assertion failed (!empty()) in cv::CascadeClassifier::detectMultiScale and
cv::Exception at memory location 0x000000000029EE10

Unhandled exception at 0x000007FEFD5CA06D in opencvTry.exe: Microsoft C++ exception: cv::Exception at memory location 0x000000000029EE10. occurred

My program - try.cpp:

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

using namespace cv;
using namespace std;


int main(int argc, char** argv)
{
    // capture from web camera init

    VideoCapture cap(0);
    cap.open(0);

    Mat img;

    // Initialize the inbuilt Harr Cascade frontal face detection
    // Below mention the path of where your haarcascade_frontalface_alt2.xml file is located

    CascadeClassifier face_cascade;
    face_cascade.load("C:\OpenCV\sources\data\haarcascades\haarcascade_frontalface_alt2.xml");    
    // i tried changing this line to match my folder in C Drive

    for (;;)
    {

        // Image from camera to Mat

        cap >> img;

        // obtain input image from source
        cap.retrieve(img, CV_CAP_OPENNI_BGR_IMAGE);

        // Just resize input image if you want
        resize(img, img, Size(1000, 640));

        // Container of faces
        vector<Rect> faces;


        // Detect faces
        face_cascade.detectMultiScale(img, faces, 1.1, 2, 0 | CV_HAAR_SCALE_IMAGE, Size(140, 140));
        // error message appears here


        //Show the results
        // Draw circles on the detected faces

        for (int i = 0; i < faces.size(); i++)
        {
            Point center(faces[i].x + faces[i].width*0.5, faces[i].y + faces[i].height*0.5);
            ellipse(img, center, Size(faces[i].width*0.5, faces[i].height*0.5), 0, 0, 360, Scalar(255, 0, 255), 4, 8, 0);
        }

        // To draw rectangles around detected faces
        /* for (unsigned i = 0; i<faces.size(); i++)
        rectangle(img,faces[i], Scalar(255, 0, 0), 2, 1);*/


        imshow("wooohooo", img);
        int key2 = waitKey(20);

    }
    return 0;
}

make sure that your path to the lib is correct with the correct files included.