elp14sma's profile - activity

I have tried alot , and I'm stuck in getting it run :

after compiling it this is the usage command :

/clandmark/examples/examples$ ./video_input ./ cam 0 output_file.avi cannot open file cam

but I'm getting errors , finally not everyone is expert like you Thanks

How the width and height of the _boundingRect can be changed ? I tried to change values of Rect eyeRect( 5, 5, mSource_Bgr.cols - 10, mSource_Bgr.rows -10 ); the result was not so different

@sturkmen thanks very much for great answer. I will try it and update you thanks again

Hi

I'm trying to do the following :

1.detect face and then eyes
2. after doing somw threshol to the detected eye region obtain morphologyEx (open) of eye region . 3. pass the result of morphologyEx (open) so that I can bound the eye region with a rectangle like this image .

using function below I'm not getting this result .

how can this be done ?

Thanks for help

void find_contour(Mat image)
{

Mat src_mat, gray_mat, canny_mat;
Mat contour_mat;
Mat bounding_mat;


contour_mat = image.clone();
bounding_mat = image.clone();


cvtColor(image, gray_mat, CV_GRAY2BGR);

// apply canny edge detection

Canny(gray_mat, canny_mat, 30, 128, 3, false);

//3. Find & process the contours
//3.1 find contours on the edge image.


vector< vector< cv::Point> > contours;
findContours(canny_mat, contours, RETR_EXTERNAL, CHAIN_APPROX_SIMPLE);

//3.2 draw contours & property value on the source image.


double area, length;
drawContours(contour_mat, contours, -1, cv::Scalar(0), 2);  //draw contours on the image

//3.3 find bounding of each contour, and draw it on the source image.

for (int i = 0; i < contours.size(); ++i)
{

    Rect rect;


    //compute the bounding rect, rotated bounding rect, minum enclosing circle.

    rect = boundingRect(contours[i]);


    //draw them on the bounding image.

    cv::rectangle(bounding_mat, rect, Scalar(255, 0, 0), 2);


}


imshow("Bounding ", bounding_mat);

}

Thanks for answer , I have made some changes to the code in the tutorial :

code

the out was like this image

how can I remove the pink border around the image and the black pixels in the original image showing only borders

Hi

I want to detect contours in this image below , so that the output is like the second image

shuold I use canny detection , how can I get this output

Thanks

@sturkment , thanks very much for you efforts it works now I have two questions :

1. what the following coordinates mean :

   enter code here

      const float EYE_SX = 0.10f;
     const float EYE_SY = 0.19f;
     const float EYE_SW = 0.40f;
     const float EYE_SH = 0.36f;
   

2. If I want to width of the of searchedRightEye like this : image

because it sometimes show hair (if women video ) or background when head moves , how this can be done ?

Hi @berak This is the my code :

code

hi

When I try to run face and eye detection on a video file unhandled exception occurs I don't know why this happeing

can any one help me to solve this

Thanks

I used haar cascade to detect face and then I detected eye region using ROI and without using eye cascade the out put is this image:

for (;;)
{
    capture >> frame;

    std::vector<Rect> faces;
    std::vector<Rect> eyes;
    Mat frame_gray;

    cvtColor(frame, frame_gray, COLOR_BGR2GRAY);
    equalizeHist(frame_gray, frame_gray);

    face_cascade.detectMultiScale(frame_gray, faces, 1.1, 4, CASCADE_SCALE_IMAGE, Size(20, 20));
    size_t i = 0;
    for (i = 0; i < faces.size(); i++) // Iterate through all current elements (detected faces)

    {

        Point pt1(faces[i].x, faces[i].y); // Display detected faces on main window - live stream from camera
        Point pt2((faces[i].x + faces[i].height), (faces[i].y + faces[i].width));
        rectangle(frame, pt1, pt2, Scalar(0, 255, 0), 2, 8, 0);

        // set ROI for the eyes

        Rect Roi = faces[i];

        Roi.height = Roi.height / 4;

        Roi.y = Roi.y + Roi.height;

        Mat eye_region = frame(Roi).clone();

        Mat eye_gray = frame(Roi).clone();

I want to to detect eye location only like this : image or this Image how can I do that ?

Sorry about that , I wanted to show you the code . how can I have ( current frame and previous frame ) to be grayscale and then calculate the difference

using your code , I used cvtColor to convery video frames to gray and calculte the frame difference , when I run it

it throws cv exception at memory location . what is the problem ?

int main(void)

{

cv::Mat frameCurrent, framePrev, frame_gray;

cv::Mat badDiff, frameAbsDiff, frameDif, frameChangeMask;

VideoCapture cap("1.mp4");

cap >> frameCurrent;


framePrev = frameCurrent;
frameAbsDiff = 0;

while (1)
{
    if (frameCurrent.empty())
    {
        std::cout << "Frame1Message->End of sequence" << std::endl;
        break;
    }

    cvtColor(frameCurrent, frame_gray, CV_RGB2GRAY);

    cv::absdiff(frame_gray, framePrev, frameAbsDiff);

    imshow("frameCurrent", frameCurrent);

    imshow("frameAbsDiff", frameAbsDiff);



    if (waitKey(90) == 27)
        break;

    frameCurrent.copyTo(framePrev);
    cap >> frameCurrent;
}



return 0;
   }

@pklab ,If I convert the the the video frames to grayscale and I want to calculate the difference as : current_frame - previous_frame .

1. which one I need to use absdiff or subtract , I know the difference between them but which one should be used .

2. in framePrev = cv::Mat::zeros(frameCurrent.size(), frameCurrent.type());
   here you are creating empty Mat filled with zeros that equals to (frame current rows , columns and data type ) right ?

@pklab ,If I convert the the the video frames to grayscale and I want to calculate the difference as : current_frame - previous_frame . 1. which one I need to use absdiff or subtract , I know the difference between them but which one should be used .

1. in framePrev = cv::Mat::zeros(frameCurrent.size(), frameCurrent.type());
   here you are creating empty Mat filled with zeros that equals to (frame current rows , columns and data type ) right ?

thanks for answer ,

Is the way that I'm getting current frame and previous frame is correct ?

how can I get current frame and previous frame

I want to do basic frame difference like this :

diff = current frame - previous frame

is this correct way to so this ? I"m not sure how to get current and next frame

#include <highgui.h>
#include <iostream>
using namespace cv;

int main()
{

VideoCapture cap("Camouflage/b%05d.bmp");
if(!cap.isOpened())
{
    std::cout<<"failed to open image sequence";
    return 1;
}
char c;
Mat frame1, frame2, frame3;
namedWindow("Original Frames",1);   
namedWindow("Frame Difference",1);
while(1)
{
    cap>>frame1;
    if(frame1.empty())
    {
        std::cout<<"Frame1Message->End of sequence"<<std::endl;
        break;
    }
    cap>>frame2;
    if(frame2.empty())
    {
        std::cout<<"Frame2Message->End of sequence"<<std::endl;
        break;
    }

    frame3=frame1.clone();
    frame3=frame3-frame2;

    imshow("Frame Difference",frame3);
    c=waitKey(90);
    if(c==27)
        break;

    imshow("Original Frames",frame1);
    c=waitKey(90);
    if(c==27)           
         break;
    }

  }