OpenCV: Use GaussianBlur or Sobel Derivatives on QImage - c++

Question

I hope you could help me.
I' m using QT and try to do a simple detection of edges on a image. But my program crash when i launch
cv::GaussianBlur( src, src, cv::Size(3,3), 0, 0, cv::BORDER_DEFAULT );
or
cv::Sobel( src_gray, grad_x, ddepth, 1, 0, 3, scale, delta, cv::BORDER_DEFAULT );
here is my code:
QImage *image1;
IplImage *cv_image1;
image1 = new QImage("./image.png"); // Format is ARGB32
cv_image1 = QImage2IplImage(image1);
cv::Mat src(cv_image1);
cv::imshow(window_name, src); // Work Well
cv::Mat src_gray;
int scale = 1;
int delta = 0;
int ddepth = CV_16S;
cv::GaussianBlur(src, src, cv::Size(3,3), 0, 0, cv::BORDER_DEFAULT); //Crash Here
cv::imshow( window_name, src);
I think that was a problem of format.
But in another program with QIMAGES in ARGB32 this code work well.
Thank you.

Answer 1

Try going with proper QImage to cv::Mat conversion using this functions and you should be fine (I also included a conversion from cv::Mat to QImage):
cv::Mat cvmat_from_qimage(const QImage& qimage)
{
cv::Mat mat = cv::Mat(qimage.height(), qimage.width(), CV_8UC4, (uchar*)qimage.bits(), qimage.bytesPerLine());
cv::Mat mat2 = cv::Mat(mat.rows, mat.cols, CV_8UC3 );
int from_to[] = { 0,0, 1,1, 2,2 };
cv::mixChannels( &mat, 1, &mat2, 1, from_to, 3 );
return mat2;
}
QImage qimage_from_cvmat(const cv::Mat& mat)
{
cv::Mat rgb;
cvtColor(mat, rgb, CV_BGR2RGB);
return QImage((const unsigned char*)(rgb.data), rgb.cols, rgb.rows, QImage::Format_RGB888);
}

Answer 2

I Found a solution.
That' s weird but when I do:
cvtColor(src, src_gray, CV_RGB2GRAY );
cv::Sobel(src_gray, grad_x, ddepth, 1, 0, 3, scale, delta, cv::BORDER_CONSTANT);
without the cv::GaussianBlur it works well. I just change the last parameter to cv::BORDER_CONSTANT