I set my mask from BGR2HSV. I have my image:
How I can change the white color in the mask? So I want to change the white parts with other colors.
Mat mask;
mask = imread("C:\\Users\\...\\Desktop\\...\\mask.png");
if (!img.data)
{
cout << "Could not find the image";
return -1;
}
cvtColor(mask, mask, COLOR_BGR2HSV);
cvtColor(mask, mask, COLOR_HSV2BGR);
imshow("Ergebnis", mask);
waitKey(0);
Between two cvtColor functions, you need to split the image into its 3 channels with split. Looking at the conversion between RGB and HSV, make S channel 0 and choose an H value between [0-180]. Then, merge the channels back.
cv::Mat hsv = mask.clone(); // from your code
std::vector<cv::Mat> hsv_vec;
cv::split(hsv, hsv_vec);
cv::Mat &H = hsv_vec[0];
cv::Mat &S = hsv_vec[1];
cv::Mat &V = hsv_vec[2];
S = 0;
mask = (V > 10); // non-zero pixels in the original image
H(mask) = your_H_value_here; // H is between 0-180 in OpenCV
cv::merge(hsv_vec, hsv);
mask = hsv; // according to your code
As a side note, I suggest using convenient names for variables.
Good Day! I'm using imwrite command to save the image below after cropping them in OpenCV (C++) but it seems like it included the black portion surrounding it in writing. All I want is to save the cropped one. Please help.
Here's my code
Mat mask,draft,res;
int nPixels;
char c=0;
while(true && c!='q') {
imshow("SAMPLE", img);
if(!roi.isSet())
roi.set("SAMPLE");
if (roi.isSet()) {
roi.createMask(img.size());
mask = roi.getMask();
res = mask & img.clone();
imwrite("masked.png",res);
imshow("draft", res);
}
c = waitKey(1);
}
Here is an example how to crop an image and save the croped image (see comment from api55). Maybe that helps you.
cv::Mat img = cv::imread("Path/To/Image/image.png", cv::IMREAD_GRAYSCALE);
if(image.empty())
return -1;
cv::Rect roi(0, 0, 100, 100); // define roi here as x0, y0, width, height
cv::Mat cropedImg(img, roi);
cv::imwrite("Path/To/Save/Location/cropedImage.png", cropedImg);
I am building a scanner feature for my app and binarize the photo of the document with OpenCV:
// convert to greyscale
cv::Mat converted, blurred, blackAndWhite;
converted = cv::Mat(inputMatrix.rows, inputMatrix.cols, CV_8UC1);
cv::cvtColor(inputMatrix, converted, CV_BGR2GRAY );
// remove noise
cv::GaussianBlur(converted, blurred, cvSize(3,3), 0);
// adaptive threshold
cv::adaptiveThreshold(blackAndWhite, blackAndWhite, 255, cv::ADAPTIVE_THRESH_GAUSSIAN_C, cv::THRESH_BINARY, 15 , 9);
The result is okay, but scans from different scanner apps are much better. Especially very small, tiny sized text is much better:
Processed with opencv
Scanned With DropBox
What can I do, to improve my result?
May be the apps are using anti-aliasing to make their binarized output look nicer. To obtain a similar effect, I first tried binarizing the image, but the result didn't look very nice with all the jagged edges. Then I applied pyramid upsampling and then downsampling to the result, and the output was better.
I didn't use adaptive thresholding however. I segmented the text-like regions and processed those regions only, then pasted them to form the final images. It is a kind of local thresholding using the Otsu method or the k-means (using combinations of thr_roi_otsu, thr_roi_kmeans and proc_parts in the code). Below are some results.
Apply Otsu threshold to all text regions, then upsample followed by downsample:
Some text:
Full image:
Upsample input image, apply Otsu threshold to individual text regions, downsample the result:
Some text:
Full image:
/*
apply Otsu threshold to the region in mask
*/
Mat thr_roi_otsu(Mat& mask, Mat& im)
{
Mat bw = Mat::ones(im.size(), CV_8U) * 255;
vector<unsigned char> pixels(countNonZero(mask));
int index = 0;
for (int r = 0; r < mask.rows; r++)
{
for (int c = 0; c < mask.cols; c++)
{
if (mask.at<unsigned char>(r, c))
{
pixels[index++] = im.at<unsigned char>(r, c);
}
}
}
// threshold pixels
threshold(pixels, pixels, 0, 255, CV_THRESH_BINARY | CV_THRESH_OTSU);
// paste pixels
index = 0;
for (int r = 0; r < mask.rows; r++)
{
for (int c = 0; c < mask.cols; c++)
{
if (mask.at<unsigned char>(r, c))
{
bw.at<unsigned char>(r, c) = pixels[index++];
}
}
}
return bw;
}
/*
apply k-means to the region in mask
*/
Mat thr_roi_kmeans(Mat& mask, Mat& im)
{
Mat bw = Mat::ones(im.size(), CV_8U) * 255;
vector<float> pixels(countNonZero(mask));
int index = 0;
for (int r = 0; r < mask.rows; r++)
{
for (int c = 0; c < mask.cols; c++)
{
if (mask.at<unsigned char>(r, c))
{
pixels[index++] = (float)im.at<unsigned char>(r, c);
}
}
}
// cluster pixels by gray level
int k = 2;
Mat data(pixels.size(), 1, CV_32FC1, &pixels[0]);
vector<float> centers;
vector<int> labels(countNonZero(mask));
kmeans(data, k, labels, TermCriteria(CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 10, 1.0), k, KMEANS_PP_CENTERS, centers);
// examine cluster centers to see which pixels are dark
int label0 = centers[0] > centers[1] ? 1 : 0;
// paste pixels
index = 0;
for (int r = 0; r < mask.rows; r++)
{
for (int c = 0; c < mask.cols; c++)
{
if (mask.at<unsigned char>(r, c))
{
bw.at<unsigned char>(r, c) = labels[index++] != label0 ? 255 : 0;
}
}
}
return bw;
}
/*
apply procfn to each connected component in the mask,
then paste the results to form the final image
*/
Mat proc_parts(Mat& mask, Mat& im, Mat (procfn)(Mat&, Mat&))
{
Mat tmp = mask.clone();
vector<vector<Point>> contours;
vector<Vec4i> hierarchy;
findContours(tmp, contours, hierarchy, CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE, Point(0, 0));
Mat byparts = Mat::ones(im.size(), CV_8U) * 255;
for(int idx = 0; idx >= 0; idx = hierarchy[idx][0])
{
Rect rect = boundingRect(contours[idx]);
Mat msk = mask(rect);
Mat img = im(rect);
// process the rect
Mat roi = procfn(msk, img);
// paste it to the final image
roi.copyTo(byparts(rect));
}
return byparts;
}
int _tmain(int argc, _TCHAR* argv[])
{
Mat im = imread("1.jpg", 0);
// detect text regions
Mat morph;
Mat kernel = getStructuringElement(MORPH_ELLIPSE, Size(3, 3));
morphologyEx(im, morph, CV_MOP_GRADIENT, kernel, Point(-1, -1), 1);
// prepare a mask for text regions
Mat bw;
threshold(morph, bw, 0, 255, THRESH_BINARY | THRESH_OTSU);
morphologyEx(bw, bw, CV_MOP_DILATE, kernel, Point(-1, -1), 10);
Mat bw2x, im2x;
pyrUp(bw, bw2x);
pyrUp(im, im2x);
// apply Otsu threshold to all text regions, then upsample followed by downsample
Mat otsu1x = thr_roi_otsu(bw, im);
pyrUp(otsu1x, otsu1x);
pyrDown(otsu1x, otsu1x);
// apply k-means to all text regions, then upsample followed by downsample
Mat kmeans1x = thr_roi_kmeans(bw, im);
pyrUp(kmeans1x, kmeans1x);
pyrDown(kmeans1x, kmeans1x);
// upsample input image, apply Otsu threshold to all text regions, downsample the result
Mat otsu2x = thr_roi_otsu(bw2x, im2x);
pyrDown(otsu2x, otsu2x);
// upsample input image, apply k-means to all text regions, downsample the result
Mat kmeans2x = thr_roi_kmeans(bw2x, im2x);
pyrDown(kmeans2x, kmeans2x);
// apply Otsu threshold to individual text regions, then upsample followed by downsample
Mat otsuparts1x = proc_parts(bw, im, thr_roi_otsu);
pyrUp(otsuparts1x, otsuparts1x);
pyrDown(otsuparts1x, otsuparts1x);
// apply k-means to individual text regions, then upsample followed by downsample
Mat kmeansparts1x = proc_parts(bw, im, thr_roi_kmeans);
pyrUp(kmeansparts1x, kmeansparts1x);
pyrDown(kmeansparts1x, kmeansparts1x);
// upsample input image, apply Otsu threshold to individual text regions, downsample the result
Mat otsuparts2x = proc_parts(bw2x, im2x, thr_roi_otsu);
pyrDown(otsuparts2x, otsuparts2x);
// upsample input image, apply k-means to individual text regions, downsample the result
Mat kmeansparts2x = proc_parts(bw2x, im2x, thr_roi_kmeans);
pyrDown(kmeansparts2x, kmeansparts2x);
return 0;
}
I have image as follows:
I want to detect 5 dials for processing. Hough circles is detecting all other irrelevant circles. to solve this i created a plain image and generated absolute difference with this one. It gave this image:
I drew box around it and final image is:
My code is as follows:
Mat img1 = imread(image_path1, COLOR_BGR2GRAY);
Mat img2 = imread(image_path2, COLOR_BGR2GRAY);
cv::Mat diffImage;
cv::absdiff(img2, img1, diffImage);
cv::Mat foregroundMask = cv::Mat::zeros(diffImage.rows, diffImage.cols, CV_8UC3);
float threshold = 30.0f;
float dist;
for(int j=0; j<diffImage.rows; ++j)
{
for(int i=0; i<diffImage.cols; ++i)
{
cv::Vec3b pix = diffImage.at<cv::Vec3b>(j,i);
dist = (pix[0]*pix[0] + pix[1]*pix[1] + pix[2]*pix[2]);
dist = sqrt(dist);
if(dist>threshold)
{
foregroundMask.at<unsigned char>(j,i) = 255;
}
}
}
cvtColor(diffImage,diffImage,COLOR_BGR2GRAY);
Mat1b img = diffImage.clone();
// Binarize image
Mat1b bin = img > 70;
// Find non-black points
vector<Point> points;
findNonZero(bin, points);
// Get bounding rect
Rect box = boundingRect(points);
// Draw (in color)
rectangle(img1, box, Scalar(0,255,0), 3);
// Show
imshow("Result", img1);
Now the issue is i cant compare plain image with anyother iamge of different sizes. Any pointer to right direction will be very helpful.
Regards,
Saghir A. Khatr
Edit
My plain image is as follows
I want to create a standard sample plain image which can be used with any image to detect that portion...
I want to blend two images using multiband blending but I am not clear to the input parameter of this function:
void detail::Blender::prepare(const std::vector<Point>& corners, const std::vector<Size>& sizes)
In my case ,I just input two warped images with black gap, and with masks all white.(forgive me can not add pictures...)
And I set the two corners (0.0,0.0),because the warped images has been registered.
but my result is not good enough.with obvious seam in the result
can someone tell me why?How can I solve this problem?
I'm not sure what do you mean when you say "my result is not good enough". It's better to watch that result, but I'll try to guess. My main part of code, which makes panorama, looks like this:
void makePanorama(Rect bounding_box, vector<Mat> images, vector<Mat> homographies, vector<vector<Point>> corners) {
detail::MultiBandBlender blender;
blender.prepare(bounding_box);
Mat mask, bigImage, curImage;
for (int i = 0; i < (int)images.size(); ++i) {
warpPerspective(images[i], curImage, homographies[i],
bounding_box.size(), INTER_LINEAR, ORDER_TRANSPARENT);
mask = makeMask(curImage.size(), corners[i], homographies[i]);
blender.feed(curImage.clone(), mask, Point(0, 0));
}
blender.blend(bigImage, mask);
bigImage.convertTo(bigImage, (bigImage.type() / 8) * 8);
imshow("Result", bigImage);
waitKey();
}
So, prepare blender and then loop: warp image, make the mask after warped image and feed blender. At the end, turn this blender on and that's all. I met two problems, which influence on my result badly. May be you have one of them or both.
The first is type. My images had CV_16SC3, and after blending you need to convert blended image type into unsigned one. Like this
bigImage.convertTo(bigImage, (bigImage.type() / 8) * 8);
If you not, the result image would be gray.
The second is borders. In the beginning, my function makeMask was calculating non-black area of warped images. As a result, the one could see borders of the warped images on the blended image. The solution is to make mask smaller than non-black warped image area. So, my function makeMask is looks like this:
Mat makeMask(Size sz, vector<Point2f> imageCorners, Mat homorgaphy) {
Scalar white(255, 255, 255);
Mat mask = Mat::zeros(sz, CV_8U);
Point2f innerPoint;
vector<Point2f> transformedCorners(4);
perspectiveTransform(imageCorners, transformedCorners, homorgaphy);
// Calculate inner point
for (auto& point : transformedCorners)
innerPoint += point;
innerPoint.x /= 4;
innerPoint.y /= 4;
// Make indent for each corner
vector<Point> corners;
for (int ind = 0; ind < 4; ++ind) {
Point2f direction = innerPoint - transformedCorners[ind];
double normOfDirection = norm(direction);
corners[ind].x += settings.indent * direction.x / normOfDirection;
corners[ind].y += settings.indent * direction.y / normOfDirection;
}
// Draw borders
Point prevPoint = corners[3];
for (auto& point : corners) {
line(mask, prevPoint, point, white);
prevPoint = point;
}
// Fill with white
floodFill(mask, innerPoint, white);
return mask;
}
I took this pieces of code from my real code, so I could possibly forget to specify something. But I hope, the idea of how to work with MultiBandBlender is clear.