I want to extract contours from a binary canny edge image.
The original image is:
After applying cvCanny() and cvDilate(), I get the following image:
I need the enclosing box(the entire blue box) to be detected as a contour. I apply cvFindContours() and extract the contour with the largest area. However, when I apply cvFindContours(), it modifies the above canny image as follows:
which is not what I intend to do. It then outputs the largest contour to be the mailbox sign inside the blue box.
What is going wrong? Does cvFindContours() modify the input image? What should be done to get just the enclosing blue box?
Thanks.
Yes, findContours indeed changes the images. If you still need your original image, than use findContours on copy of your image.
Instead of:
findContours(image, contours, mode, method);
Use:
findContours(image.clone(), contours, mode, method);
*Edit (answer to comment): *
It depends on what you define as "largest". If you use area this may be problematic because calling findContours on edge map may result in very long but very thin contours. Better definition of "largest" is contour whose bounding rectangle has biggest area. You can use function called boundingRect to find it. And if you want to find bounding box of all polygons use OR operator between all bounding boxes:
Rect bbox = boundingRect(contours[0]);
for(i=1; i<contours.size(); i++)
bbox = bbox | boundingRect(contours[i]);
Related
i'm using OpenCV 3.4.6 in a c++/Objective C project and given an image with negative rectangular areas, like this one:
I should detect those negative areas, reverse them and finally get the original image.
I tried to use findContours, enhancing the contrast of the original image or adding a threshold but the rectangles are not detected.
Here one of the test i've tried:
Mat contrasted = [self enhanceContrastTo: matOriginal];
Mat thresholded;
threshold(contrasted, thresholded, 125, 241, THRESH_BINARY);
std::vector<std::vector<cv::Point> > contours;
std::vector<Vec4i> hierarchy;
findContours( thresholded, contours, hierarchy, CV_RETR_EXTERNAL, CV_RETR_TREE );
/* contrast method */
+(Mat)enhanceContrastTo:(Mat)image {
cv::Mat lab_image;
cv::cvtColor(image, lab_image, CV_BGR2Lab);
// Extract the L channel
std::vector<cv::Mat> lab_planes(3);
cv::split(lab_image, lab_planes); // now we have the L image in lab_planes[0]
// apply the CLAHE algorithm to the L channel
cv::Ptr<cv::CLAHE> clahe = cv::createCLAHE();
// clahe->setClipLimit(4);
clahe->setClipLimit(3);
cv::Mat dst;
clahe->apply(lab_planes[0], dst);
// Merge the the color planes back into an Lab image
dst.copyTo(lab_planes[0]);
cv::merge(lab_planes, lab_image);
// convert back to RGB
cv::Mat image_clahe;
cv::cvtColor(lab_image, image_clahe, CV_Lab2BGR);
return image_clahe;
}
The rectangles are clearly visible to the naked eye, I hope that opencv can also identify them but I don't know how.
Any idea?
Thanks
This particular question isn't too complicated but even minor variants can get complex. I can advise you on a couple of simple ideas that should suffice to solve the problem.
1) Instead of contour you can check whether neighboring points are close to reverse - this should filter out most irrelevant edges. But just checking for near-reverse is not sufficient as monotone grey area (127) fits the criteria too. Require also minimal threshold difference.
2) Since rectangles are parallel to axes - you can simply go along each row and column and count the number of pixels that are potentially edges of the reversed rectangles. It is better not to just count the number - but to check whether you have continuous large sequences of such pixels and record where exactly these segments are.
3) Use the found segments (or just indexes of rows and columns) of reversed edge-pixels to make candidates for reversed rectangles and then make final verifications.
This is but an algo draft - it will surely require refining. I am not sure why you wanted to use the contour function, tho.
I am working with binary images from CASIA database and opencv in a C++ project. I am looking for a way of extracting only the silhouette(the bounding box containing the silhouette). The original images are 240x320 and my goal is to get only the silhouette in a new image (let’s say 100x50 size).
My first idea would be to get the minimum and maximum position of “white” pixels on rows and columns and get the pixels inside this rectangle in a new image, but I consider this not efficient at all. If you have any suggetion, I would be more than happy to hear it. On the left is the input and on the right is the output.
You can use the built-in OpenCV functionalities to find contours from your binary image:
e.g.
// using namespace cv;
vector<vector<Point> > contours;
vector<Vec4i> hierarchy;
findContours( your_binary_mat, contours, hierarchy, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_SIMPLE );
Note this will look for external contours (ignores inner contours which for the image above don't apply anyway) and retrieve a simplified approximation of the points.
Once you access the contour you can use either boundingRect() or minAreaRect() (wether you need the bounding box rotated or not).
I'm trying solve the recognition problem with a help OpenCV library for C++.
I have a some text(below) and i want to separate each symbol in this text using by cvFindContours(...) function. After, I want to send each separated symbol on the input of neural network for recognition it. It's all ok. I will can get all contours in my image and i can drawn it on my image with a help cvDrawContours(...) function(below). But cvFindContours(...) returns unordered sequence(pointer on the first contour in this sequence) where contains all the found contours. For my task order is very important.
CVAPI(int) cvFindContours( CvArr* image, CvMemStorage* storage, CvSeq** first_contour,
int header_size CV_DEFAULT(sizeof(CvContour)),
int mode CV_DEFAULT(CV_RETR_LIST),
int method CV_DEFAULT(CV_CHAIN_APPROX_SIMPLE),
CvPoint offset CV_DEFAULT(cvPoint(0,0)));
-image- source image
-storage- for storing where contains contours
-first_contour- pointer to the first contour in the storage
-mode- mode of search (I use the CV_RETR_EXTERNAL for search external contours)
-method- method of approximation (I'm using the CV_CHAIN_APPROX_SIMPLE by default)
How can I make the cvFindContours(...) function that returns the contours in the order in which they in the picture? Is it possible?
Thanks!
You can't directly force findContours to yield contours in a certain order (I mean there is no parameter to tune this in the function call).
To sort your contours in a "read text" order, you could do a loop which goes through all your contours and retrieves for each contour the top-leftest point, either by directly going through all points in each contour object, or by using a boundingbox (see minAreaRect for example).
Once you have all these points, sort them from left to right and bottom to top (some adjustments will probably have to be made, like detecting all contours starting within a range of heights to be all part of the same text line)
You have found bounding rectangles for all the contours present in your image. Instead of going about with the left-most point approach, you can sort your contours based on the centroid of each contour, which is more robust since your approach is being for text.
THIS ANSWER from the OpenCV community might help provide a start
Ok sorry for asking pretty much the same question again but I've tried many methods and I still can't do what I'm trying to do and I'm not even sure it's possible with opencv alone.
I have rotated an image and I want to copy it inside another image. The problem is that no matter what way I crop this rotated image it always copies inside this second image with a non rotated square around it. As can be seen in the image below.(Forget the white part thats ok). I just want to remove the striped part.
I believe my problem is with my ROI that I copy the image to as this ROI is a rect and not a RotatedRect. As can be seen in the code below.
cv::Rect roi(Pt1.x, Pt1.y, ImageAd.cols, ImageAd.rows);
ImageAd.copyTo(ImageABC(roi));
But I can't copyTo with a rotatedRect like in the code below...
cv::RotatedRect roi(cent, sizeroi, angled);
ImageAd.copyTo(ImageABC(roi));
So is there a way of doing what I want in opencv?
Thanks!
After using method below with masks I get this image which as seen is cut off by the roi in which I use to say where in the image I want to copy my rotated image. Basically now that I've masked the image, how can I select where to put this masked image into my second image. At the moment I use a rect but that won't work as my image is no longer a rect but a rotated rect. Look at the code to see how I wrongly do it at the moment (it cuts off and if I make the rect bigger an exception is thrown).
cv::Rect roi(Pt1.x, Pt1.y, creditcardimg.cols, creditcardimg.rows);
creditcardimg.copyTo(imagetocopyto(roi),mask);
Instead of ROI you can use mask to copy,
First create mask using rotated rect.
Copy your source image to destination image using this mask
See below C++ code
Your rotated rect and I calculated manually.
RotatedRect rRect = RotatedRect(Point2f(140,115),Size2f(115,80),192);
Create mask using draw contour.
Point2f vertices[4];
rRect.points(vertices);
Mat mask(src.rows, src.cols, CV_8UC1, cv::Scalar(0));
vector< vector<Point> > co_ordinates;
co_ordinates.push_back(vector<Point>());
co_ordinates[0].push_back(vertices[0]);
co_ordinates[0].push_back(vertices[1]);
co_ordinates[0].push_back(vertices[2]);
co_ordinates[0].push_back(vertices[3]);
drawContours( mask,co_ordinates,0, Scalar(255),CV_FILLED, 8 );
Finally copy source to destination using above mask.
Mat dst;
src.copyTo(dst,mask);
I am currently working on image processing project. I am using Opencv2.3.1 with VC++.
I have written the code such that, the input image is filtered to only blue color and converted to a binary image. The binary image has some small objects which I don't want. I wanted to eliminate those small objects, so i used openCV's cvFindContours() method to detect contours in Binary image. but the problem is I cant eliminate the small objects in the image output. I used cvContourArea() function , but didn't work properly.. , erode function also didn't work properly.
So please someone help me with this problem..
The binary image which I obtained :
The result/output image which I want to obtain :
Ok, I believe your problem could be solved with the bounding box demo recently introduced by OpenCV.
As you have probably noticed, the object you are interested at should be inside the largest rectangle draw in the picture. Luckily, this code is not very complex and I'm sure you can figure it all out by investigating and experimenting with it.
Here is my solution to eliminate small contours.
The basic idea is check the length/area for each contour, then delete the smaller one from vector container.
normally you will get contours like this
Mat canny_output; //example from OpenCV Tutorial
vector<vector<Point> > contours;
vector<Vec4i> hierarchy;
Canny(src_img, canny_output, thresh, thresh*2, 3);//with or without, explained later.
findContours(canny_output, contours, hierarchy, CV_RETR_TREE, CV_CHAIN_APPROX_SIMPLE, Point(0,0));
With Canny() pre-processing, you will get contour segments, however each segment is stored with boundary pixels as a closed ring. In this case, you can check the length and delete the small one like
for (vector<vector<Point> >::iterator it = contours.begin(); it!=contours.end(); )
{
if (it->size()<contour_length_threshold)
it=contours.erase(it);
else
++it;
}
Without Canny() preprocessing, you will get contours of objects.
Similarity, you can also use area to define a threshold to eliminate small objects, as OpenCV tutorial shown
vector<Point> contour = contours[i];
double area0 = contourArea(contour);
this contourArea() is the number of non-zero pixels
Are you sure filtering by small contour area didn't work? It's always worked for me. Can we see your code?
Also, as sue-ling mentioned, it's a good idea to use both erode and dilate to approximately preserve area. To remove small noisy bits, use erode first, and to fill in holes, use dilate first.
And another aside, you may want to check out the new C++ versions of the cv* functions if you weren't aware of them already (documentation for findContours). They're much easier to use, in my opinion.
Judging by the before and after images, you need to determine the area of all the white areas or blobs, then apply a threshold area value. This would eliminate all areas less than the value and leave only the large white region which is seen in the 2nd image. After using the cvFindContours function, try using 0 order moments. This would return the area of the blobs in the image. This link might be helpful in implementing what I've just described.
http://www.aishack.in/2010/07/tracking-colored-objects-in-opencv/
I believe you can use morphological operators like erode and dilate (read more here)
You need to perform erosion with a kernel size near to the radius of the circle on the right (the one you want to eliminate).
followed by dilation using the same kernel to fill the gaps created by the erosion step.
FYI erosion followed by dilation using the same kernel is called opening.
the code will be something like this
int erosion_size = 30; // adjust with you application
Mat erode_element = getStructuringElement( MORPH_ELLIPSE,
Size( 2*erosion_size + 1, 2*erosion_size+1 ),
Point( erosion_size, erosion_size ) );
erode( binary_img, binary_img, erode_element );
dilate( binary_img, binary_img, erode_element );
It is not a fast way but may be usefull in some cases.
There is a new function in OpencCV 3.0 - connectedComponentsWithStats. With it we can get area of connected components and eliminate unnecessary. So we can easy remove circle with holes, with the same bounding box as solid circle.