I have a variety of contours, from which I need to draw masks. To do so, I need to use CV_FILLED when drawing the contours. However, my contours aren't closed - as in they aren't complete polygons, so the CV_FILLED thing won't work. Does anyone have any suggestions on how I can "close" my contours?
PS: For clarification, by closing I mean all segments aren't joined. Unlike a polygon, where the shape is closed off, mine is open.
In addition to trying convexHull, you can also look at trying the morphology operators erode and dilate. You can apply the erosion or dilation operators multiple times by using the iterations parameter.
Also, could you post the image with the objects you are trying to segment?
Related
I'm trying to extract the contour of some traffic signs. The images pass through several steps in order to get a good segmented image. In the final step before applying Canny method I get this image:
After applying Canny I get this image:
The algorithm performs as expected except the top left image for which returns an open contour.
So, my question is, is there any way to use Canny in a manner that the top left image returns an closed contour?
If you already have a binary image, Canny does not give much more information. Canny is useful for finding edges in grayscale images (it decides if a gradient is an edge or not), if the image is black and white, Canny will return the edges that you already have,
I think that you need to use findContours(), which depending on the parameters will return only white or black objects, with or without the holes. It also handles the edges of the image.
Image boundary conditions are problematic in most cases. In this particular case, I would try padding the original image with some extra pixels around the image. Depending on how you add those padding pixels, you should get a complete contour around the signs.
You can use Morphological Transformations before and after applying Canny Edge Detection to manipulate the result.
I am using OpenCV-C++ and 1) I want to approximate the detected contours using findContours by only horizontal or vertical lines, and not by curves, as in floor plans. So can you suggest a method for the same.
2) Is there a way to remove smaller contours like tree borders, which can automate the process for every image, since removing the smaller areas with findContours() can lead to elimination of walls with smaller dimensions.
http://property.magicbricks.com/microsite/buy/provident-welworth/floor-plan.html
On what sort of image do you use the find contours? I assume you did follow this example..
findContour example
if not, please clarify.
However, why not try to first find all horizontal and vertical edges with the corresponding filters? Afterwards you can still try to find contours with the findContours function. Or you can use the hough transform, also available in opencv. hough lines within the hough lines you can easily eliminate smaller line segments.
for 2) what do youi mean by tree borders? you mean the contours of a tree on an image? it would be very helpful if you could provide an example image.
Cheers
I'm trying to remove foreground from two images, here's a sample pair of images:
As you can see, the Budweiser bottle is removed from the scene before the second shot is taken.
These photos were captured from a pinhole camera (iPhone), and, the tricky part is I'm hand-holding the camera, so it cannot be guaranteed that the images are perfectly aligned pixel by pixel, so a simple minus-threshold method will not work.
Then, I've decided to perform image registration using findHomography and warpPerspective from OpenCV, here's the result image:
This image is warped with the matrix I've got from findHomography, it kind of improved the alignment quality, but still not that aligned so I can use a simple way to remove the foreground.
So, finally, I decided to implement a "fuzzy-minus" algorithm: for every pixel in image1, I'll look through a 7x7 neighbour in image2 (a 7 by 7 kernel?), using the minimal difference in grayscale as the result of minus, and threshold the result into binary image, here's what I've got:
And the result is still not good. Notice the white wholes in the bottle, this is produced due to similar grayscale value of foreground and background. So I'm not sure what to do now.
I can think of two ways to solve the problem, the first is to get a better aligned pair of images, and simply minus the pairs; the second is to use a more robust way to extract the foreground.
Can anyone give me some advice on how to deal with this kind of problem? I believe there should be some state-of-art algorithms or processing pipelines, but after googling around, I get nothing.
I'm using OpenCV with C++, it would be fantastic if you can tell me how to do it with these tools in hand.
Big big thanks in advance!
The problem is not in your algorithm. You are having problem because the two scenes were not taken from exactly the same angle, as shown in the animation below. This slight difference highlight the edges in the subtraction.
You need a static camera in order to apply this approach.
I suggest using mathematical morphology on the mask that you got to get rid of the artifacts.
Try applying both opening and closing to get rid of the black and the white small regions.
Mathematical Morphology
Mathematical Morphology in opencv
The difference between the two picture is pretty huge, so you will need to use a large structure element, but I don't think you will be able to get rid of the shadow.
For the two large strips in the background, you may try to use a horizontally shaped structure element as well.
Edit
Is it possible to produce a grayscale image instead of a binary image? if yes, you may try to experiment with the hat method for the shadow, but I am not sure about this point.
This is what I got using two different structure elements for closing THEN opening
Mat mask = imread("mask.jpg",CV_LOAD_IMAGE_GRAYSCALE);
morphologyEx(mask,mask,MORPH_CLOSE,getStructuringElement(CV_SHAPE_ELLIPSE,Size(50,10)));
morphologyEx(mask,mask,MORPH_OPEN,getStructuringElement(CV_SHAPE_ELLIPSE,Size(10,50)));
imshow("open",mask);
imwrite("maskopenclose.jpg",mask);
I would suggest optical flow for alignment and OpenCV's background subtraction algorithm:
http://docs.opencv.org/trunk/doc/tutorials/video/background_subtraction/background_subtraction.html
I suggest that instead of using findHomography try using some of openCV's stereo correspondence functions: http://docs.opencv.org/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.html
there is a sample code here: https://github.com/Itseez/opencv/blob/master/samples/cpp/stereo_calib.cpp
I've been trying to find the contour of a single shape in a very plain background using OpenCV's findContour (I'd like to use the C++ syntax). However, it keeps on making its outline a contour and not the shape itself. I'm thinking it's because of the white edge resulted from Canny which doesn't make the shape closed.
Case A: Shape is by the image's edge
(This is not the actual input image but a simpler input image to illustrate this problem.)
Case B: Background surrounds the shape
There are the main functions I used:
findContours( grayImage, contours, hierarchy, RETR_LIST,CHAIN_APPROX_SIMPLE);
approxPolyDP(Mat(contours.at(largestContourIndex)),poly,3,true);
drawContours(output, contours, largestContourIndex, RGB(250,0,100), -1, 8, hierarchy, 0, Point() );
EDIT: Skipping edge detection gives the contour I need but I need to have the best contour approximate I can get.
Thanks in advance.
Did you try playing around with morphology operations?
If your basic problem is that the contour you're getting is on the outside of the object instead of the inside, and especially if your object are made out of so clear-cut and mostly regular shapes, than morphology might help.
I know OpenCV has implementations of dilation and erosion, as well as opening and closing operations. A very simple approach that might work in your situation is just eroding the shape a little bit (maybe 1-2-3 iterations) and then doing exactly what you are doing already. Hopefully, then, you'll get the outer contours of the eroded shape, that should actually be the inner contours of the original shape.
I think OpenCV actually implements even some more complex morphology, but as always, try the simple stuff first :D
It seems to me that the contour you are looking for is probably detected, but you are not using it. Instead you are using the largest contour. Try plotting all found contours one by one and see if it's in there.
If it is not, try inverting the canny image and repeating the process.
I still haven't found the reason why I can't get the shape contour but I found a workaround. After doing erosion and dilation, I basically have to draw a border or a rectangle on the outermost pixels of the input image for the background to surround the shape, ...
rectangle(input,Point(0,0),Point(input.cols-1,input.rows-1),Scalar(0,0,0),1,8,0);
... hence, letting Canny draw a closed shape outline and giving me the shape contour I want. I am still trying to successfully invert Canny's output like what #dvhamme has suggested but it's still giving me errors. It would be better if somebody points out how to properly get or access the shape contour but thanks everyone for the help.
I need to find all contours in an image. I know the whole findcontours () and drawContours () thing, but its using the Canny edge detector that I am having trouble with. To use find contours, you either need to use canny edge detection or threshold the image. I cannot threshold the image because this would result in several edges getting blurred out ("merging" of the edges). So I decided to use Canny Edge detection. However, when I do use it instead of getting perfect edges, I get a variety of lines with gaps in them. This prevents me from getting good contours For example instead of getting the edges of a square, I would get 4 separate lines separated by small gaps resulting in me getting 4 contours instead of one. I tried dilating, opening, closing, Gaussian blurring and basically every morphological operator, but none of these are doing the job. Some do not merge the lines, while some merge the lines with non-relevant lines too. So I was wondering does anyone have a solution on how I can get actual contours from Canny Edge detection, or if not does someone have any alternatives to get all the contours from an image?
make blob, then contours come with it. :)
http://code.google.com/p/cvblob/