I want to separate a noiseless 1-bit (black and white) image with white circles based on the concave part of the outline.
Please refer to the picture below.
This is the white object to separate:
The target result is:
Here is my implementation with the watershed algorithm:
The above result is not what I want.
If the size of the separated objects is similar, my algorithm is fine, but if the size difference is large, a problem occurs as shown in the picture above.
I would like to implement an opencv algorithm that can segment a region like the second picture.
However, the input photo is not necessarily a perfect circle.
It can be oval like the picture below:
Or it can be squished:
However, I would like to separate it based on the concave part of the outline anyway.
I think it can be implemented by using the distanceTransform function well, but I'm not sure how to approach it.
Please let me know which way to refer.
Thank you.
Here is an algorithm which should give you a good start.
Compute all contours.
For each contour compute the convexity defects. If there is no defect the contour is an isolated circle and you can segment it out.
After you handled all the isolated circles, you can work out the remaining contours by counting the convexity defects: the number of circles N for each contour is the number of convexity defects divided by 2.
Use a clustering algorithm (https://scikit-learn.org/stable/modules/generated/sklearn.mixture.GaussianMixture.html should do well given the shapes you have) and cluster the "white" points using N as the number of clusters to be found.
If you want to find the minimal openings, you can use a medial axis based approach.
Pseudo code:
compute contours of bitmap
compute medial-axis of bitmap
for each point on medial-axis:
get minimal distance d from medial axis algorithm
for each local minimum of distance d:
get two points on bitmap contours with minimal distance that are at least d apart from each other
use these points for deviding line
If you need a working implementation in python, please let me know. I would use skimage lib. For other languages you might have to implement medial-axis on your own. But that shouldn't be a big deal.
I have the following binary image of a disk, and extracted the border of it:
How can I calculate the center and the radius of the circle? I already tried some methods with cv2.HoughCircles() and cv2.findContours() + cv2.fitEllipse(), however these don't work with images where the circle center is far outside of the image.
You can find center of circle from 3 points, but for robust solution it is better to use ransac method. It uses a set of different solutions, for all your bounding points set and will give you more accurate solution. For instance check : here
While using hough circle, I didn't quite understand how to define the parameters for hough circles? I also don't even know what the parameters they signify. As far as I know
image: It is the source image
method: It is the process it uses to detect the circles,(are there any other than hough gradient)
minDist: is the min. distance between two centres of a circle
minRadius: It the min radius of the circles
maxRadius: It is the max radius
The rest of the parameters I don't even understand. Can someone help to explain this to me.
Good question!
This is an example of HoughCircles() function from opencv-python tutorials. Lets look at it in details
HoughCircles(image, method, dp, minDist[, param1[, param2[, minRadius[, maxRadius]]]]])
image
This is the input image you want to detect circles from. It's strongly recommended that the image is grayscaled because HoughCircles() uses Canny() function to detect edges in image.
method
This is the mathematical formula used to find circles. The only available formula in HoughCircle is cv2.HOUGH_GRADIENT so you don't have other choice but using it.
dp
Check out this answer here. If you couldn't understand it don't worry. Hough Transform is broad subjet and I advise you to research it more in detail if you want to know what this variable mean, but anyway, this variable should be between 0 and 2 and is of type double, so try using numbers like 0.6 or 1.3.
minDist
This is the minimum distance between the center of circles to be detected. How close are the circles in your image? Do you want the function to detect closely connected circles or far between circles?
param1 and param2
As mentioned before, HoughCircles() internally uses Canny() function. These parameters specify how aggressively you want to detect the edges.
The thresholder used in the Canny operator uses a method called
"hysteresis". Most thresholders used a single threshold limit, which
means if the edge values fluctuate above and below this value the line
will appear broken (commonly referred to as ``streaking''). Hysteresis
counters streaking by setting an upper and lower edge value limit.
Considering a line segment, if a value lies above the upper threshold
limit it is immediately accepted. If the value lies below the low
threshold it is immediately rejected. Points which lie between the two
limits are accepted if they are connected to pixels which exhibit
strong response.
minRadius and maxRadius
The size of circle is represented by its radius. The bigger the radius the bigger the circle and vice versa. These parameters specify the range of sizes of the circles you want to detect.
Finally
When you're using HoughCircles() and other similar functions, a lot of time you will spend will be on tuning these parameters to find the best combination of numbers to detect the circles in your image. So don't be frustrated if you think your parameters are wrong.
I have a webcam looking down on a surface which rotates about a single-axis. I'd like to be able to measure the rotation angle of the surface.
The camera position and the rotation axis of the surface are both fixed. The surface is a distinct solid color right now, but I do have the option to draw features on the surface if it would help.
Here's an animation of the surface moving through its full range, showing the different apparent shapes:
My approach thus far:
Record a series of "calibration" images, where the surface is at a known angle in each image
Threshold each image to isolate the surface.
Find the four corners with cv2.approxPolyDP(). I iterate through various epsilon values until I find one that yields exactly 4 points.
Order the points consistently (top-left, top-right, bottom-right, bottom-left)
Compute the angles between each points with atan2.
Use the angles to fit a sklearn linear_model.linearRegression()
This approach is getting me predictions within about 10% of actual with only 3 training images (covering full positive, full negative, and middle position). I'm pretty new to both opencv and sklearn; is there anything I should consider doing differently to improve the accuracy of my predictions? (Probably increasing the number of training images is a big one??)
I did experiment with cv2.moments directly as my model features, and then some values derived from the moments, but these did not perform as well as the angles. I also tried using a RidgeCV model, but it seemed to perform about the same as the linear model.
If I'm clear, you want to estimate the Rotation of the polygon with respect to the camera. If you know the length of the object in 3D, you can use solvePnP to estimate the pose of the object, from which you can get the Rotation of the object.
Steps:
Calibrate your webcam and get the intrinsic matrix and distortion matrix.
Get the 3D measurements of the object corners and find the corresponding points in 2d. Let me assume a rectangular planar object and the corners in 3d will be (0,0,0), (0, 100, 0), (100, 100, 0), (100, 0, 0).
Use solvePnP to get the rotation and translation of the object
The rotation will be the rotation of your object along the axis. Here you can find an example to estimate the pose of the head, you can modify it to suit your application
Your first step is good -- everything after that becomes way way way more complicated than necessary (if I understand correctly).
Don't think of it as 'learning,' just think of it as a reference. Every time you're in a particular position where you DON'T know the angle, take a picture, and find the reference picture that looks most like it. Guess it's THAT angle. You're done! (They may well be indeterminacies, maybe the relationship isn't bijective, but that's where I'd start.)
You can consider this a 'nearest-neighbor classifier,' if you want, but that's just to make it sound better. Measure a simple distance (Euclidean! Why not!) between the uncertain picture, and all the reference pictures -- meaning, between the raw image vectors, nothing fancy -- and choose the angle that corresponds to the minimum distance between observed, and known.
If this isn't working -- and maybe, do this anyway -- stop throwing away so much information! You're stripping things down, then trying to re-estimate them, propagating error all over the place for no obvious (to me) benefit. So when you do a nearest neighbor, reference pictures and all that, why not just use the full picture? (Maybe other elements will change in it? That's a more complicated question, but basically, throw away as little as possible -- it should all be useful in, later, accurately choosing your 'nearest neighbor.')
Another option that is rather easy to implement, especially since you've done a part of the job is the following (I've used it to compute the orientation of a cylindrical part from 3 images acquired when the tube was rotating) :
Threshold each image to isolate the surface.
Find the four corners with cv2.approxPolyDP(), alternatively you could find the four sides of your part with LineSegmentDetector (available from OpenCV 3).
Compute the angle alpha, as depicted on the image hereunder
When your part is rotating, this angle alpha will follow a sine curve. That is, you will measure alpha(theta) = A sin(theta + B) + C. Given alpha you want to know theta, but first you need to determine A, B and C.
You've acquired many "calibration" or reference images, you can use all of these to fit a sine curve and determine A, B and C.
Once this is done, you can determine theta from alpha.
Notice that you have to deal with sin(a+Pi/2) = sin(a). It is not a problem if you acquire more than one image sequentially, if you have a single static image, you have to use an extra mechanism.
Hope I'm clear enough, the implementation really shouldn't be a problem given what you have done already.
I know how to do basic Canny edge detection using OpenCV. However I need to discard all edges that do not fall within 15 degrees of a predetermined angle.
Any help would be greatly appreciated.
Its an old question but here is the process you should use.
1]Start by filter your source image (back-ground subtract/color/etc)
2]Apply a generic Edge detector or a steerable filter or (if you want to get some really good result & are doing it for research purposes look for Phase Strectch Transform Algorithm
3]Save those line in a vector/whatever
4]Create a circle drawing algorithm (here is the main idea)
Your circle drawing algorithm (CDA further) will take every point returned by your edge filter.
For each point it will build circles of a variable diameter [Dmin;Dmax] based on the max/min distance you can accept for two points be considered on the same line.
If no next-pixel are present in the circle octant corresponding to your angle, simply dismiss it.
Once you have your lines that match your angle you can sort them by length to dismiss line probably due to noise.
You should also note that there is other methods, this method as some good aspect:
1- Its robust against noise & low quality images/video
2- Its CUDA compliant (i.e. easy to push in parallel processing).
3-Its fast and roughly more accurate than most basic line detectors.