I'm currently working with Hough Circles. Are there any methods to automatically find suitable parameters for the Hough circles? Right now, I am just manually changing values until it draws the circles correctly.
I think you should also look at http://www.cse.yorku.ca/~kosta/CompVis_Notes/isophote_curvature.pdf and http://www.science.uva.nl/research/publications/2008/ValentiCVPR2008/CVPR%2008.pdf
This will help you find isophote curvature, values for your image. Curvature is inverse of curve radius at a point. After you calculate isophote curvature values for every pixel, you'll have range of radius values you should check.
If you are able to evaluate the output of Hough Circles automatically, a brute force search should be enough for most of the cases. Just loop over all possibilities for all parameters and take the values that gave the best result.
If you need to speed things up, you can reduce the space search by locking some parameters to values you already know work fine or reducing its range.
Another option for more accurate searching is using a Genetic Algorithm.
If you have an idea what size circles you are looking for, then it would be best to set min_radius and max_radius accordingly. Otherwise, it will return anything circular of any size and your total purpose is destroyed
Parameters 1 and 2 don't affect accuracy as such, more reliability. Param 1 will set the sensitivity; how strong the edges of the circles need to be. Too high and it won't detect anything, too low and it will find too much clutter. Param 2 will set how many edge points it needs to find to declare that it's found a circle. Again, too high will detect nothing, too low will declare anything to be a circle. The ideal value of param 2 will be related to the circumference of the circles.
Related
I have got a binary image/contour containing four human beings, and I want to detect/count all humans. Since there are occlusions, so I think it is best to get the head/maxima in the contour of all the humans. In that case human can be counted.
I am able to get the global maxima\topmost point (in terms of calculus language), but I want to get all the local maximas
The code for finding the topmost point is as suggested by Adrian in his blogpost i.e.:
topmost = tuple(biggest_contour[biggest_contour[:,:,1].argmin()][0])
Can anyone please suggest how to get all the local maximas, instead of just topmost location?
Here is the sample of my Image:
The definition of "local maximum" can be tricky to pin down, but if you start with a simple method you'll develop an intuition to look further. Even if there are methods available on the web to do this work for you, it's worth implementing a few basic techniques yourself before you go googling.
One simple method I've used in the path goes something like this:
Find the contours as arrays/lists/containers of (x,y) coordinates.
At each element N (a pixel) in the list, get the pixels at N - D and N + D; that is the pixels D ahead of the current pixel and D behind the current pixel
Calculate the point-to-point distance
Calculate the distance along the contour from N-D to N+D
Calculate (distanceAlongContour)/(point-to-point distance)
...
There are numerous other ways to do this, but this is quick to implement from scratch, and I think a reasonable starting point: Compare the "geodesic" distance and the Euclidean distance.
A few other possibilities:
Do a bunch of curve fits to chunks of pixels from the contour. (Lots of details to investigate here.)
Use Ramer-Puecker-Douglas to render the outlines as polygons, then choose parameters to ensure those polygons are appropriately simplified. (Second time I've mentioned R-P-D today; it's handy.) Check for vertices with angles that deviate much from 180 degrees.
Try a corner detector. Crude, but easy to implement.
Implement an edge follower that moves from one pixel to the next in the contour list, and calculate some kind of "inertia" as the pixel shifts direction. This wouldn't be useful on a pixel-by-pixel basis, but you could compare, say, pixels N-1,N,N+1 to pixels N+1,N+2,N+3. Or just calculate the angle between them.
The shape of an object is detected on a bw image. The object is a black continuous shape, the background is white.
We use PCA (http://docs.opencv.org/3.1.0/d1/dee/tutorial_introduction_to_pca.html) to get the object direction and align the object. Currently the shape itself (the points on the contour) is the input to the opencv PCA implementation. This usually works very well. But from time to time there is small dirt on the object border, causing the shape to pass around the dirt. This causes more points and more weight on one side, slightly turning the object.
Idea: Instead of the contour, we use the area of the object as input for our PCA analysis. The issue there, to check all points on if they are inside the contour and then use them for PCA slows the application down. This part will be about 52352 times slower.
New Approach: We take random points in the image, check if they are inside the shape and if so, use them for our PCA. We have to see if we can get the consistent quality needed from this approach.
Is there already a similar implementation in opencv which is using the area instead of the shape?
Another approach would be to put a mesh over the object and use the mesh points inside the object for PCA.
Is there already something similar available one can just use or does one quickly need to implement something like this?
Going for straight lines around the object isn't an option.
Given that we have received very limited information about your problem (posting images would help a lot) and you do not seem to know the probability density function of the noise, your best bet is to consider the noise to be Gaussian.
As such, and following your intuition, my suggested approach is to take a few (by a few I mean statistically relevant but not raising the computation time that much) random points that lie inside the object and compute the PCA.
Repeat this procedure in an iterative loop and store somewhere the resulting rotation angles you get from the application of the PCA to the object shape.
Stop once you have enough point, compute the mean of the rotation angles: this is a decent estimate of the true angle. Compute also the standard deviation to get a measure of the quality of your estimation. By "enough points" you can consider that ~30 points is usually considered to be "enough" for being representative of the underlying population according to the central limit theorem.
If you want, you can improve on this approach in many ways, for example doing robust estimation of the true angle once you have collected enough points. It all depends on the data you have at hand...take my suggestion just as a starting point.
There are few parameters that you could change, in which may improve your system.
First is the threshold you use to binarize your image. I don't know what your application is about, but you could use other color systems, or normalize your image by cromacity, and after that, apply the new threshold.
Other aspect is to exclude shapes (contours) that have bigger or smaller area that what you are expecting.
To add up, you may use a blur filter before detect contours.
I don't know how the noise looks but when you say "small dirt" I think it might be only some few pixels that is a lot smaller then the object it self, but it might be attached to the object. To reduce this noise it might be possible to perform an opening (morphology) on the binary image.
http://docs.opencv.org/2.4/doc/tutorials/imgproc/opening_closing_hats/opening_closing_hats.html
I performed edge detection on images (with Python 2-7 and OpenCV 3.2) and have results like the following picture, i.e. one-pixel-wide edges not necessarily closed (can have "loose ends"), and with possible holes :
Now I would like to get the "derivative" of these edges, meaning the "slope" at each point, as in the following image :
For the moment, the only way I managed to do it is very locally. For each point of the edge (in red in next "zoomed" picture), I create a circle around it (in pink), mask the circle with the edge to get the red point's neighbors, then compute the slope of these two neighbors.
However, it can be quite messy if edges have holes (which they often do) or are close to other edges (which they often are) and masking all the points is pretty computationally intensive, so I wonder if there is a better way.
My first idea was spline interpolation, but you need to give as input an ordered list of points, which you can't have for a given edge unless you use a pixel neighbor tracking algorithm which can also get quite messy in case of not-that-good edges.
I also thought of findContours but it needs closed edges or else it yields the contour of a one-pixel-wide edge, i.e. two lines on both side of the edges, started at an arbitrary location on the edge, in short it's a mess.
Is there a cleaner and more efficient way than my actual method to achieve what I want ? Does OpenCV have any resources or is its job done after edge detection (I think the latter is more probable !) ?
P.S. : "I don't think there is a better way" is an answer I'm ready to accept !
So, if I understood everything correctly, what you need is an ordered list of your points free from holes, because after that it seems you know how to proceed to obtain your result. So, you should concentrate in getting an ordered gapless list.
FindContours does output an ordered list, but probably not in the order you need. It groups connected pixels with a TOP-DOWN / LEFT-RIGHT priority. So, it swipes each row sequentially, when it hits a white pixel, it finds the first contour. So, in your image, the first contour it finds is actually the one on the right, since it has the closest to 0 Y value.
In the case of this particular image, if you rotate it 90 degrees you'll realize that it will actually order your contours and points in the way you need. But will this always be the case? Only you can tell. If there is a pre-process method to apply to your images that will guarantee that findContours will order your pixels in the correct way, the rest will be easy. If not, I suggest you create your own pixel-connectivity algorithm that will work as you need it to, since all your problems depends on getting an ordered list.
Once you have the ordered list, just interpolate the missing pixels.
If you have an ordered set of pixels, "closing the gaps" is easy, since you just need to find the gaps and interpolate between them as an approximation that probably wont hurt your algorithm.
I can successfully threshold images and find edges in an image. What I am struggling with is trying to extract the angle of the black edges accurately.
I am currently taking the extreme points of the black edge and calculating the angle with the atan2 function, but because of aliasing, depending on the point you choose the angle can come out with some degree of variation. Is there a reliable programmable way of choosing the points to calculate the angle from?
Example image:
For example, the Gimp Measure tool angle at 3.12°,
If you're writing your own library, then creating a robust solution for this problem will allow you to develop several independent chunks of code that you can string together to solve other problems, too. I'll assume that you want to find the corners of the checkerboard under arbitrary rotation, under varying lighting conditions, in the presence of image noise, with a little nonlinear pincushion/barrel distortion, and so on.
Although there are simple kernel-based techniques to find whole pixels as edge pixels, when working with filled polygons you'll want to favor algorithms that can find edges with sub-pixel accuracy so that you can perform accurate line fits. Even though the gradient from dark square to white square crosses several pixels, the "true" edge will be found at some sub-pixel point, and very likely not the point you'd guess by manually clicking.
I tried to provide a simple summary of edge finding in this older SO post:
what is the relationship between image edges and gradient?
For problems like yours, a robust solution is to find edge points along the dark-to-light transitions with sub-pixel accuracy, then fit lines to the edge points, and use the line angles. If you are processing a true camera image, and if there is an uncorrected radial distortion in the image, then there are some potential problems with measurement accuracy, but we'll ignore those.
If you want to find an accurate fit for an edge, then it'd be great to scan for sub-pixel edges in a direction perpendicular to that edge. That presupposes that we have some reasonable estimate of the edge direction to begin with. We can first find a rough estimate of the edge orientation, then perform an accurate line fit.
The algorithm below may appear to have too many steps, but my purpose is point out how to provide a robust solution.
Perform a few iterations of erosion on black pixels to separate the black boxes from one another.
Run a connected components algorithm (blob-finding algorithm) to find the eroded black squares.
Identify the center (x,y) point of each eroded square as well as the (x,y) end points defining the major and minor axes.
Maintain the data for each square in a structure that has the total area in pixels, the center (x,y) point, the (x,y) points of the major and minor axes, etc.
As needed, eliminate all components (blobs) that are too small. For example, you would want to exclude all "salt and pepper" noise blobs. You might also temporarily ignore checkboard squares that are cut off by the image edges--we can return to those later.
Then you'll loop through your list of blobs and do the following for each blob:
Determine the direction roughly perpendicular to the edges of the checkerboard square. How you accomplish this depends in part on what data you calculate when you run your connected components algorithm. In a general-purpose image processing library, a standard connected components algorithm will determine dozens of properties and measurements for each individual blob: area, roundness, major axis direction, minor axis direction, end points of the major and minor axis, etc. For rectangular figures, it can be sufficient to calculate the topmost, leftmost, rightmost, and bottommost points, as these will define the four corners.
Generate edge scans in the direction roughly perpendicular to the edges. These must be performed on the original, unmodified image. This generally assumes you have bilinear interpolation implemented to find the grayscale values of sub-pixel (x,y) points such as (100.35, 25.72) since your scan lines won't fall exactly on whole pixels.
Use a sub-pixel edge point finding technique. In general, you'll perform a curve fit to the edge points in the direction of the scan, then find the real-valued (x,y) point at maximum gradient. That's the edge point.
Store all sub-pixel edge points in a list/array/collection.
Generate line fits for the edge points. These can use Hough, RANSAC, least squares, or other techniques.
From the line equations for each of your four line fits, calculate the line angle.
That algorithm finds the angles independently for each black checkerboard square. It may be overkill for this one application, but if you're developing a library maybe it'll give you some ideas about what sub-algorithms to implement and how to structure them. For example, the algorithm would rely on implementations of these techniques:
Image morphology (e.g. erode, dilate, close, open, ...)
Kernel operations to implement morphology
Thresholding to binarize an image -- the Otsu method is worth checking out
Connected components algorithm (a.k.a blob finding, or the OpenCV contours function)
Data structure for blob
Moment calculations for blob data
Bilinear interpolation to find sub-pixel (x,y) values
A linear ray-scanning technique to find (x,y) gray values along a specific direction (which will also rely on bilinear interpolation)
A curve fitting technique and means to determine steepest tangent to find edge points
Robust line fit technique: Hough, RANSAC, and/or least squares
Data structure for line equation, related functions
All that said, if you're willing to settle for a slight loss of accuracy, and if you know that the image does not suffer from radial distortion, etc., and if you just need to find the angle of the parallel lines defined by all checkboard edges, then you might try..
Simple kernel-based edge point finding technique (Laplacian on Gaussian-smoothed image)
Hough line fit to edge points
Choose the two line fits with the greatest number of votes, which should be one set of horizontal-ish lines and the other set of vertical-ish lines
There are also other techniques that are less accurate but easier to implement:
Use a kernel-based corner-finding operator
Find the angles between corner points.
And so on and so on. As you're developing your library and creating robust implementations of standalone functions that you can string together to create application-specific solutions, you're likely to find that robust solutions rely on more steps than you would have guessed, but it'll also be more clear what the failure mode will be at each incremental step, and how to address that failure mode.
Can I ask, what C++ library are you using to code this?
Jerry is right, if you actually apply a threshold to the image it would be in 2bit, black OR white. What you may have applied is a kind of limiter instead.
You can make a threshold function (if you're coding the image processing yourself) by applying the limiter you may have been using and then turning all non-white pixels black. If you have the right settings, the squares should be isolated and you will be able to calculate the angle.
Once this is done you can use a path finding algorithm to find some edge, any edge will do. If you find a more or less straight path, you can use the extreme points as you are doing now to determine the angle. Since the checker-board rotation is only relevant within 90 degrees, your angle should be modulo 90 degrees or pi over 2 radians.
I'm not sure it's (anywhere close to) the right answer, but my immediate reaction would be to threshold twice: once where anything but black is treated as white, and once where anything but white is treated as black.
Find the angle for each, then interpolate between the two angles.
Your problem have few solutions but all have one very important issue which you seem to neglect. Note: When you are trying to make geometrical calculation in the image, the points you use must be as far as possible one from the other. You are taking 2 points inside a single square. Those points are very close one to another, so a slight error in pixel location of of the points leads to a large error in the angle. Why do you use only a single square, when you have many squares in the image?
Here are few solutions:
Find the line angle of every square. You have at least 9 squares in the image, 4 lines in each square which give you total of 36 angles (18 will be roughly at 3[deg] and 18 will be ~93[deg]). Remove the 90[degrees] and you get 36 different measurements of the angle. Sort them and take the average of the middle 30 (disregarding the lower 3 and higher 3 measurements). This will give you an accurate result
Second solution, find the left extreme point of the leftmost square and the right extreme point of the rightmost square. Now calculate the angle between them. The result will be much more accurate because the points are far away.
A third algorithm which will give you accurate results because it doesn't involve finding any points and no need for thresholding. Just smooth the image, calculate gradients in X and Y directions (gx,gy), calculate the angle of the gradient in each pixel atan(gy,gx) and make histogram of the angles. You will have 2 significant peaks near the 3[deg] and 93[deg]. Just find the peaks by searching the maximum in the histogram. This will work even if you have a lot of noise in the image, even with antialising and jpg artifacts, and even if you have other drawings on the image. But remember, you must smooth the image a lot before calculating the derivatives.
I am just starting to use OpenCV to detect specific curves in an image. First, I want to verify if there is a curve, and next, I would like to identify the type of curve according to vertical or horizontal convex or concave curve. Is there an available function in OpenCV? If not, can you give me some ideas about how can I possibly write such a function? Thanks! By the way, I'm using C++.
Template matching is not a robust way to solve this problem (its like looking at an object from a small pinhole) and edge detectors don't necessarily return you the true edges in the image; false edges such as those due to shadows are returned too. Further, you have to deal with the problem of incomplete edges and other problems that scales up with the complexity of the scene in your image.
The problem you posed, in general, is a very challenging one and, except for toy examples, there are no good solutions.
A rough attempt could be to first try to detect plausible edges using an edge detector (e.g. the canny edge detector suggested). Next, use RANSAC to try to fit a subset of the points in the detected edges to your curve model.
For e.g. let's say you are trying to detect a curve of the following form f(x) = ax^2 + bx + c. RANSAC will basically try to find from among the points in the detected edges, a subset of them that would best fit this curve model. To detect different curves, change f(x) accordingly and run RANSAC for each of them. You can then try to determine if the curve represented by f(x) really exists in your image using some heuristic applied to from the points that were assigned to it by RANSAC (e.g. if too few points were fitted to the model it is likely that the curve is not there. But how to determine a good threshold for the number of points?). You model will get more complex when you have to account for allowable transformation such as rotation etc.
The problem with this approach is you are basically trying fit what you think should be in the image to the points and sometimes, even if what you are looking for is not there, it will return you the "best possible" fit. For e.g. you have a whole bunch of points detected from a concentric circle. If you try to detect straight lines from these points, RANSAC will return you the best fit line! In fact, it could give you many different lines from different runs depending on which points it selected during its random initialization stage.
For more details on how to use RANSAC on this sort of problem, have a look at RANSAC for Dummies by Marco Zuliani. He also has a nice MATLAB toolbox to accompany this tech report, which you can probably port to the language of your choice.
Unless you know what you background looks like, or if you are in control of it e.g. by forcing a clean background, this is a very difficult problem to solve.