I'm new to image processing and hope someone can help/guide me in the right direction.
So I have a picture in black/white and I want to find the corner coordinates of the inner black part of the preprocessed picture. My question is what kind of method/s will yield the most accurate result?
I want something like this (red dots shows the inner corners)
go with cv::goodFeaturesToTrack() and play with params until you get your result.
you can refer to this on why choose this and not cornerHarris: goodFeaturesToTrack vs cornerHarris
and also to this SO answer for an example: opencv-using-cvgoodfeaturestotrack-with-c-mat-variable
of course I assume you are using C++, if you are using python it won't change much...
have luck and try to do a search before asking next time
I don't know what language you're using which makes it harder to answer this question but the way I did it my last time was by applying openCV's canny edge detection algorithm. This allows you to see the edges on the image. Next find the contours. With those two functions and a little help from your friend Google, you will be able to figure this out. Good luck!
One of the aproaches would be to use just sobel independently in X and Y (in original image). Since you have binary already just find inner edge, which will be easy.
Those edges can be then sampled - take a few points of the edge. And with the help of OpenCV library function cv::fitLine find the line of the edge. Do the same with all the inner edges and compute the intersections. This approach should be fairly accurate since from the fitLine function on you basically compute the corners in sub-pixel accuracy.
Related
Just wish to receive some ideas on I can solve this problem.
For a clearer picture, here are examples of some of the image that we are looking at:
I have tried looking into thresholding it, like otsu, blobbing it, etc. However, I am still unable to segment out the books and count them properly. Hardcover is easy of course, as the cover clearly separates the books, but when it comes to softcover, I have not been able to successfully count the number of books.
Does anybody have any suggestions on what I can do? Any help will be greatly appreciated. Thanks.
I ran a sobel edge detector and used Hough transform to detect lines on the last image and it seemed to be working okay for me. You can then link the edges on the output of the sobel edge detector and then count the number of horizontal lines. Or, you can do the same on the output of the lines detected using Hough.
You can further narrow down the area of interest by converting the image into a binary image. The outputs of all of these operators can be seen in following figure ( I couldn't upload an image so had to host it here) http://www.pictureshoster.com/files/v34h8hvvv1no4x13ng6c.jpg
Refer to http://www.mathworks.com/help/images/analyzing-images.html#f11-12512 for some more useful examples on how to do edge, line and corner detection.
Hope this helps.
I think that #audiohead's recommendation is good but you should be careful when applying the Hough transform for images that will have the library's stamp as it might confuse it with another book (You can see that the letters form some break-lines that will be detected by sobel).
Consider to apply first an edge preserving smoothing algorithm such as a Bilateral Filter. When tuned correctly (setting of the Kernels) it can avoid these such of problems.
A Different Solution That Might Work (But can be slow)
Here is a different approach that is based on pixel marking strategy.
a) Based on some very dark threshold, mark all black pixels as visited.
b) While there are unvisited pixels: Pick the next unvisited pixel and apply a region-growing algorithm http://en.wikipedia.org/wiki/Region_growing while marking its pixels with a unique number. At this stage you will need to analyse the geometric shape that this region is forming. A good criteria to detecting a book is that the region is creating some form of a rectangle where width >> height. This will detect a book and mark all its pixels to the unique number.
Once there are no more unvisited pixels, the number of unique numbers is the number of books you will have + For each pixel on your image you will now to which book does it belongs.
Do you have to keep the books this way? If you can change the books to face back side to the camera then I think you can get more information about the different colors used by different books.The lines by Hough transform or edge detection will be more prominent this way.
There exist more sophisticated methods which are much better in contour detection and segmentation, you can have a look at them here, however it is quite slow, http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html
Once you get the ultrametric contour map, you can perform some computation on them to count the number of books
I would try a completely different approach; with paperbacks, the covers are medium-dark lines whilst the rest of the (assuming white pages) are fairly white and "bloomed", so I'd try to thicken up the dark edges to make them easy to detect, then that would give the edges akin to working with hardbacks which you say you've done.
I'd try something like an erosion to thicken up the edges. This would be a nice, fast operation.
I tried to understand the cornerSubPix API in OpenCV for its idea behind and usefulness. I read the explanation in the link and can't understand how it works and how it is useful.
Can somebody explain me how it works and how it is useful at corner refinement? I checked my corner detection application for without cornerSubPix and with cornerSubPix. Not much difference in output image, but it takes time to process.
Thanks
I can´t explain better how it works than the actual documentation but I can help you with the: "how it is useful at corner refinement" Part.
The corners you find are in Pixel Coordinates. This means a Pixel can be at Position (10,10) or (11,11) but not at Position (11.3,11.2)
Subpixel refinement allows edges at such positions and helps to find a better position.
did somebody tried to find a pizzamarker like this one with "only" OpenCV so far?
I was trying to detect this one but couldn't get good results so far. I do not know where this marker is in picture (no ROI is possible), the marker will be somewhere in the room (different ligthning effects) and not faceing orthoonal towards us. What I want - the corners and later the orientation of this marker extracted with the corners but first of all only the 5Corners. (up, down, left, right, center)
I was trying so far: threshold, noiseclearing, find contours but nothing realy helped for a good result. Chessboards or square markers are normaly found because of their (parallel) lines- i guess this can't help me here...
What is an easy way to find those markers?
How would you start?
Use other colorformat like HSV?
A step-by-step idea or tutorial would be realy helpfull. Cause i couldn't find tuts at the net. Maybe this marker isn't called pizzamarker -> does somebody knows the real name?
thx for help
First - thank you for all of your help.
It seems that several methods are usefull. Some more or less time expansive.
For me it was the easiest with a template matching but not with the same marker.
I used only a small part of it...
this can be found 5 times(4 times negative and one positive) in this new marker:
now I use only the 4 most negatives Points and the most positive and got my 5 points that I finaly wanted. To make this more sure, I check if they are close to each other and will do a cornerSubPix().
If you need something which can operate in real-time I'd go down the edge detection route and look for intersecting lines like these guys did. Seems fast and robust to lighting changes.
Read up on the Hough Line Transform in openCV to get started.
Addendum:
Black to White is the strongest edge you can have. If you create a gradient image and use the strongest edges found in the scene (via histogram or other) you will be able to limit the detection to only the black/white edges. Look for intersections. This should give you a small number of center points to apply Hough ellipse detection (or alternate) to. You could rotate in a template as a further check if you wish.
BTW.. OpenCV has Edge Detection, Hough transform and FitEllipse if you do go down this route.
actually this 'pizza' pattern is one of the building blocks of the haar featured used in the
Viola–Jones object detection framework.
So what I would do is compute the summed area table, or integral image using cv::integral(img) and then run exhaustive search for this pattern, on various scales (size dependant).
In each window you are using only 9 points (top-left, top-center, ..., bottom left).
You can train and use cvHaarDetectObjects to detect the marker using VJ.
Probably not the fastest method but it should work.
You can find more info on object detection methods using OpenCV here: http://opencv.willowgarage.com/documentation/object_detection.html
I am currently facing a, in my opinion, rather common problem which should be quite easy to solve but so far all my approached have failed so I am turning to you for help.
I think the problem is explained best with some illustrations. I have some Patterns like these two:
I also have an Image like (probably better, because the photo this one originated from was quite poorly lit) this:
(Note how the Template was scaled to kinda fit the size of the image)
The ultimate goal is a tool which determines whether the user shows a thumb up/thumbs down gesture and also some angles in between. So I want to match the patterns against the image and see which one resembles the picture the most (or to be more precise, the angle the hand is showing). I know the direction in which the thumb is showing in the pattern, so if i find the pattern which looks identical I also have the angle.
I am working with OpenCV (with Python Bindings) and already tried cvMatchTemplate and MatchShapes but so far its not really working reliably.
I can only guess why MatchTemplate failed but I think that a smaller pattern with a smaller white are fits fully into the white area of a picture thus creating the best matching factor although its obvious that they dont really look the same.
Are there some Methods hidden in OpenCV I havent found yet or is there a known algorithm for those kinds of problem I should reimplement?
Happy New Year.
A few simple techniques could work:
After binarization and segmentation, find Feret's diameter of the blob (a.k.a. the farthest distance between points, or the major axis).
Find the convex hull of the point set, flood fill it, and treat it as a connected region. Subtract the original image with the thumb. The difference will be the area between the thumb and fist, and the position of that area relative to the center of mass should give you an indication of rotation.
Use a watershed algorithm on the distances of each point to the blob edge. This can help identify the connected thin region (the thumb).
Fit the largest circle (or largest inscribed polygon) within the blob. Dilate this circle or polygon until some fraction of its edge overlaps the background. Subtract this dilated figure from the original image; only the thumb will remain.
If the size of the hand is consistent (or relatively consistent), then you could also perform N morphological erode operations until the thumb disappears, then N dilate operations to grow the fist back to its original approximate size. Subtract this fist-only blob from the original blob to get the thumb blob. Then uses the thumb blob direction (Feret's diameter) and/or center of mass relative to the fist blob center of mass to determine direction.
Techniques to find critical points (regions of strong direction change) are trickier. At the simplest, you might also use corner detectors and then check the distance from one corner to another to identify the place when the inner edge of the thumb meets the fist.
For more complex methods, look into papers about shape decomposition by authors such as Kimia, Siddiqi, and Xiaofing Mi.
MatchTemplate seems like a good fit for the problem you describe. In what way is it failing for you? If you are actually masking the thumbs-up/thumbs-down/thumbs-in-between signs as nicely as you show in your sample image then you have already done the most difficult part.
MatchTemplate does not include rotation and scaling in the search space, so you should generate more templates from your reference image at all rotations you'd like to detect, and you should scale your templates to match the general size of the found thumbs up/thumbs down signs.
[edit]
The result array for MatchTemplate contains an integer value that specifies how well the fit of template in image is at that location. If you use CV_TM_SQDIFF then the lowest value in the result array is the location of best fit, if you use CV_TM_CCORR or CV_TM_CCOEFF then it is the highest value. If your scaled and rotated template images all have the same number of white pixels then you can compare the value of best fit you find for all different template images, and the template image that has the best fit overall is the one you want to select.
There are tons of rotation/scaling independent detection functions that could conceivably help you, but normalizing your problem to work with MatchTemplate is by far the easiest.
For the more advanced stuff, check out SIFT, Haar feature based classifiers, or one of the others available in OpenCV
I think you can get excellent results if you just compute the two points that have the furthest shortest path going through white. The direction in which the thumb is pointing is just the direction of the line that joins the two points.
You can do this easily by sampling points on the white area and using Floyd-Warshall.
I am looking for an efficient way to detect the small boxes around the numbers (see images)?
I already tried to use hough transformation with no success. Any ideas? I need some hints! I am using opencv...
For inspiration, you can have a look at the
Matlab video sudoku solver demo and explanation
Sudoku Grab, an Iphone App, whose author explains the computer vision part on his blog
Alternatively, if you are always hunting for the same grid you could deploy something like this:
Make a perfect artificial template of the grid and detect or save all coordinates from all corners.
In the target image, do the same thing, for example with Harris points. Be creative, you might also be able to use the distinct triangles that can be found in your images.
Using the coordinates from the template and the found harris points, determine the affine transformation x = Ax' between the template and the target image. That transformation can then be used to map the template grid onto the target image. At the very least this will give you some prior information to help guide further segmentation.
The gist of the idea and examples of the estimation of affine matrix A can be found on the site of Zissermans book Multiple View Geometry in Computer Vision and Peter Kovesi
I'd start by trying to detect the rectangular boundary of the overall sheet, then applying a perspective transform to make it truly rectangular. Crop that portion of the image out. If possible, then try to make the alternating white and grey sub-rectangles have an equal background brightness - maybe try adaptive histogram equalization.
Then the Hough transform might perform better. Alternatively, you could then take an approach that's broadly similar to this demonstration by Robert Bemis on MATLAB Central (it's analysing a DNA microarray image rather than Lotto cards, but it's essentially finding bounding boxes of items arranged in a grid). At a high level, the approach is to calculate the autocorrelation along columns and rows of pixels to detect the periodicity of the items in the grid, and use that to impose a bounding box on each item.
Sorry the above advice is mostly MATLAB-based; I'm afraid I'm not an opencv user, but hopefully it will give you some ideas at least.