I am trying to detect circular road signs and I have some issues.
The HoughCircles function detects circles in a gray image, however with the same parameters but the image binarized (the circle is still perfectly visible) it does not detect any circle. I do not why it fails a lot with a binarized image. Any ideas why I have this issue with binary images?
To try to correct that I set the dp parameter to 2 and changed the threshold. In the binary image I now detect circles, but it also gives me a lot of false positives. I do not understand what the dp parameter is, or how to use it.
If there is no way to make it work, I would like to know if there is any other way of detecting circles in an image.
Hough generally works well with bad data - partial or obscured circles and noise.
But it is sensitive to the tuning parameters (max, min diameter, number of votes for a result).
Typically you could run hough to find all possible circles and then examine each possible circle by eg checking distance from center to points on the circumference. Or you could look at found circle diameters and then refine your diameter/vote bins, especially if this is a video stream and you expect the circles to be similar in the future.
Related
I am am currently working on a method to extract colors from a macbeth color chart. So far I have had moderate success by using thresholding and then extracting square contours. Sadly through, colors that are too close to each other either mix together or do no get detected.
The code in it's current form:
<script src="https://pastebin.com/embed_js/mNi0TcDE"></script>
The image before any processing
After thresholding, you can see that there are areas where lines are incomplete due to too small differences in color. I have tried to use dilation to midigate these issues and it does work to a degree. But not enough to detect all squares.
Image after thresholding
This results in the following contours being detected
Detected contours
I have tried using:
Hough lines, sadly no lines here detected.
Centroids of contours, but I was unable to find a way to use centroids to draw lines and detect the centers of the missing contours
Corner detection, corners where found. But I was unsuccessful in finding a real way to put them to use.
Can anyone point me in the right direction?
Thaks in advance,
Emil
Hum, if your goal is color calibration, you really do not need to detect the squares in their entirety. A 10x10 sample near the center of the image of each physical square will give you 100 color samples, which is plenty for any reasonable calibration procedure.
There are many ways to approach this problem. If you can guarantee that the chart will cover the image, you could even just do k-means clustering, since you know in advance the exact number of clusters you seek.
If you insist on using geometry, I'd do template matching in scale+angle space - it is reasonable to assume that the chart will be mostly facing, and only slightly rotated, so you only need to estimate scale and a small rotation about the axis orthogonal to the chart.
I'm working on an algorithm that counts patterns (bars) in a specific image. It seemed to me very simple at the first look, but I realized the complexity quickly.
I have tried simple thresholding, template matching (small sliding windows), edge detection...
I have just few images like this one. so I think that a machine learning algorithm can't give better results! but I still need suggestions.
I think you have enough data from your images. You need to crop from your images only the bars. You would get several dozens of small images for each image. After that you can resize all the images to some predefined size (for example 24X24 pixels) use a descriptor like HOG and SVM for the learning. For the false just use any other areas from your images.
This may not work in all cases, but since these are round bars, you can also try using circle detection. Both matlab(find circles) and opencv(hough circle transform) support this hough circle transformation. One issue is that you have to play with the parameters a bit (matlab is more simplistic than open cv) but that is true of almost any method.
These methods work better with larger images so I resized yours. You also need to know the radius of the circles to look for. If your camera position is constant, this shouldn't change much. This code is taken from the matlab documentation page I linked. It doensn't find all the circles, but some tuning may help
im = imread('http://i.stack.imgur.com/NRwUq.jpg');
%find circles doesn't work well on small images, I made the image
%three times larger, if you have larger images you should use those for
%better results
bim = imresize(im, 3*size(im));
%find and display circles
[centers, radii] = imfindcircles(bim,[8 20],'ObjectPolarity','bright',...
'Sensitivity',0.9);
imshow(bim);
h = viscircles(centers,radii);
number_of_bars = numel(centers)
I added green dots to circles the detector missed and blue X's over incorrect detection. I did these by hand, but the red circles were located by matlab.
I have an image like below :
I am trying to detect the circles via HoughCircles function.
Prior to detection, I threshold the image, and blur it via gaussian technique. The result is like follows :
The inverted image is larger, because I happened to find out that, if I dont resize image with same aspect ratio, hough circles algorithm goes nuts and finds either very few circles, or very wrong set of circles. I do understand the hough transformation algorithm to an extent. I use this snippet to detect the circles :
circles = cv2.HoughCircles(invertedBlurredImg, cv2.HOUGH_GRADIENT, 1, 30, param1=100, param2=23, minRadius=7, maxRadius=20)
I tried a lot of different dp values ranging from 1 to 2. I do think that if I get it close to 2, the sensitivity drops and, it becomes somewhat more possible to find the circles in a bad quality image. However, even if I dont enlargen the inverted image, I think the circles are quite clear, and I dont understand why it cannot find all the circles, unless I enlargen the image.
Here are the detected circle in case of the original sized image, and enlarged image, respectively.
What is the positive effect I receive from enlarging the image?
Does it kinda work like dilation because of the interpolation that goes on during the resizing to a larger image ?
Thanks
You had a problem and you have solved it in another way. Your problem is the parameters of the HoughCircle. They are too high for your small circles. Instead of changing them, you changed the image size. Thus gave you a good results since your new image is suitable for the old paramters.
The solution is to change your HoughCircle parameters until you got a good results on your original image. I am pretty sure it is the minRaduis which need to be decreased a bit.
I am interested in detecting single object more precisely a fire extinguisher which has no inter class variability (all fire extinguisher looks same). However, The application is supposedly realtime i.e a robot is exploring the environment and whenever it sees the object of interest it should be able to detect it and give pixel coordinates of it.
My question is which algorithm will be good choice for this task?
1. Is this a classification problem and should we use features(sift/surf etc) + bow +svm?
2. some other solution (no idea yet).
Any kind of input will be appreciated.
Thanks.
(P.S bear with me i am newbie to computer vision and stack over flow)
update1:
Height varies all are mounted on the wall but with different height. I tried with SIFT features and bow but it is expensive to extract bow descriptors in testing part. Moreover I have no idea how to locate the object(pixel coordinates) inside the image after its been classified positive.
update 2:
I finally used sift + bow + svm and am able to classify the object. But using this technique, i only get output interms of whether the object is present in the scene or not?
How can i detect the object i.e getting the bounding box or centre of the object. what is the compatible approach with the above method for achieving these results.
Thank you all.
I would suggest using color as the main feature to look for, and only try other features as needed. The fire extinguisher red is very distinctive, and should not occur too often elsewhere in an office environment. Other, more computationally expensive tests can then be performed only in regions of the right color.
Here is a good tutorial for color detection that also explains how to find good thresholds for your desired color.
I would suggest the following approach:
denoise your image with a median filter
convert the image to HSV format (Hue, Saturation, Value)
select pixels close to that particular shade of red with InRange()
Now you have a binary image image that contains only the pixels that are red.
count the number of red pixels with CountNonZero()
If that number is too small, abort
remove noise from the binary image by morphological opening / closing
find contours of all blobs in your picture with findContours or the CvBlob library
check if there are blobs of the correct width, correct height and correct width/height ratio
since your fire extinguishers are vertical cylinders, the width/height ratio will be constant from every angle. The width and height will of course vary somewhat with distance to the camera.
if the width and height do not match, abort
repeat these steps to find the black-colored part on the bottom of the extinguisher,
abort if there is no black region with correct width/height below the red region
(perhaps also repeat these steps for the metallic top and the yellow rectangle)
These tests should all be very fast. If they are too slow, you could reduce the resolution of your input images.
Depending on your environment, it is possible that this is already a robust enough test. If not, you can proceed with sift/surf feature matching, but only in a small region around the blobs with the correct color. You also do not necessarily have to do that for each frame, each n-th frame should be be enough for confirmation.
This is a old question .. but will still like to give my recommendation to use YOLO algorithm to solve this problem.
YOLO fits very well to this scenario.
first, I've learning just couple of week about image processing, NN, dll, by myself, so I'm really new n really far to pro. n sorry for my bad english.
there's image or photo of my drawing, I want to get the coordinates of object/shape (black dot) n the number around it, the number indicating the sequence number of dot.
How to get it? How to detect the dots? Shape recognition for the dots? Number handwriting recognition for the numbers? Then segmentation to get the position? Or use template matching? But every dot has a bit different shape because of hand drawing. Use neural network? in NN, the neuron is usually contain every pixel to recognize an character, right? can I use an picture of character or drawing dot contained by each neuron to recognize my whole picture?
I'm very new, so I'm really need your advice, correct me if I wrong! Please tell me what I must learn, what I must do, what I must use.
Thank you very much. :'D
This is a difficult problem which can't be solved by a quick solution.
Here is how I would approach it:
Get a better picture. Your image is very noisy and is taken in low light with high ISO. Use a better camera and better lighting conditions so you can get the background to be as white as possible and the dots as black as possible. Try to maximize the contrast.
Threshold the image so that all the background is white and the dots and numbers are black. Maybe you could apply some erosion and/or dilation to help connect the dark edges together.
Detect the rectangle somehow and set your work area to be inside the rectangle (crop the rest of the image so that you are left with the area inside the rectangle). You could do this by detecting the contours in the image and then the contour that has the largest area is the rectangle (because it's the largest object in the image). Of course, this is not the only way. See this: OpenCV find contours
Once you are left with only the dots, circles and numbers you need to find a way to detect them and discriminate between them. You could again find all contours (or maybe you've found them all from the previous step). You need to figure out a way to see if a certain contour is a circle, a filled circle (dot) or a number. This is a problem in it's own. Maybe you could count the white/black pixels in the contour's bounding box. Dots have more black pixels than circles and numbers. You also need to do something about numbers that connect with dots (like the number 5 in your image)
Once you know what is a dot, circle or number you could use an OCR library (Tesseract or any other OCR lib) to try and recognize the numbers. You could also use a neural network library (maybe trained with the MNIST dataset) to recognize the digits. A good one would be a convolutional neural network similar to LeNet-5.
As you can see, this is a problem that requires many different steps to solve, and many different components are involved. The steps I suggested might not be the best, but with some work I think it can be solved.