I would like to know if there is a clever way to segment individual pills using edge detector (e.g Canny) in the following image (without somekind of CNN or other ML way):
So far I have tried to use the Canny dector on a filtered image (box/gauss, with k=(3,3) or k=(5,5)) on different channels of several color spaces, e.g. GRAY, HSV, LAB. Unfortunately, I have not been able to find a perfect edges for several different experiments. If I could find the edges segmentation would already be quite simple, because I could compare the different colors of the pills and their sizes.
I thought that it could be done in another way: apply masks to the image corresponding to each pill and then find the edges on the filtered image, however, this method seems primitive and it will be difficult to distinguish between two-colored pills.
Best I can get so far:
Related
i need some advice in a computer vision projekt that i am working on. I am trying to extract a corner in the image below. The edge im searching for is marked yellow in the right image. The edge detection is always failing because the edge is too blurred in the middle.
I run this process with opencv and python.
I started to remove the white dots with a threshold method. After that a big median blur (31-53). After that a adaptive Threshod method to seperate the areas left and right from the corners. But the sepearation is always bad because the edge is barely visible.
Is there some other way to extract this edge or do i have to try with a better camera?
Thanks for your help.
First do you have other dataset? because it is hard to discuss it just from 1 input.
Couple things that you can do.
The best is you change the camera of imaging technique to have a better and clear edge.
When it is hard to do so. Try model-based fitting.If you image is repeatable in all class. I can observe some circles on the right and 2 sharp straight-line edges on the left. Your wanted red soft edge circle is in the middle of those 2 apparent features. That can be considered as a model. then you can always use some other technique for the pixel in-between those 2 region(because they are easy to detect) . Those technique includes but not limit to histogram equalization, high pass filter or even wavelet transform.
The Wost way is to use parameter fitting to do. What you want to segment is sth not a strong edge and sth not a smooth plane. So you can tweak the canny edge detect to find those edge which is not so strong. I do not support this method. If you really no choice and no other image, then you can try it.
Last way is to use deep learning based method to train and auto segment this part out. This method might work. but it needs you to have hundred if not thousands of dataset and labels.
Regards
Shenghai Yuan
Is there a way to attach low feature images together from vertical? I have tried OpenCV's ORB, SIFT& SURF, however, if the images have no features or low features, it fails to stitch them together.
I want these images put together:
Please, let me know if there a way to stitch them together or if blending works?
the feature matching are often based on contours inside images, there is not contours on your both images like corners or particular poylgon. Once openCv can't find contours and so feature, it can't make template matching to check if feature are ok and assembly both images.
If you have some feature despite the image content, try to lower the matching threshold, it will allow algorithm to match feature that are not exactly the same, like in your two differents pictures
I need to delete the noise from this image. My problem is that I need a neat contour without all the lines like in this image.
Do you have any suggestions how to do that using python?
Looking at your example images, I suppose you are looking for an image processing algorithm that finds the edges of your image (in your case, the border lines of the ground plan).
Have a look the Canny edge detection algorithm which might be a well-suited for this task. A tutorial with an example implementation in python can be found here.
I need to make an automatic adaptive segmentation for this kind of images:
All of them are bees' wings but the size of the image, the species of the bee, the camera, almost everything might be a little different.
I'm currently using OpenCV getting good results, doing the segmentation in this order:
Gray image
Smootheness(Median and BilateralFilter)
Treasholding(Adaptive Mean)
Remove small objects
Dilation
Remove median objects
Dilation
Remove big objects
Erosion
These dilations are used to connect the edges.
Here's an example of what I want to achieve, using manual segmentation:
Any suggestion that I can try to make it better? I prefer in OpenCV (Python).
When humans see markers suggesting the form of a shape, they immediately perceive the shape itself, as in https://en.wikipedia.org/wiki/Illusory_contours. I'm trying to accomplish something similar in OpenCV in order to detect the shape of a hand in a depth image with very heavy noise. In this question, assume that skin color based detection is not working (actually it is the best I've achieved so far but it is not robust under changing light conditions, shadows or skin colors. Also various paper shapes (flat and colorful) are on the table, confusing color-based approaches. This is why I'm attempting to use the depth cam instead).
Here's a sample image of the live footage that is already pre-processed for better contrast and with background gradient removed:
I want to isolate the exact shape of the hand from the rest of the picture. For a human eye this is a trivial thing to do. So here are a few attempts I did:
Here's the result with canny edge detection applied. The problem here is that the black shape inside the hand is larger than the actual hand, causing the detected hand to overshoot in size. Also, the lines are not connected and I fail at detecting contours.
Update: Combining Canny and a morphological closing (4x4 px ellipse) makes contour detection possible with the following result. It is still waaay too noisy.
Update 2: The result can be slightly enhanced by drawing that contour to an empty mask, save that in a buffer and re-detect yet another contour on a merge of three buffered images. The line that combines the buffered images is is hand_img = np.array(np.minimum(255, np.multiply.reduce(self.buf)), np.uint8) which is then morphed once again (closing) and finally contour detected. The results are slightly less horrible than in the picture above but laggy instead.
Alternatively I tried to use an existing CNN (https://github.com/victordibia/handtracking) for detecting the approximate position of the hand's center (this step works) and then flood from there. In order to detect contours the result is put into an OTSU filter and then the largest contour is taken, resulting in the following picture (ignore black rectangles in the left). The problem is that some of the noise is flooded as well and the results are mediocre:
Finally, I tried background removers such as MOG2 or GMG. They are confused by the enormous amount of fast-moving noise. Also they cut off the fingertips (which are crucial for this project). Finally, they don't see enough details in the hand (8 bit plus further color reduction via equalizeHist yield a very poor grayscale resolution) to reliably detect small movements.
It's ridiculous how simple it is for a human to see the exact precise shape of the hand in the first picture and how incredibly hard it is for the computer to draw a shape.
What would be your recommended method to achieve an exact hand segmentation?
After two days of desperate testing, the solution was to VERY carefully apply thresholding to an well-preprocessed image.
Here are the steps:
Remove as much noise as you possibly can. In my case, denoising was done using Intel's pyrealsense2 (I'm using an Intel RealSense depth camera and the algorithms were written for that camera family, thus they work very well). I used rs.temporal_filter() and directly after rs.hole_filling_filter() on every frame.
Capture the very first frame. Besides capturing the exact distance to the table (for later thresholding), this step also saves a still picture that is blurred by a 100x100 px kernel. Since the camera is never mounted perfectly but slightly tilted, there's an ugly grayscale gradient going over the picture and making operations impossible. This still picture is then subtracted from every single later frame, eliminating the gradient. BTW: this gradient removal step is already incorporated in the screenshots shown in the question above
Now the picture is almost noise-free. Do not use equalizeHist. This does not simply increase the general contrast regularly but instead empathizes the remaining noise way too much. This was my main error I did in almost all experiments. Instead, apply a threshold (binary with fixed border) directly. The border is extremely thin, setting it at 104 instead of 205 makes a huge difference.
Invert colors (unless you have taken BINARY_INV in the previous step), apply contours, take the largest one and write it to a mask
Voilà!