The left image is my result image after some processing. the right image is after running peak detection on the result image
How do I filter the image to only get the middle peak, which approximates to a 2d gaussian or circle, compared to the line on the right or peaks on the left that are quite spread out.
I need the filter to generalize across different peak sizes and imperfect gaussian/circle to some degree and be very fast
I tried eroding with different shapes (eg: circle, vertical/horizontal line) but that only created circles instead of removing non-circles
I thought about running a 2D gaussian as a filter with small positive numbers in the middle and large negative numbers on the edges but that would be sensitive to the size of the filter
Maybe i could use the detected peaks as starting points and "descend" the peak checking an increasing radius around it for almost uniform decrease until it reaches a certain threshold? But i fear manually coding that would be very slow
Related
I would like to calculate the angle of the tangent on a given white to black transition point on an image that consists entirely of black and white pixels and displays simple shapes such as squares, circles or triangles.
Zooming in on an image like that would look like this:
If you were to pick any of the black pixels next to a white one, my solution would be to follow the edge for a few pixels, then define a formula based on the curvature of the pixels and calculate the exact value of the defined point. Is there a simpler way of doing that? The resolution of the images is around 800x600 pixels so a fairly accurate estiamate of the angle of the provided point should be possible.
In my current approach I follow the edge line of the shape for about ten pixels, but I'm not sure where to go from there. Is there a library that already performs this kind of calculation for you? How many pixels would you need in order to be able to make an accurate judgement of the angle at that point?
Such a measurement is highly inaccurate on binary images, if not unusable.
If you measure on two neighboring pixels, the angle will be one of 0° or ±45°, so the angular resolution is very poor !
You can compute on several pixels to improve that resolution (five pixels correspond to like 11°), but now you are no more sure that the direction is the same, because the shape might be rounded.
If in your case the repertoire of shapes is known to be simple, you'd better perform fitting of the whole shapes before querying the tangents.
How to calculate the amount of overlap between images? I'm stitching two images and I need to know the minimum overlap that is enough to stitch the two images I need to calculate the overlap between images. I use the Python language.
How to calculate the amount of overlap between images?
You perform an image registration and the result of it will automatically give you an overlap (if there is any).
To calculate the overlap, compute the bounds of both images (after overlaying) and then compute the bound of the intersection. The intersecting rectangle of two bounding rectangles [x1,y1,w1,h1] and [x2,y2,w2,h2] (both left upper corner, width, height) and is [max(x1,x2),max(y1,y2),min(x1+w1,x2+w2)-max(x1,x2),min(y1+h1,y2+h2)-max(y1,y2)] (only if the resulting width and height is positive).
There are routines for image registration in in the popular Python packages: scikit, open-cv or itk.
In case, the images only need to be shifted to be overlaid, the maximum of a cross-correlation of two images (normalized by the overlapping area) is something that is commonly used.
I need to know the minimum overlap that is enough to stitch the two images
The absolute minimum overlap required is a single line. In practice I would be worried about the uncertainty of the computation of the overlap (should be smaller with increasing overlap) as well as non-homogeneous imaging conditions (vignetting for example). Both should favor a somewhat larger overlap.
I have an Image (or several hundreds of them) that need to be analyzed. The goal is to find all black spots close to each other.
For example all black spots with a Horizontal distance of 160 pixel and vertical 40 pixel.
For now I just look at each Pixel and if there is a black pixel I call a recursive Method to find its neighbours (i can post the code too if you want to)
It works, but its very slow. At the moment the script runs about 3-4 minutes depending on image size.
Is there some easy/fast way to accomplish this (best would be a scikit-image method to help out here) I'm using Python.
edit: I tried to use scikit.measure.find_contours, now i have an array with arrays containing the contours of the black spots. Now I only need to find the contours in the neighbourhood of these contours.
When you get the coordinates of the different black spots, rather than computing all distances between all pairs of black pixels, you can use a cKDTree (in scipy.spatial, http://docs.scipy.org/doc/scipy/reference/generated/scipy.spatial.cKDTree.html#scipy.spatial.cKDTree). The exact method of cKDTree to use depends on your exact criterion (you can for example use cKDTree.query_ball_tree to know whether there exists a pair of points belonging to two different labels, with a maximal distance that you give).
KDTrees are a great method to reduce the complexity of problems based on neighboring points. If you want to use KDTrees, you'll need to rescale the coordinates so that you can use one of the classical norms to compute the distance between points.
Disclaimer: I'm not proficient with the scikit image library at all, but I've tackled similar problems using MATLAB so I've searched for the equivalent methods in scikit, and I hope my findings below help you.
First you can use skimage.measure.label which returns label_image, i.e. an image where all connected regions are labelled with the same number. I believe you should call this function with background=255 because from your description it seems that the background in your images is the while region (hence the value 255).
This is essentially an image where the background pixels are assigned the value 0 and the pixels that make up each (connected) spot are assigned the value of an integer label, so all the pixels of one spot will be labelled with the value 1, the pixels of another spot will be labelled with the value 2, and so on. Below I'll refer to "spots" and "labelled regions" interchangeably.
You can then call skimage.measure.regionprops, that takes as input the label_image obtained in the previous step. This function returns a list of RegionProperties (one for each labelled region), which is a summary of properties of a labelled region.
Depending on your definition of
The goal is to find all black spots close to each other.
there are different fields of the RegionProperties that you can use to help solve your problem:
bbox gives you the set of coordinates of the bounding box that contains that labelled region,
centroid gives you the coordinates of the centroid pixel of that labelled region,
local_centroid gives you the centroid relative to the bounding box bbox
(Note there are also area and bbox_area properties which you can use to decide whether to throw away very small spots that you might not be interested in, thus reducing computation time when it comes to comparing proximity of each pair of spots)
If you're looking for a coarse comparison, then comparing the centroid or local_centroid between each pair of labelled regions might be enough.
Otherwise you can use the bbox coordinates to measure the exact distance between the outer bounds of any two regions.
If you want to base the decision on the precise distance between the pixel(s) of each pair of regions that are closest to each other, then you'll likely have to use the coords property.
If your input image is binary, you could separate your regions of interest as follows:
"grow" all the regions by the expected distance (actually half of it, as you grow from "both sides of the gap") with binary_dilation, where the structure is a kernel (e.g. rectangular: http://scikit-image.org/docs/dev/api/skimage.morphology.html#skimage.morphology.rectangle) of, let's say, 20x80pixels;
use the resulting mask as an input to skimage.measure.label to assign different values for different regions' pixels;
multiply your input image by the mask created above to zero dilated pixels.
Here are the results of proposed method on your image and kernel = rectange(5,5):
Dilated binary image (output of step 1):
Labeled version of the above (output of step 2):
Multiplication results (output of step 3):
I want to segment defective areas in images using MATLAB/Python-OpenCV.
Original image:
With Defects:
http://imgur.com/fyDkpcZ
Defect can be seen at 3rd rectangle.
What I tried so far:
Extract borders of rectangles with LoG filter / threshold graylevel (but not helps much because of shadows)
Trace their boundaries
Get centroid
Find distance between boundary points and centroid with respect to angle ( increment angle by 0.5 degrees for better resolution)
Find a good template rectangle and save it
Find the difference between template rectangle and candidate rectangle
Based on that result I can find the faulty regions but the false-alarm rate increases when I try to increase the sensitivity of algorithm.
I need to get boundaries much more precise and non-noisy. Because of the shadows, the edges of rectangle may vary vastly.
How can I get edges of rectangles more robust to shadows?
What can be done instead of what I tried so far?
Thanks for your help!
A Laplace of Gaussian filter is a zero mean operation. If you feed it an 8-bit image with intensities centered on 127, it will return you image data centered on zero. You must use a filter bias of arbitrary value, usually half the container's max value (so in this 8-bit example, the bias would be 127). You can also adjust the filter strength by multiplying the result pixels by a constant, this makes the log filter's effect more apparent.
The log filter will make one white and one black edge for very strong transitions. In the horizontal or vertical direction, finding the actual edge is very easy, as you need only take the average of position of both. This gives you sub-pixel resolution if integrated over a small distance.
If the illumination of these images is very similar, you can use registration and subtraction:
Normalize both the image suspected to contain defects and a reference image to some intensity.
Register (align) them; you could do this by detecting three points on a rectangle and then moving and rotating one of the images.
Subtract the suspect image from the reference image. This gives you an error map. You can apply a small blur and then a tight LoG filter to it to remove noise and make detection more accurate.
The image below shows two circles of same radius, rendered with antialiasing, only that the left circle is shifted half pixel horizontally (notice that the circle horizontal center is at the middle of a pixel at the left, and at the pixel border at the right).
If I perform a cross-correlation, I can take the position of the maximum on the correlation array, and then calculate the shift. But since pixel positions are always integers, my question is:
"How can I obtain a sub-pixel (floating point) offset between two images using cross-correlation in Numpy/Scipy?"
In my scripts, am using either of scipy.signal.correlate2d or scipy.ndimage.filters.correlate, and they seem to produce identical results.
The circles here are just examples, but my domain-specific features tend to have sub-pixel shifts, and currently getting only integer shifts is giving results that are not so good...
Any help will be much appreciated!
The discrete cross-correlation (implemented by those) can only have a single pixel precision. The only solution I can see is to interpolate your 2D arrays to a finer grid (up-sampling).
Here's some discussion on DSP about upsampling before cross-correlation.
I had a very similar issue, also with shifted circles, and stumbled upon a great Python package called 'image registration' by Adam Ginsburg. It gives you sub-pixel 2D images shifts and is fairly fast. I believe it's a Python implementation of a popular MATLAB module, which only upsamples images around the peak of the x-correlation.
Check it out: https://github.com/keflavich/image_registration
I've been using 'chi2_shifts.py' with good results.