I'm trying to extract objects from scanned images. There could be a few documents on a white background, and I need to crop and rotate them automatically. This seems like a rather simple task, but I've got stuck at some point and get bad results all the time.
I've tried to:
Binarise the image and get connected components by performing morphological operations.
Perform watershed segmentation by using dilated and eroded binary images as mask components.
Apply Canny detector and fill the contours.
None of this gets me good results. If the object does't have contrast edges (i.e a piece of paper on white background), it splits into a lot of separate components. If I connect these components by applying excessive dilation, background noise also expands and everything becomes a mess.
For example, I have an image:
After applying Canny detector and filling the contours I get something like this:
As you can see, the components are not connected. They are eve too far from each other to be connected by a reasonable amount of dilation. And when I apply watershed to this mask combined with some background points, it yields very bad results.
Some images are noisy:
In this particular case I was able to obtain contour of the whole passport by Canny detector because of it's contrast edges. But threshold method doesn't work here.
If the images are always on a very light background, then you can binarize with a threshold close to the maximum possible value. After that it is a matter of correcting the binary image to get the objects, but this step will vary depending on how your other images look like.
For instance, the following image at left is what we get with a threshold at 99% of the maximum value after a gaussian filtering on the input. After removing components connected to the border and other small components, and also combining with some basic morphological tools, we get the image at right.
This may seem a bit wishy-washy but bear with me:
This looks like quite a challenging case for image processing recipes involving only edge detection, morphological operations and segmentation.
What you are not exploiting here is that you (I believe) know what your document should look like. You are currently looking at completely general solutions which do not take into account this prior knowledge. If you can get some training data then you can go all the way from simple template/patch-based matching (SSD, Normalized Cross-Correlation) to more sophisticated object detection techniques to find the position and rotation of your documents.
My guess is that if your objects are always more or less the same and at the same scale (e.g. passports scanned at a fixed resolution/similar machines) then you can get away with a fairly crude approach. There won't be any one correct method. It's also likely that the technique you end up using will not work until you have done a significant amount of parameter tweaking, so don't give up on anything too quickly.
Related
I applied few techniques of denoising on MRI images and could not realize what techniques are applicable on my data to make the cartilage object more clear. First I applied Contrast-limited adaptive histogram equalization (CLAHE) with this function:
J = adapthisteq(I)
But I got a white image. This is original image and manual segmentation of two thin objects(cartilage):
And then I read a paper that they had used some preprocessing on microscopy images, such as: Anisotropic diffusion filter(ADF), then, K-SVD algorithm, and then Batch-Orthogonal Matching Pursuit (OMP). I applied the first two and the output is as following:
It seems my object is not clear. It should be brighter than other objects. I do not what kind of algorithms are applicable to make the cartilage objects more clear. I really appreciate any help.
Extended:
This is the object:
Edited (now knowing exactly what you are looking for)
The differences between your cartilage and the surrounding tissue is very slight and for that reason I do not think you can afford to do any filtration. What I mean by this is that the two things that I can kinda catch with my eye is that the edge on the cartilage is very sharp (the grey to black drop-off), and also there seems to be a texture regularity in the cartilage that is smoother than the rest of the image. To be honest, these features are incredibly hard to even pick out by eye, and a common rule of thumb is that if you can't do it with your eye, vision processing is going to be rough.
I still think you want to do histogram stretching to increase your contrast.
1:In order to do a clean global contrast stretch you will need to remove bone/skin edge/ whatever that line on the left is from the image (bright white). To do this, I would suggest looking at the intensity histogram and setting a cut-off after the first peak (make sure to limit this so some value well above what cartilage could be in case there is no white signal). After determining that value, cut all pixels above that intensity from the image.
2:There appears to be low frequency gradients in this image (the background seems to vary in intensity), global histogram management (normalization) doesn't handle this well, CLAHE can handle this if set up well. But a far simpler solution worth trying is just hitting the image with a high pass filter as this will help to remove some of those (low frequency) background shifts. (after this step you should see no bulk intensity variation across the image.
3: I think you should try various implementations of histogram stretching, your goal in your histogram stretch implementation is to make the cartilage look more unique in the image compared to all other tissue.
This is by far the hardest step as you need to actually take a stab at what makes that tissue different from the rest of the tissue. I am at work, but when I get off, I will try to brainstorm some concepts for this final segmentation step here. In the meantime, what you want to try to identify is anything unique about the cartilage tissue at this point. My top ideas are cylindrical style color gradient, surface roughness, edge sharpness, location, size/shape
I am trying to subtract two images using absdiff function ,to extract moving object, it works good but sometimes background appears in front of foreground.
This actually happens when the background and foreground colors are similar,Is there any solution to overcome this problem?
It may be description of the problem above not enough; so I attach images in the following
link .
Thanks..
You can use some pre-processing techniques like edge detection and some contrast stretching algorithm, which will give you some extra information for subtracting the image. Since color is same but new object should have texture feature like edge; if the edge gets preserved properly then when performing image subtraction you will obtain the object.
Process flow:
Use edge detection algorithm.
Contrast stretching algorithm(like histogram stretching).
Use the detected edge top of the contrast stretched image.
Now use the image subtraction algorithm from OpenCV.
There isn't enough information to formulate a complete solution to your problem but there are some tips I can offer:
First, prefilter the input and background images using a strong
median (or gaussian) filter. This will make your results much more
robust to image noise and confusion from minor, non-essential detail
(like the horizontal lines of your background image). Unless you want
to detect a single moving strand of hair, you don't need to process
the raw pixels.
Next, take the advice offered in the comments to test all 3 color
channels as opposed to going straight to grayscale.
Then create a grayscale image from the the max of the 3 absdiffs done
on each channel.
Then perform your closing and opening procedure.
I don't know your requirements so I can't take them into account. If accuracy is of the utmost importance. I'd use the median filter on input image over gaussian. If speed is an issue I'd scale down the input images for processing by at least half, then scale the result up again. If the camera is in a fixed position and you have a pre-calibrated background, then the current naive difference method should work. If the system has to determine movement from a real world environment over an extended period of time (moving shadows, plants, vehicles, weather, etc) then a rolling average (or gaussian) background model will work better. If the camera is moving you will need to do a lot more processing, probably some optical flow and/or fourier transform tests. All of these things need to be considered to provide the best solution for the application.
I was wondering if its possible to match the exposure across a set of images.
For example, lets say you have 5 images that were taken at different angles. Images 1-3,5 are taken with the same exposure whilst the 4th image have a slightly darker exposure. When I then try to combine these into a cylindrical panorama using (seamFinder with: gc_color, surf detection, MULTI_BAND blending,Wave correction, etc.) the result turns out with a big shadow in the middle due to the darkness from image 4.
I've also tried using exposureCompensator without luck.
Since I'm taking the pictures in iOS, I maybe could increase exposure manually when needed? But this doesn't seem optimal..
Have anyone else dealt with this problem?
This method is probably overkill (and not just a little) but the current state-of-the-art method for ensuring color consistency between different images is presented in this article from HaCohen et al.
Their algorithm can correct a wide range of errors in image sets. I have implemented and tested it on datasets with large errors and it performs very well.
But, once again, I suppose this is way overkill for panorama stitching.
Sunreef has provided a very good paper, but it does seem overkill because of the complexity of a possible implementation.
What you want to do is to equalize the exposure not on the entire images, but on the overlapping zones. If the histograms of the overlapped zones match, it is a good indicator that the images have similar brightness and exposure conditions. Since you are doing more than 1 stitch, you may require a global equalization in order to make all the images look similar, and then only equalize them using either a weighted equalization on the overlapped region or a quadratic optimiser (which is again overkill if you are not a professional photographer). OpenCV has a simple implmentation of a simple equalization compensation algorithm.
The detail::ExposureCompensator class of OpenCV (sample implementation of such a stitiching is here) would be ideal for you to use.
Just create a compensator (try the 2 different types of compensation: GAIN and GAIN_BLOCKS)
Feed the images into the compensator, based on where their top-left cornes lie (in the stitched image) along with a mask (which can be either completely white or white only in the overlapped region).
Apply compensation on each individual image and iteratively check the results.
I don't know any way to do this in iOS, just OpenCV.
I'm working with Infra Red image that is an output of a 3D sensor. This sensors project a Infra Red pattern in order to draw a depth map, and, because of this, the IR image has a lot of white spots that reduce its quality. So, I want to process this image to make it smoother in order to make it possible to detect objects laying in the surface.
The original image looks like this:
My objective is to have something like this (which I obtained by blocking the IR projecter with my hand) :
An "open" morphological operation does remove some noise, but I think first there should be some noise removal operation that addresses the white dots.
Any ideas?
I should mention that the algorithm to reduce the noise has to run on real time.
A median filter would be my first attempt .... possibly followed by a Gaussian blur. It really depends what you want to do with it afterwards.
For example, here's your original image after a 5x5 median filter and 5x5 Gaussian blur:
The main difficulty in your images is the large radius of the white dots.
Median and morphologic filters should be of little help here.
Usually I'm not a big fan of these algorithms, but you seem to have a perfect use case for a decomposition of your images on a functional space with a sketch and an oscillatary component.
Basically, these algorithms aim at solving for the cartoon-like image X that approaches the observed image, and that differs from Y only through the removal of some oscillatory texture.
You can find a list of related papers and algorithms here.
(Disclaimer: I'm not Jérôme Gilles, but I know him, and I know that
most of his algorithms were implemented in plain C, so I think most of
them are practical to implement with OpenCV.)
What you can try otherwise, if you want to try simpler implementations first:
taking the difference between the input image and a blurred version to see if it emphasizes the dots, in which case you have an easy way to find and mark them. The output of this part may be enough, but you may also want to fill the previous place of the dots using inpainting,
or applying anisotropic diffusion (like the Rudin-Osher-Fatemi equation) to see if the dots disappear. Despite its apparent complexity, this diffusion can be implemented easily and efficiently in OpenCV by applying the algorithms in this paper. TV diffusion can also be used for the inpainting step of the previous item.
My main point on the noise removal was to have a cleaner image so it would be easier to detect objects. However, as I tried to find a solution for the problem, I realized that it was unrealistic to remove all noise from the image using on-the-fly noise removal algorithms, since most of the image is actually noise.. So I had to find the objects despite those conditions. Here is my aproach
1 - Initial image
2 - Background subtraction followed by opening operation to smooth noise
3 - Binary threshold
4 - Morphological operation close to make sure object has no edge discontinuities (necessary for thin objects)
5 - Fill holes + opening morphological operations to remove small noise blobs
6 - Detection
Is the IR projected pattern fixed or changes over time?
In the second case, you could try to take advantage of the movement of the dots.
For instance, you could acquire a sequence of images and assign each pixel of the result image to the minimum (or a very low percentile) value of the sequence.
Edit: here is a Python script you might want to try
I implemented some adaptive binarization methods, they use a small window and at each pixel the threshold value is calculated. There are problems with these methods:
If we select the window size too small we will get this effect (I think the reason is because of window size is small)
(source: piccy.info)
At the left upper corner there is an original image, right upper corner - global threshold result. Bottom left - example of dividing image to some parts (but I am talking about analyzing image's pixel small surrounding, for example window of size 10X10).
So you can see the result of such algorithms at the bottom right picture, we got a black area, but it must be white.
Does anybody know how to improve an algorithm to solve this problem?
There shpuld be quite a lot of research going on in this area, but unfortunately I have no good links to give.
An idea, which might work but I have not tested, is to try to estimate the lighting variations and then remove that before thresholding (which is a better term than "binarization").
The problem is then moved from adaptive thresholding to finding a good lighting model.
If you know anything about the light sources then you could of course build a model from that.
Otherwise a quick hack that might work is to apply a really heavy low pass filter to your image (blur it) and then use that as your lighting model. Then create a difference image between the original and the blurred version, and threshold that.
EDIT: After quick testing, it appears that my "quick hack" is not really going to work at all. After thinking about it I am not very surprised either :)
I = someImage
Ib = blur(I, 'a lot!')
Idiff = I - Idiff
It = threshold(Idiff, 'some global threshold')
EDIT 2
Got one other idea which could work depending on how your images are generated.
Try estimating the lighting model from the first few rows in the image:
Take the first N rows in the image
Create a mean row from the N collected rows. You know have one row as your background model.
For each row in the image subtract the background model row (the mean row).
Threshold the resulting image.
Unfortunately I am at home without any good tools to test this.
It looks like you're doing adaptive thresholding wrong. Your images look as if you divided your image into small blocks, calculated a threshold for each block and applied that threshold to the whole block. That would explain the "box" artifacts. Usually, adaptive thresholding means finding a threshold for each pixel separately, with a separate window centered around the pixel.
Another suggestion would be to build a global model for your lighting: In your sample image, I'm pretty sure you could fit a plane (in X/Y/Brightness space) to the image using least-squares, then separate the pixels into pixels brighter (foreground) and darker than that plane (background). You can then fit separate planes to the background and foreground pixels, threshold using the mean between these planes again and improve the segmentation iteratively. How well that would work in practice depends on how well your lightning can be modeled with a linear model.
If the actual objects you try to segment are "thinner" (you said something about barcodes in a comment), you could try a simple opening/closing operation the get a lighting model. (i.e. close the image to remove the foreground pixels, then use [closed image+X] as threshold).
Or, you could try mean-shift filtering to get the foreground and background pixels to the same brightness. (Personally, I'd try that one first)
You have very non-uniform illumination and fairly large object (thus, no universal easy way to extract the background and correct the non-uniformity). This basically means you can not use global thresholding at all, you need adaptive thresholding.
You want to try Niblack binarization. Matlab code is available here
http://www.uio.no/studier/emner/matnat/ifi/INF3300/h06/undervisningsmateriale/week-36-2006-solution.pdf (page 4).
There are two parameters you'll have to tune by hand: window size (N in the above code) and weight.
Try to apply a local adaptive threshold using this procedure:
convolve the image with a mean or median filter
subtract the original image from the convolved one
threshold the difference image
The local adaptive threshold method selects an individual threshold for each pixel.
I'm using this approach extensively and it's working fine with images having non uniform background.