I am doing a project in opencv to detect handwritten characters from a user filled form. I have made algorithm to detect the skew angle of the scanned image using Hough Line Transform. But it does not work when the image is 180 degree rotated since 0 and 180 degree are treated as same by Hough Line function. My image contains some rectangles to fill data in them and some text. So how do i detect if a scanned image is 180 degree rotated or not?
Since I will have to first correct the skew angle of the image then only I can detect exactly where on the image user filled data (which I need to extract) lies using rectangle coordinates from the empty template form provided earlier, answers without using chacater recognition are appreciated.
To lift the 180° degrees ambiguity, only OCR can tell you: perform two reads on the deskewed text, one using the given angle, the other one using the angle + 180°, and keep the most successful read.
Unless you have some a priori information it's the only way, as other image processing operations don't know about characters.
UPDATE:
Some strings are forever ambiguous, like 0689HINOSXZ <=> ZXSONIH6890.
If the layout of the text is known (boxes) and asymmetric, it is a relatively easy matter to check matching of the text strings to the layout: choose a box (such as the topmost) and a string (the topmost), and align them by translation; then see how the other boxes and strings match (using a nearest neighbor rule) and establish the correspondences. Compare results with the straight and flipped layout, and keep the best overall area of overlap.
For reliability, it can be better to try more than a starting box/string pair, as there can be some ambiguity to which is the topmost (it could even be missing).
Isn't your problem more general? Let's say, you detect a skew angle of +45 degrees and rotate the image by -45 degrees. Then it could still be that the image is rotated by 180 degrees because it was not rotated +45 degrees but -135 instead.
Anyway, to the actual question: I am not an expert in character recognition but I think if you use it anyway in your application, couldn't you just try character recognition for both rotations and then choose the one that gets stronger response?
If you match the rectangles in your template with those of the skew corrected image, you'll be able to get the correct orientation (but only if there's no symmetry in the placement of those rectangles). For matching you may be able to use the rectangles in your template as a mask to extract regions from skew corrected image.
EDIT
Suppose your template and the skew corrected image look like this (in the best case where there are no displacements in skew corrected) :
Then you can use the template as a mask to copy data from skew corrected image. Then check what fraction of the white pixels in the template is contained in the copied image. This value will be very low for a 180 degree rotated image.
But as you say, this won't work in practice because of the displacements. Then may be you can try template matching (cross correlation) in which you use the template image as the template. Location of the strongest peak and the strength would give you some indication of the orientation. You can perform template matching at a reduced resolution so it runs faster.
You could try to match keypoints (Harris, Sift, ...) from the scanned image and the empty template. With the matched points you can easily find a transformation to align the scanned image with the template. This may work for your case, but you are more likely to succeed if the are some textured logos in the images, as it's usually the case for forms.
Can't you simple compute two cross-correlations? One with 180 rotation and one without? The one with the matching rectangle should give you a higher correlation maximum (provided the image contrast of the remaining page is not too misleading, but some pre-filtering could help here.)
Related
I'm trying to blindly detect signals in a spectra.
one way that came to my mind is to detect rectangles in the waterfall (a 2D matrix that can be interpret as an image) .
Is there any fast way (in the order of 0.1 second) to find center and width of all of the horizontal rectangles in an image? (heights of rectangles are not considered for me).
an example image will be uploaded (Note I know that all rectangles are horizontal.
I would appreciate it if you give me any other suggestion for this purpose.
e.g. I want the algorithm to give me 9 center and 9 coordinates for the above image.
Since the rectangle are aligned, you can do that quite easily and efficiently (this is not the case with unaligned rectangles since they are not clearly separated). The idea is first to compute the average color of each line and for each column. You should get something like that:
Then, you can subtract the background color (blue), compute the luminance and then compute a threshold. You can remove some artefact using a median/blur before.
Then, you can just scan the resulting 1D array filled with binary values so to locate where each rectangle start/stop. The center of each rectangle is ((x_start+x_end)/2, (y_start+y_end)/2).
I am trying to find a reliable method to calculate the corner points of a container. From these corner point’s idea is to calculate the center point of the container for the localization of robot, it means that the calculated center point will be the destination of robot in order to pick the container. For this I am looking for any suggestions to calculate the corner points or may be if any possibility to calculate the center point directly. Up to this point PCL library C/C++ is used for the processing of the 3D data.
The image below is the screenshot of the container.
thanks in advance.
afterApplyingPassthrough
I did the following things:
I binarized the image (black pixels = 0, green pixels = 1),
inverted the image (black pixels = 1, green pixels = 0),
eroded the image with 3x3 kernel N-times and dilated it with same kernel M-times.
Left: N=2, M=1;Right: N=6, M=6
After that:
I computed contours of all non-zero areas and
removed the contour that surrounded entire image.
This are the contours that remained:
I do not know how "typical" input image looks like in your case. Since I only have access to one sample image, I would rather not speculate about "general solution" that will be suitable for you. But to solve this particular case, you could analyze every contour in the following way:
compute rotatated rectangle that fits best around your contour (you need something similar to minAreaRect from OpenCV)
compute areas of rectangle and contour interior
if the difference between contour area and the area of the rotated bounding rectangle is small, the contour has approximately rectangular shape
find the contour that is both rectangular and satisfies some other condition (for example: typical area of the container). Assume that this belongs to container and compute its center.
I am not claiming that this is a solution that will work well in real world scenarios. It is also not fast. You should view it as a "sketch" that shows how to extract some useful information.
I assume the wheels maintain the cart a known offset from the floor and you can identify the floor. Filter out all points which are too close to the floor (this will remove wheels and everything but cart which will help limit data and simplify later steps.
If you isolate the cart, you could apply a simple average point (centroid), alternately, if that is not precise, you could try finding the bounding box of the isolated cart (min max in primary directions) and then take the centroid of that bounding box (this should be more accurate, but will still need a slight vertical offset due to the top handles).
If you can not isolate the cart or the other methods are not working well, you could try using PCL sample consensus specifically SACMODEL_LINE. This will be an involved strategy, but will give very solid results, basically run through and find each line and subtract its members from the cloud so as to find the next best line. After you have your 4 primary cart lines, use their parameters to find your centroid. *this would also be robust against random items being in or on the cart as well as carts of various sizes (assuming they always had linear perpendicular walls)
What is Distance Transform?What is the theory behind it?if I have 2 similar images but in different positions, how does distance transform help in overlapping them?The results that distance transform function produce are like divided in the middle-is it to find the center of one image so that the other is overlapped just half way?I have looked into the documentation of opencv but it's still not clear.
Look at the picture below (you may want to increase you monitor brightness to see it better). The pictures shows the distance from the red contour depicted with pixel intensities, so in the middle of the image where the distance is maximum the intensities are highest. This is a manifestation of the distance transform. Here is an immediate application - a green shape is a so-called active contour or snake that moves according to the gradient of distances from the contour (and also follows some other constraints) curls around the red outline. Thus one application of distance transform is shape processing.
Another application is text recognition - one of the powerful cues for text is a stable width of a stroke. The distance transform run on segmented text can confirm this. A corresponding method is called stroke width transform (SWT)
As for aligning two rotated shapes, I am not sure how you can use DT. You can find a center of a shape to rotate the shape but you can also rotate it about any point as well. The difference will be just in translation which is irrelevant if you run matchTemplate to match them in correct orientation.
Perhaps if you upload your images it will be more clear what to do. In general you can match them as a whole or by features (which is more robust to various deformations or perspective distortions) or even using outlines/silhouettes if they there are only a few features. Finally you can figure out the orientation of your object (if it has a dominant orientation) by running PCA or fitting an ellipse (as rotated rectangle).
cv::RotatedRect rect = cv::fitEllipse(points2D);
float angle_to_rotate = rect.angle;
The distance transform is an operation that works on a single binary image that fundamentally seeks to measure a value from every empty point (zero pixel) to the nearest boundary point (non-zero pixel).
An example is provided here and here.
The measurement can be based on various definitions, calculated discretely or precisely: e.g. Euclidean, Manhattan, or Chessboard. Indeed, the parameters in the OpenCV implementation allow some of these, and control their accuracy via the mask size.
The function can return the output measurement image (floating point) - as well as a labelled connected components image (a Voronoi diagram). There is an example of it in operation here.
I see from another question you have asked recently you are looking to register two images together. I don't think the distance transform is really what you are looking for here. If you are looking to align a set of points I would instead suggest you look at techniques like Procrustes, Iterative Closest Point, or Ransac.
I'd like to know what would be the best strategy to compare a group of contours, in fact are edges resulting of a canny edges detection, from two pictures, in order to know which pair is more alike.
I have this image:
http://i55.tinypic.com/10fe1y8.jpg
And I would like to know how can I calculate which one of these fits best to it:
http://i56.tinypic.com/zmxd13.jpg
(it should be the one on the right)
Is there anyway to compare the contours as a whole?
I can easily rotate the images but I don't know what functions to use in order to calculate that the reference image on the right is the best fit.
Here it is what I've already tried using opencv:
matchShapes function - I tried this function using 2 gray scales images and I always get the same result in every comparison image and the value seems wrong as it is 0,0002.
So what I realized about matchShapes, but I'm not sure it's the correct assumption, is that the function works with pairs of contours and not full images. Now this is a problem because although I have the contours of the images I want to compare, they are hundreds and I don't know which ones should be "paired up".
So I also tried to compare all the contours of the first image against the other two with a for iteration but I might be comparing,for example, the contour of the 5 against the circle contour of the two reference images and not the 2 contour.
Also tried simple cv::compare function and matchTemplate, none with success.
Well, for this you have a couple of options depending on how robust you need your approach to be.
Simple Solutions (with assumptions):
For these methods, I'm assuming your the images you supplied are what you are working with (i.e., the objects are already segmented and approximately the same scale. Also, you will need to correct the rotation (at least in a coarse manner). You might do something like iteratively rotate the comparison image every 10, 30, 60, or 90 degrees, or whatever coarseness you feel you can get away with.
For example,
for(degrees = 10; degrees < 360; degrees += 10)
coinRot = rotate(compareCoin, degrees)
// you could also try Cosine Similarity, or even matchedTemplate here.
metric = SAD(coinRot, targetCoin)
if(metric > bestMetric)
bestMetric = metric
coinRotation = degrees
Sum of Absolute Differences (SAD): This will allow you to quickly compare the images once you have determined an approximate rotation angle.
Cosine Similarity: This operates a bit differently by treating the image as a 1D vector, and then computes the the high-dimensional angle between the two vectors. The better the match the smaller the angle will be.
Complex Solutions (possibly more robust):
These solutions will be more complex to implement, but will probably yield more robust classifications.
Haussdorf Distance: This answer will give you an introduction on using this method. This solution will probably also need the rotation correction to work properly.
Fourier-Mellin Transform: This method is an extension of Phase Correlation, which can extract the rotation, scale, and translation (RST) transform between two images.
Feature Detection and Extraction: This method involves detecting "robust" (i.e., scale and/or rotation invariant) features in the image and comparing them against a set of target features with RANSAC, LMedS, or simple least squares. OpenCV has a couple of samples using this technique in matcher_simple.cpp and matching_to_many_images.cpp. NOTE: With this method you will probably not want to binarize the image, so there are more detectable features available.
I have an image with free-form curved lines (actually lists of small line-segments) overlayed onto it, and I want to generate some kind of image-warp that will deform the image in such a way that these curves are deformed into horizontal straight lines.
I already have the coordinates of all the line-segment points stored separately so they don't have to be extracted from the image. What I'm looking for is an appropriate method of warping the image such that these lines are warped into straight ones.
thanks
You can use methods similar to those developed here:
http://www-ui.is.s.u-tokyo.ac.jp/~takeo/research/rigid/
What you do, is you define an MxN grid of control points which covers your source image.
You then need to determine how to modify each of your control points so that the final image will minimize some energy function (minimum curvature or something of this sort).
The final image is a linear warp determined by your control points (think of it as a 2D mesh whose texture is your source image and whose vertices' positions you're about to modify).
As long as your energy function can be expressed using linear equations, you can globally solve your problem (figuring out where to send each control point) using linear equations solver.
You express each of your source points (those which lie on your curved lines) using bi-linear interpolation weights of their surrounding grid points, then you express your restriction on the target by writing equations for these points.
After solving these linear equations you end up with destination grid points, then you just render your 2D mesh with the new vertices' positions.
You need to start out with a mapping formula that given an output coordinate will provide the corresponding coordinate from the input image. Depending on the distortion you're trying to correct for, this can get exceedingly complex; your question doesn't specify the problem in enough detail. For example, are the curves at the top of the image the same as the curves on the bottom and the same as those in the middle? Do horizontal distances compress based on the angle of the line? Let's assume the simplest case where the horizontal coordinate doesn't need any correction at all, and the vertical simply needs a constant correction based on the horizontal. Here x,y are the coordinates on the input image, x',y' are the coordinates on the output image, and f() is the difference between the drawn line segment and your ideal straight line.
x = x'
y = y' + f(x')
Now you simply go through all the pixels of your output image, calculate the corresponding point in the input image, and copy the pixel. The wrinkle here is that your formula is likely to give you points that lie between input pixels, such as y=4.37. In that case you'll need to interpolate to get an intermediate value from the input; there are many interpolation methods for images and I won't try to get into that here. The simplest would be "nearest neighbor", where you simply round the coordinate to the nearest integer.