I developed an algorithm for border tracing of objects in an image. The algorithm is capable of tracing all the objects in an image and returns the result so that you don't have to slice an image with multiple objects to use them with the algorithm.
So basically I begin by finding a threshold value, then get the binary image after threshold and then run the algorithm on it.
The algorithm is below:
find the first pixel that belongs to any object.
Trace that object (has its own algorithm)
get the minimum area of the square that contains that object
mark all the pixels in that square as 0 (erase it from the binary image)
repeat from 1 until there isn't any objects left.
This algorithm worked perfectly with objects that are far from each other, but when I tried with the image attached, I got the result attached also.
The problem is that, the square is near the circle and part of it lies in the square that contains the object, so this part is deleted because the program thinks that it is part of the first object.
I would appreciate it if anyone has a solution to this issue.
Thanks!
A quick-and-dirty method is to sort the bounding boxes in ascending order by area before erasing the shapes. That way smaller shapes are removed first, which will reduce the number of overlapping objects. This will be sufficient if you have only convex shapes.
Pseudocode:
calculate all bounding boxes of shapes
sort boxes by area (smallest area first)
foreach box in list:
foreach pixel in box:
set pixel to 0
A method guaranteed to work for arbitrary shapes is to fill the box using a mask of the object. You already create a binary image, so you can use this as the mask.
Pseudocode:
foreach box in list:
foreach pixel in box:
if (pixel in mask == white): set pixel to 0
You can try using the canny edge detection technique for resolving this issue.
You can find more about it in the following URL,
http://homepages.inf.ed.ac.uk/rbf/HIPR2/canny.htm
Regards
Shiva
Related
I'm working on a project which locates the Machine Readable Zone on ID cards.
For this I need to do some pre processing to extract the ID card from a scanned image which typically are randomly disposed on a white page. I'm able to locate the majority of the cards by using a Histogram equalization with CLAHE before a contour detection. But in some cases the border around the MRZ is totally invisible (white on white) as shown on the attached image.
I'd like to detect rectangle of a predefined shape as I know the shape of the ID card will be always the same but so far I wasn't able to find a way do do something like this with OpenCV.
Basically what I need is to find two rectangle of a fixed ratio that best match the 2 cards on the scan.
I'm wondering if I need to try OpenCV matchers or if there is a simpler way to accomplish this kind of detection.
The solution to you problem is likely going to be matrix transformations. The concept is to pinpoint 4 coordinates on the card that can be easily detected using opencv, such as the the rectangle colored in blue & cyan.
Have coordinates of the card with the predefined shape stored in an array, where a corner of the card is at the 0, 0. Also store the coordinates of the blue * cyan rectangle in an array. With the two arrays you can find the perspective transform of the two arrays using the cv2.getPerspectiveTransform method.
Using the perspective transform found, you can detect the coordinates of the whole card every time you detect the coordinates of the blue & cyan rectangle.
I have this image:
and I am using cv2.goodFeaturesToTrack to detect the coroners, so now I have this:
The corners are in red and the numbers show the order of which goodFeaturesToTrack got the corners.. for example, corner with number 0 is the first detected one, etc...
If I were to connect the dots based on that order, I would get a messy polygon so I thought of using a function that given a random set of points, it returns them in an order with which the polygon wouldn't intersect..
I found this function and it does exactly what I want.
However, although the polygon doesn't intersect, for this example I am not getting the same shape as the initial one (I am getting a non self-intersecting polygon but a different shape).
Does anyone have an idea to fix this? I was thinking of making cv2.goodFeaturesToTrack return an ordered set of points but I couldn't figure out how to do that.
Thank you so much!
If you want to get the polygon, you can threshold the image and extract the outer contour with findContours, using CV_RETR_EXTERNAL as the mode to obtain the outer contour and CV_CHAIN_APPROX_SIMPLE as the method. CV_CHAIN_APPROX_SIMPLE compresses horizontal, vertical, and diagonal segments and leaves only their end points (see the documentation).
If you want to use corner detection results and arrange them in correct order to make the polygon, you'll have to trace the boundary of the shape and add those corner points into a list as you find them along the boundary. For this, I think you can use findContours with CV_RETR_EXTERNAL and CV_CHAIN_APPROX_NONE to get every pixel. Still, you might not find your detected corner points exactly on the contour returned from findContours, so you'll have to use a proximity threshold.
I have an array of data from a grayscale image that I have segmented sets of contiguous points of a certain intensity value from.
Currently I am doing a naive bounding box routine where I find the minimum and maximum (x,y) [row, col] points. This obviously does not provide the smallest possible box that contains the set of points which is demonstrable by simply rotating a rectangle so the longest axis is no longer aligned with a principal axis.
What I wish to do is find the minimum sized oriented bounding box. This seems to be possible using an algorithm known as rotating calipers, however the implementations of this algorithm seem to rely on the idea that you have a set of vertices to begin with. Some details on this algorithm: https://www.geometrictools.com/Documentation/MinimumAreaRectangle.pdf
My main issue is in finding the vertices within the data that I currently have. I believe I need to at least find candidate vertices in order to reduce the amount of iterations I am performing, since the amount of points is relatively large and treating the interior points as if they are vertices is unnecessary if I can figure out a way to not include them.
Here is some example data that I am working with:
Here's the segmented scene using the naive algorithm, where it segments out the central objects relatively well due to the objects mostly being aligned with the image axes:
.
In red, you can see the current bounding boxes that I am drawing utilizing 2 vertices: top-left and bottom-right corners of the groups of points I have found.
The rotation part is where my current approach fails, as I am only defining the bounding box using two points, anything that is rotated and not axis-aligned will occupy much more area than necessary to encapsulate the points.
Here's an example with rotated objects in the scene:
Here's the current naive segmentation's performance on that scene, which is drawing larger than necessary boxes around the rotated objects:
Ideally the result would be bounding boxes aligned with the longest axis of the points that are being segmented, which is what I am having trouble implementing.
Here's an image roughly showing what I am really looking to accomplish:
You can also notice unnecessary segmentation done in the image around the borders as well as some small segments, which should be removed with some further heuristics that I have yet to develop. I would also be open to alternative segmentation algorithm suggestions that provide a more robust detection of the objects I am interested in.
I am not sure if this question will be completely clear, therefore I will try my best to clarify if it is not obvious what I am asking.
It's late, but that might still help. This is what you need to do:
expand pixels to make small segments connect larger bodies
find connected bodies
select a sample of pixels from each body
find the MBR ([oriented] minimum bounding rectangle) for selected set
For first step you can perform dilation. It's somehow like DBSCAN clustering. For step 3 you can simply select random pixels from a uniform distribution. Obviously the more pixels you keep, the more accurate the MBR will be. I tested this in MATLAB:
% import image as a matrix of 0s and 1s
oI = ~im2bw(rgb2gray(imread('vSb2r.png'))); % original image
% expand pixels
dI = imdilate(oI,strel('disk',4)); % dilated
% find connected bodies of pixels
CC = bwconncomp(dI);
L = labelmatrix(CC) .* uint8(oI); % labeled
% mark some random pixels
rI = rand(size(oI))<0.3;
sI = L.* uint8(rI) .* uint8(oI); % sampled
% find MBR for a set of connected pixels
for i=1:CC.NumObjects
[Y,X] = find(sI == i);
mbr(i) = getMBR( X, Y );
end
You can also remove some ineffective pixels using some more processing and morphological operations:
remove holes
find boundaries
find skeleton
In MATLAB:
I = imfill(I, 'holes');
I = bwmorph(I,'remove');
I = bwmorph(I,'skel');
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)
Does someone have an idea to get the size and the position from an object? The Object is detected in a binary image with white pixels:
For example: Detected / Original
http://ivrgwww.epfl.ch/supplementary_material/RK_CVPR09/Images/segmentation/2_sal/0_12_12171.jpg
http://ivrgwww.epfl.ch/supplementary_material/RK_CVPR09/Images/comparison/orig/0_12_12171.jpg
I know about the CvMoments- Method. But I don't know how to use it in this case.
By the way: How can I make my mask more clearly?
Simple algorithm:
Delete small areas of white pixels using morphological operations (erosion).
Use findContours to find all contours.
Use countNonZero or contourArea to find area of each contour.
Cycle throught all points of each contour and find mean of them. This will be the center of contour.
If the object is tree, you should delete small areas by using morphology as Astor written.
Alternative of finding mass, and mass center is using moments:
http://docs.opencv.org/modules/imgproc/doc/structural_analysis_and_shape_descriptors.html?highlight=moments#moments
m00 as doc says is mass
There are also formulas for mass center.
This approach works when only your object remains on image after segmentation.