I am using threshold in Opencv to find the contours. My input is a hand image. Sometimes the threshold is not good so I couldnt find the contours.
I have applied the below preprocessing steps
1. Grabcut
cv::grabCut(image, result,rectangle,bgModel,fgModel, 3,cv::GC_INIT_WITH_RECT);
gray Scale conversion
cvtColor(handMat, handMat, CV_BGR2GRAY);
meadianblur
medianBlur(handMat, handMat, MEDIAN_BLUR_K);
I used the below code to find threshold
threshold( handMat, handMat, 141, 255, THRESH_BINARY||CV_THRESH_OTSU );
Sometimes I get good output and sometimes the threshold output is not good. I have attached the two output images.
Is there any other way than threshold from which contours can be found?
Good threshold Output:
Bad threshold Output
Have you tried an adaptive threshold? A single value of threshold rarely works in real life application. Another truism - threshold is a non-linear operation and hence non-stable. Gradient on the other hand is linear so you may want to find a contour by tracking the gradient if your background is smooth and solid color. Gradient is also more reliable during illumination changes or shadows than thresholding.
Grab-cut, by the way, uses color information to improve segmentation on the boundary when you already found 90% or so of the segment, so it is a post processing step. Also your initialization of grab cut with rectangle lets in a lot of contamination from background colors. Instead of rectangle use a mask where you mark as GC_FGD deep inside your initial segment where you are sure the hand is; mark as GC_BGD far outside your segment where you sure background is; mark GC_PR_FGD or probably foreground everywhere else - this is what will be refined by grab cut. to sum up - your initialization of grab cut will look like a russian doll with three layers indicating foreground (gray), probably foreground (white) and background (balck). You can use dilate and erode to create these layers, see below
Overall my suggestion is to define what you want to do first. Are you looking for contours of arbitrary objects on arbitrary moving background? If you are looking for a contour of a hand to find fingers on relatively uniform background I would:
1. use connected components or MSER to segment out a hand. Possibly improve results with grab cut initialized with the conservative mask and not rectangle!
2. use convexity defects to find fingers if this is your goal;
One issue is to try to find contours without binarizing the image.
If your input is in color, you can try to change color space in order to enhance the difference between the hand and the background.
Otsu try to find an optimal threshold, you can also try to set it manually but Otsu is useful because if the illumination change, the threshold will adapt automatically.
There are also many other kind of binarization : Sauvola, Bradley, Niblack, Kasar... but Otsu is simple, and work well. I suggest you to do preprocessing or postprocessing if you want to improve the binarization result.
Related
I have a thermal image of human standing either carrying a cold tool or a hot tool. I want to find the place this tool is. So basically i am trying to make an image processing filter which would give me the area of the place where drastic change of intensity of gray color occurs in the relatively smoother background. I have tried canny edge detector but it gives a lot of noise.
Hot Object To be detected: https://imgur.com/0ZyK6WP
Cold object to be detected: https://imgur.com/YYT9rHW
You might increase the Gaussian smoothing kernel to filter out the noise, but that might result in losing out the edges. So in that case you might want to use filter that would preserve the edge and also smooth out the image. Something like Bilateral filter could help in that case. It replaces the intensity of each pixel with a weighted average of intensity values from nearby pixels.
Also have you tried different threshold values foe non-max suppression. As that might be helpful when dealing with false positives.
I'm doing computer vision project for automatic card detection.
I need to separate the card from the background. I have applied the canny edge detection, using automatic parameter settings from this
Automatic calculation of low and high thresholds for the Canny operation in opencv
The result is excellent. However, sometimes the canny is not perfect like this
I have applied cvFindContour to detect the box. However, due to "hole" on the upper side, opencv failed to detect the contour.
How do I tune the cvFindContour to detect the contour or should I tune the canny edge instead?
There are multiple possible solutions.
The simplest one may be:
if FindContours does not find a closed contour, repeat the canny filter with a slightly decreased low_threshold, until you find a closed contour. If the closed contour has roughly the right size and shape, it is a card. The answer linked by Haris explains how to check whether a contour is closed
Another rather simple solution:
Don't apply Canny to the image at all. Execute findContours on the otsu thresholded image. Optionally use morphological opening and closing on the thresholded image to remove noise before findContours
FindContours does not need an edge image, it is usually executed with a thresholded image. I don't know your source image, so I cannot say how good this would work, but you would definitely avoid the problem of holes in the shape.
If the source image does not allow this, then the following may help:
use watershed to separate the card from the background. Use a high threshold to get some seed pixels that are definitely foreground and a low threshold to get pixels that are definitely background, then grow those two seeds using cv:watershed().
If the background in that image is the same color as the card, then the previous two methods may not work so well. In that case, your best bet may be the solution suggested by Micka:
use hough transform to find the 4 most prominent lines in the image. Form a rectangle with these 4 lines.
Is there a robust way to detect the water line, like the edge of a river in this image, in OpenCV?
(source: pequannockriver.org)
This task is challenging because a combination of techniques must be used. Furthermore, for each technique, the numerical parameters may only work correctly for a very narrow range. This means either a human expert must tune them by trial-and-error for each image, or that the technique must be executed many times with many different parameters, in order for the correct result to be selected.
The following outline is highly-specific to this sample image. It might not work with any other images.
One bit of advice: As usual, any multi-step image analysis should always begin with the most reliable step, and then proceed down to the less reliable steps. Whenever possible, the less reliable step should make use of the result of more-reliable steps to augment its own accuracy.
Detection of sky
Convert image to HSV colorspace, and find the cyan located at the upper-half of the image.
Keep this HSV image, becuase it could be handy for the next few steps as well.
Detection of shrubs
Run Canny edge detection on the grayscale version of image, with suitably chosen sigma and thresholds. This will pick up the branches on the shrubs, which would look like a bunch of noise. Meanwhile, the water surface would be relatively smooth.
Grayscale is used in this technique in order to reduce the influence of reflections on the water surface (the green and yellow reflections from the shrubs). There might be other colorspaces (or preprocessing techniques) more capable of removing that reflection.
Detection of water ripples from a lower elevation angle viewpoint
Firstly, mark off any image parts that are already classified as shrubs or sky. Since shrub detection would be more reliable than water detection, shrub detection's result should be used to inform the less-reliable water detection.
Observation
Because of the low elevation angle viewpoint, the water ripples appear horizontally elongated. In fact, every image feature appears stretched horizontally. This is called Anisotropy. We could make use of this tendency to detect them.
Note: I am not experienced in anisotropy detection. Perhaps you can get better ideas from other people.
Idea 1:
Use maximally-stable extremal regions (MSER) as a blob detector.
The Wikipedia introduction appears intimidating, but it is really related to connected-component algorithms. A naive implementation can be done similar to Dijkstra's algorithm.
Idea 2:
Notice that the image features are horizontally stretched, a simpler approach is to just sum up the absolute values of horizontal gradients and compare that to the sum of absolute values of vertical gradients.
I have the image of hand that was detected using this link. Its hand detection using HSV color space.
Now I face a problem: I need to get the enclosing area/draw bounding lines possible enough to determine the hand area, then fill the enclosing area and subtract it from the original to remove the hand.
I have thus so far tried to blurring the image to reduce noise, dilating the image, closing holes, etc. that seem to be an overdose. I have tried contours, and that seem to be the best approach so far. I was trying to get the convex hull (largest) and I ended up with the following after testing with different thresholds.
The inaccuracies can be seen with the thumb were the hull straightens. It must be curved. I am trying to figure out the location of the hand so to identify the region being covered by the hand. Going to subtract it to remove the hand from the original image. That is what I want to achieve.
Is there a better approach to this?
And ideas suggestions greatly appreciated.
Original and detected are as follows
Instead of the convex hull, consider using the alpha hull, which can better follow the contours of a shape by allowing concavities.
This site has a nice summary of alpha shapes: "Everything You Always Wanted to Know About Alpha Shapes But Were Afraid to Ask" by François Bélair.
http://cgm.cs.mcgill.ca/~godfried/teaching/projects97/belair/alpha.html
As David mentioned in his post, consider thresholding using HSV (or HSI) color space rather than on RGB or grayscale. If you can allow for longer processing time, you can use an algorithm such as Mean Shift to segment trickier images like yours. OpenCV has an implementation of Mean Shift, and the book Learning OpenCV provides a concise description of the algorithm.
Image Segmentation using Mean Shift explained
In any case, a standard binarization threshold doesn't appear to be helping much. Consider using a dynamic threshold; at least local/dynamic threshold is implemented for contours in OpenCV, from what I recall.
Assuming you want to identify hand area instead of the area convex hull gives and background of the application is at least in same color, I would apply hsv-threshold to identify background instead of hand if possible. Or maybe adaptive threshold if light distribution is not consistent. I believe this is what many applications do
If background can't be fixed, the segmentation is not an easy problem to resolve as you should take care of shadows and palm lines.
i am new to opencv. i have to implement a headcount.
my idea is:
Identification of circular objects
We will start by edge detection to find border line of each shape.
sort through the image matrix pixel by pixel
for each pixel, analyze each of the 8 pixels surrounding it
record the value of the darkest pixel, and the lightest pixel
if (darkest_pixel_value - lightest_pixel_value) > threshold)
then rewrite that pixel as 1;
else rewrite that pixel as 0;
Now we detect shapes
count the number of continuous edges
a sharp change in line direction signifies a different line
do this by determining the average vector between adjacent pixels
if one line, then its a circle
by measure angles between lines more information can be deduced (rhomboid, equilateral triangle, etc.)
Face detection
This part includes two common approaches based on features and color. The basic idea of the algorithm is to find objects resembling an eye, then on the basis of geometric face characteristics try to join two the objects into an eye pair.
Steps:
Unimportant colors are eliminated from the image and insignificant colors are replaced with white color.
The image is then converted to grayscale.
The image is filtered with a median filter (unimportant white regions are blurred)
White regions are segmented using a Region growth algorithm.
Hough transform is applied to find circles
For each region the best possible circle is found
Using geometric face characteristics the pair of eyes is found
is this the right way to proceed or is there an easier way?
i want to count the number (estimate) of people found in a crowd (meetings, gatherings)
can you help me with the codes please?
Thank you
You can use the OpenCV built-in face detection.See http://opencv.willowgarage.com/wiki/FaceDetection for detailed instructions.
I had a similar project.
You need to get the best image so concentrate on fixing saturation, contrast and intensity.
If your planning to use color, if you want skin color detection for example, than you need to fix white balance.
Don't think of headcount, instead think of people count.
You need a good background segmentation, use Gaussian Mixture of Models
combined with other background modeling algorithm.
If this is an outdoor application you need shadow detection.
Get foreground blobs and then determine where people are in those blobs.
If your counting heads, you need to detect omega shape for the head and shoulders.
You will need tracking for occlusions and people crossing.
You can also use human body classification, opencv has haarcascade_fullbody.xml
These are just some ideas...