bjoernz
  • Member for 10 years, 5 months
  • Last seen more than 3 years ago
Fastest Algorithm for Distance Transform
Accepted answer
16 votes

Pedro F. Felzenszwalb and Daniel P. Huttenlocher have published their implementation for the distance transform. You cannot use it for volumetric images, but maybe you can extend it to support 3d data....

View answer
Alternatives to Hough transform for detecting a grid-like structure
11 votes

An alternative to the Hough Transform would be the Radon Transform (1, 2). A rough description of an algorithm to detect a grid-like structure could look like this: 1. Perform Radon Transform from 0 ...

View answer
main direction in 2D map of data
Accepted answer
7 votes

You could compute the covariance matrix from your elevation data. The eigenvector that belongs to the larger eigenvalue will give you the main direction of variation: http://en.wikipedia.org/wiki/...

View answer
OpenCV/C++ connect nearby contours based on distance between them
6 votes

To fix the connectivity issue, you can try a close operation: cv::Mat structuringElement = cv::getStructuringElement(cv::MORPH_ELLIPSE, cv::Size(40, 40)); cv::morphologyEx( inputImage, outputImage, ...

View answer
count blood cells
5 votes

Just an idea with no guarantee of success: isolate the red blobs (e.g. mark them as white, the rest of the image as black) perform a distance transform for the white blobs (every pixel indicates the ...

View answer
JPEG steganography
5 votes

I am not sure if Jsteg, Outguess or F5 make already use of this, but in theory you could use the APP segment to hide information. Also the Quantization Table (DQT) could offer some limited space. You ...

View answer
Skel to infinity morphological operations on 3D volume
Accepted answer
4 votes

As a start, you could look at the distance transform. The distance transform will assign each voxel the minimal distance to the volume boundary. Afterwards you could do a non-maximum suppression. The ...

View answer
maximum contrast using linear gery-level trasformation
Accepted answer
2 votes

You want to design a linear transformation, that puts the MIN(I) at 0 and the MAX(I) at 1. A linear equation has the form: y = m*x+b, where m is the slope and b is the point on the y-axis for x = 0. ...

View answer
Commonly used test image sets
2 votes

Collections of data sets for various computer vision tasks: http://www.computervisiononline.com/datasets http://www.cvpapers.com/datasets.html

View answer
Tools for 3D shape analysis
Accepted answer
2 votes

To approximate the volume ($V_{counted}$) you need to count all the voxels. To roughly approximate the surface area ($A_{approx}$) count all the voxels that have an "empty" voxel as a neighbor. (Have ...

View answer
Is there an algorithm to compare several pictures?
2 votes

It looks like you are looking for algorithms for Content-Based Image Retrieval. As long as you don't expect any miracles, you should be quite happy with a colour histogram approach. Have a look at ...

View answer
How can i compute perimeter and area of a skeletonized circle?
1 votes

It is not clear if the skeletonized image can be reversed to a contour image. Skeletonization is often done by calculating the distance transform and then thresholding the result or performing a non-...

View answer
YV12 to RGB - What is wrong with my algorithm?
1 votes

I don't know anything about fragment shader programming, but to me it looks like the word size of the input and output vary. And to me it looks like, you don't pay attention to unpacking and repacking ...

View answer