MATLAB: Kurtosis and skewness detection

boundary descriptionregion properties

I want to calculate Kurtosis and skewness of a region whose area is 1287 and perimeter is 166.3575, but kurtosis value of total image is obtain. How Kurtosis value of a single region is obtained.

Best Answer

See my demo on image moments, attached below in blue. It calculates skew and kurtosis of the histogram. Feel free to adapt it to your needs.

How were you getting the kurtosis of the entire image up to now? To get it for any particular blob, you have to call regionprops and ask for pixelList, as shown in my BlobsDemo tutorial in my File Exchange. Then loop over all blobs getting their kurtosis:

for k = 1 : numberOfBlobs           % Loop through all blobs.
  % Get list of pixels in current blob.
  thisBlobsPixels = blobMeasurements(k).PixelIdxList;
  % Get kurtosis of this blob, using your recipe or Image Analyst's.
  kurtosis(k) = ComputeKurtosis(thisBlobsPixels);
end

Related Solutions

MATLAB: Threshold image after applying mask

I think imbinarize() and graythresh() work on 1-D images. So if you want to determine the a threshold only considering the gray levels of the gray ring and not considering the black background, extract the ring pixels into a list and pass them to graythresh():

ringPixels = originalImage(originalImage > theThreshold); % No black pixels here
newThreshold = graythresh(ringPixels);

Since you've already masked the image by doing something like

maskedImage = originalImage; % Initialize
maskedImage(mask) = 0; % Erase background.

you could also do the first line like this

ringPixels = maskedImage(maskedImage > 0);

and then call graythresh();

MATLAB: How to detect the waist in a BW image

Why not use imdistline() or improfile() to manually specify them. Unless you have hundreds of images and need to do this automatically, that's probably the best way.

Otherwise, first call bwareafilt() to extract the largest blob. Then try to iterate where you call imdilate() followed by bwlabel() to count the number of blobs and quit when you get to two. Then binarize again and call bwmorph() with the "thicken" option to expand the blobs out so that they touch, but will not join/combine them. Then label again and call graycomatrix() to count how many pixels of blob #1 occur next to blob #2.

Best Answer

Related Solutions

MATLAB: Threshold image after applying mask

MATLAB: How to detect the waist in a BW image

Related Question