Determine lowest part in sub regions of image and segment the image

1 view (last 30 days)
I want to segment object into head, torso and leg region.
There is a binary image and I want to:
- Calculate the sum of white pixels along each row
- Based on my knowledge from papers, head is located into 30% region of the image, torso 70%, and leg is the rest.
So I want to compare the sum of pixel in each row of each of the three regions, get the lowest pixel sum and its corresponding row in the image and then segment the image into the three parts.

Answers (1)

Image Analyst
Image Analyst on 22 Jun 2013
First threshold the image to get a binary image of the silhouette, or use some other method that basically gives you the silhouette. Then get the vertical profile by summing horizontally:
verticalSum = sum(binaryImage, 2);
Then examine that with your algorithm to identify valleys in the profile that determine where the dividing lines from head-to-torso and torso-to-legs are.
  4 Comments
Jack Sparrow
Jack Sparrow on 30 Jun 2013
Dear Image Analyst, you can please try the code on an upright human image to see the problem I have in the code.
I currently dont possess the right to display the images I have for now.

Sign in to comment.

Categories

Find more on Image Processing Toolbox in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!