EN161 - Image Processing and Understanding
Lab 7 - Segmentation
Due Tuesday 10/29
NOTE: Problems should be done in MATLAB.  Type up your solutions for each one including: (1) The answer to any questions posed, (2) any resulting images (include in document), and (3) the name of any function(s) (testfunc.m, threshold.m, etc.) you used. 

Zip or tar your document with your source code (m-files) into a file called [Lastname_FirstInitial_Lab7.zip/tar] and email it to mcchang@lems.brown.edu with the subject "EN161 Lab7".
 

 
Data:
 
Image A
Image B

 
Problem 1:
Implement region growing using the split & merge technique and use it on images A and B to identify different regions in the images. 

Use a local intensity range for the homogeneity property.  For example:

for region R with intensity values ranging from R_min to R_max, 
H(R) = True, if (R_max - R_min) < 100
H(R) = False, otherwise

How well did it work?  How could you improve the homogeneity property to achieve better results?

 
Problem 2:
Implement region growing using the boundary melting technique, and try it on images A and B.
Problem 3:
Compare these techniques.  What advantages does each have over the other?  Can you think of situations where each algorithm might break down?