Description
2 Background
The purpose of this assignment is to solve a more challenging segmentation problem using a modern
segmentation algoirthm.
2.1 Assignment Synposis
The dataset of this assignment consists of images of leaves on a cluttered background — the same dataset
as in Assignment 3, but this time, the images are corrupted by noise! Since it is robust to noise, you’ll
use the random walker algorithm to segment the dataset. Performance will be gauged by mean Dice
coefficient.
2.2 Images
Download the archive original-noisy.zip. This archive contains 30 colour images of leaves against
various backgrounds. These are the same images from assignment 3, but they are now corrupted by noise.
As before there are images of three different classes (shapes) of leaves. The first class has image numbers
between 1 and 19; the second class are in the files numbered 78 through 113; and the third class is in the
images numbered between 132 and 175.
Download segmented.zip which is a set of binary images representing the “ground truth” for each of
the 30 images in original.zip. This is the exact same ground truth as from Assignment 3. As before,
these binary images will be treated as the “right answer” when performing segmentation validation.
White pixels denote the pixels that your segmentation algorithm should add to the leaf region.
3 Problems
Question 1 (36 points):
Detailed instructions are provided asn4-q1.ipynb.
Notice that on the grading rubric (see Moodle) there are some points for how well your algorithm
performs. You should be able to achieve at a mean DSC of at least 0.7 – this is the bare minimum we
are expecting for accuracy and will earn you only half of these “accuracy marks”. For full “accuracy”
marks for you will need to obtain a mean DSC of at least 0.8. You will still get most of the marks for
achieving a mean DSC of at least 0.75.
4 Files Provided
asn4-qX.ipynb: These are iPython notebooks, one for each question, which includes instructions and in
which you will do your assignment.
images-noisy.zip: Original images to be segmented.
groundtruth.zip: Binary ground truth images.
5 What to Hand In
Hand in your completed iPython notebooks, one for each question.
6 Appendix A — Grading Rubric
Grading rubric is available on Moodle.
Page 2
