For get_interest_points.m, I implemented the basic Harris Corner Algorithm.
For get_features.m, I implement a basic SIFT like algorithm.
Feature Matching
I had to play around with the sigma value of the second gaussian filter in get_features.m. I hypothesize that down scaled images require smaller values of sigma. So changing the sigma value from feature width to three fourth the value increased accuracy by about 10%. I started with a threshold equal to the mean of the values in the matrix but I received way too few values. Reducing the threshold to mean/6, however, increased the number of keypoints to greater than 100.
Results: 89% - 134/150 correct | |
Results: 82% - 89/108 correct | |
Results: 0.00% - 0/7 correct |