1. EE 596 Machine Vision HW 6
Assigned: Nov 20, 2013
Due: Dec 8, 2013 at 11:59pm
img img img5

2. Your task Write Harris detector HarrisCornerDetector() in features.cpp
Write Feature descriptor ComputeDescriptors() in features.cpp
Run your program to get required numerical and image results

3. Interest Point Detection
Convert the RGB image to a gray-scale image.
(Save the RGB image for later.)
Apply a 9 x 9 Gaussian filter we give you.
3. Construct the Harris matrix M using a 5 x 5
neighborhood around each pixel.
Compute corner response R = det(M) – k*Tr(M)2
at each pixel.
If R is above a threshold and is a local maximum
in a 3 x 3 neighborhood, select it as an interest point.
600 to 3000 points are expected to be detected for each
image

4. Feature Description Go back to RGB space.
2. Take a 45 x 45 window around each feature point.
Divide that window into 9 x 9 squares, each
of them size 5 x 5.
Applying a (given) 5 x 5 mask to each of these
squares in each of R, G, and B, gives 3 results
per square x 81 squares = a vector V of 243 values.
Compute V = V / ||V||2 (V divided by its L2-norm).
V is the descriptor.

5. Features Matching
1. Always find matches between img1.ppm and other images
Features matching and homography have been provided in both C++ and Matlab

6. Visualize Matches Load img1.ppm Load img2.ppm Click “Harris Corners”
Click “Find Matches”
Matlab Users:
Visualize matches in your own way
No need for a GUI

7. The GUI

8. After Harris Detector

9. After Matching