Project 3: Object categorization with a “bag of
keypoints”
Description
•
Implement
a bag of ‘words’ approach described in “Visual Categorization
with Bags of Keypoints” G.Cruska, C. R. Dance, L.Fan, J.Willamowski,C.
Bray.
•
Test
it on Bar-Hillel Data set
Results
The detection results should
be presented as a confusion matrix
Example on Dogs vs. easy
animals
|
|
Dogs |
Easy Animals |
|
Dogs |
How
many of the dogs are classified as dogs |
How
many of the other animals are classified as
dogs |
|
Easy Animals |
How
many of the dogs are classified as other
animals |
How
many of the other animals are classified as other animals |
Obviously the best results
will produce diagonal confusion matrix.
Similar tables should be
obtained for each test.
Interest Point Detectors
Use Kadir interest point detectors and SIFT
image descriptors.
For feature extraction code contact the instructor.
Data sets
The system should be trained
and tested on Bar-Hillel data sets:
1) dogs vs. easy animals
2) dogs vs. hard animals
3) Chairs vs. furniture
background.
The data will be provided by
the instructor.
Instructor
Mr. Elran Morash
"
Consulting hours:
Monday
10:00-12:00 a.m
Wednesday 16:00- 18:00 p.m
Phone: 8301
Email: elranmorash at nana.co.il
SVM Package
K-Means
Use MATLAB function kmeans(…) for
the codebook construction.
Useful Links
"Distinctive image features from scale-invariant
keypoints" by David Lowe
Status
Claimed
by Eli Abromovitch, Kobi Afoota