This code was written for the course Computer Vision (CSCI-B 657) at Indiana University handled by Professor David Crandall. Skeleton code was provided by the Professor to get us started with the assignment.
What does the program do?
- The program tries to label the specific scene to which the given image belongs.
How does it find it?
- The program uses Bag of Words model to extract features and then Cornell's SVMLight to train and classify based on these features.
Detailed explanation about how the code works and the reason why we chose this implementation could be found here.