Demonstrates all the Computer Vision topics undertaken and programmed on.
Each Project inside this Repository gives a brief description on an aspect of Computer Vision.
Topics that are covered are:
Spatial Pyramid Matching for Scene Classification:
In Natural Language Processing we have Bag of Words, where we count the number of each word appears in a document, use the frequency of each word to know the keywords of the document, and make a frequency histogram from it. Similarly in Computer Vision, we develop a bag of visual words (BOVW), but instead of words, we use image features as the “words”. Image features are unique pattern that we can find in an image. This Bag of Visual Words is then employed to classify scenes based on kMeans clusters.
Augmented Reality with Planar Homographies:
Lucas Kanade Tracking Algorithm: