Computer vision is a technique that is used to identify and classify images of similarities within a image set. This process is known as a visual search.
The aim of this project was to create a visual search using some of the traditional computer vision techniques using MATLAB.
Visual search is based on computing an accurate image descriptor for a query image that is manually selected by the user or automatically by the system. It is then represented in an N dimensional feature space. The rest of the images are represented in the feature space in which it measured against the query image using distance.
This completed was completed at Surrey University. Below is a link to the project repository.