In this Repo you will find documentation of the process of exploring correlation filters and Fourier transforms to identify a human face using advanced correlation techniques. It is a project developed for the course on Optics and Acoustics from the National University of Colombia. It is carried out by:
- Diego Alejandro Herrera rojas
- Luis Neme
- Andrés Duque
- Juan Manuel Moreno
The aim is to develop a MATLAB - based application that may be deployed on any computer, that ultimately will identify a persons face in a scene. If possible, an Android application might be developed so that the face-recognition system can be used in a smartphone.
The project contains the following folders:
- MATLABCodes: This folder contains the MATLAB codes used to explore the capabilities of correlation techniques.
- images: Contains images for filter synthesis and further facial identification processes.
- Figures: Contains images for initial exploration.
In order to keep track of the work, the following formats are proposed for committing files to the repository:
-
All code files must me in a directory with the name (Language)Codes. For instance, if the codes are in MATLAB, they must be in the directory MATLABCodes.
-
All code files must have a heading that includes: 1) Descriptive title, 2) Author's name, 3) Date of deploy, 4) Brief description. Codes must be accurately commented so that anyone can understand them.
-
Al images that are not used for filter synthesis must go in the directory Figures. Images that are used for filter synthesis must be in directory images, and in a subdirectory with the name of the person to be identified.
-
Al images must be stored in PNG format.