Skip to content

Home

Jump to bottom
Diego Herrera edited this page Jul 3, 2020 · 15 revisions

Welcome to the Correlation-Techniques-for-Face-Recognition wiki!

This project aims at studying correlation techniques for facial recognition. We explore the capabilities of correlation techniques as a non-segmentation alternative for biometric recognition. The use of correlation techniques has been historically developed in the context of optical correlators. However, in this project a digital implementation of correlation is considered as an illustration of the scope of these techniques. A simple application that performs identity verification and a simple threshold-based decision algorithm are developed using MATLAB. By means of a ROC curve analysis, parameters of the decision are chosen to achieve a confidence higher than 80% in the performance of the application under ideal conditions of illumination.

Objectives of the project

The main objective of the project is to perform subject identification using correlation techniques. In this project we aim at exploring two techniques: MACE filtering and Composite Filtering. Those techniques are based on a simple principle. A database of images is acquired, and a filter is devised in the image frequency domain so that matching is performed via correlation.

Fundamentals of Correlation Techniques

The basic approach of correlation techniques is the following:

  1. A set of carefully chosen training images is used to design a correlation filter that embodies the main features of the biometric of interest in a variety of scenarios.

  2. The correlation between the filter and a test image is computed in image frequency space. The output is known as correlation plane.

  3. The intensity pattern in the correlation plane is used to perform a decision concerning the recognition of the biometric of interest. If the pattern presents a sharp enough peak, the test image is said to correspond to the true class. This means that the biometric is likely to be found in the test image and the peak location is an indicator of the location of the biometric in the image plane. On the other hand, if the plane does not present a visible peak, the biometric is likely to be missing in the test image, and it is said to belong to the false class. This decision process is known as biometric matching.

The fundamental references of the project are:

Clone this wiki locally