Abhishek Patil
← Back to Projects Face Recognition

Face Recognition

face recognitionface detectionOpenCvfisherfaceseigenfacesrobotics

Goal

Using a webcam, OpenCV and ROS, develop an API to recognize people in real-time.

Overview

The following flow-chart shows how the interface functions:

Face Recognition Flow Chart

Demo

Project Website

This project was integrated into another bigger project on TurtleBot navigation and can be viewed here: TurtleBot Navigation

Project Details

Fisherfaces algorithm is implemented to train and recognize faces. The algorithm can be summarized as follows:

Fisherfaces Algorithm

The code (integrated with ROS & the TurtleBot project) is available on GitHub: patilnabhi/tbotnav

Future Work

  • Improve accuracy of classification by combining various classifiers such as Principal Component Analysis (PCA), Independent Component Analysis (ICA) and LDA; this could be done using a Radial Basis Function (RBF)-based interpolation.

This project was completed as part of the MS in Robotics ([MSR]) program at Northwestern University.