Back to search

Rochester Institute of Technology

Real time face matching with multiple cameras using principal component analysis

Abstract

dc:description.abstract

Face recognition is a rapidly advancing research topic due to the large number of applications that can benefit from it. Face recognition consists of determining whether a known face is present in an image and is typically composed of four distinct steps. These steps are face detection, face alignment, feature extraction, and face classification [1]. The leading application for face recognition is video surveillance. The majority of current research in face recognition has focused on determining if a face is present in an image, and if so, which subject in a known database is the closest match. This Thesis deals with face matching, which is a subset of face recognition, focusing on face identification, yet it is an area where little research has been done. The objective of face matching is to determine, in real-time, the degree of confidence to which a live subject matches a facial image. Applications for face matching include video surveillance, determination of identification credentials, computer-human interfaces, and communications security. The method proposed here employs principal component analysis [16] to create a method of face matching which is both computationally efficient and accurate. This method is integrated into a real time system that is based upon a two camera setup. It is able to scan the room, detect faces, and zoom in for a high quality capture of the facial features. The image capture is used in a face matching process to determine if the person found is the desired target. The performance of the system is analyzed based upon the matching accuracy for 10 unique subjects.

Degree

thesis:*
Name thesis:degree_name
Computer Engineering (MS)
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Computer Engineering (KGCOE)

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Mullen, Andrew
Contributors dc:contributor
  • Andreas Savakis

Identifiers

dc:identifier.*
Repository record dc:identifier
https://repository.rit.edu/theses/8021

Chain of custody

source
Harvested from
Rochester Institute of Technology
Base URL
repository.rit.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Mullen, Andrew. Real time face matching with multiple cameras using principal component analysis. Thesis thesis, https://repository.rit.edu/theses/8021