Efikasno raspoznavanje lica u ograničenoj bazi osoba

master's thesis

• Title (english): Efficient face recognition from the limited data base
• Author: Marko Kolarek
• Mentor: Marko Subašić (mentor)
• Committee member: Marko Subašić (predsjednik povjerenstva)
• Committee member: Sven Lončarić (član povjerenstva)
• Committee member: Zvonko Kostanjčar (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U okviru ovog rada istražujemo mogućnosti i metode rada Viola-Jones sustava za detekciju lica, te razmatramo mogućnosti njegove prilagodbe kako bi uz detekciju omogućavao i raspoznavanje ograničenog broja lica u danoj slici ili u videu uz pomoć neuronskih mreža. Izabrane su radijalne neuronske mreže jer omogućuju dodavanje novih osoba u postojeću bazu na brz i efikasan način koji je i uspješno implementiran u ovom radu. U okviru rada također je razmatrana te naposljetku i definirana odgovarajuća ispitna baza lica za detektor na kojoj su vršena testiranja detektora i mjerenja njegove osjetljivosti.

Abstract (english)

In this thesis we explore the possibilities and methods of the Viola-Jones face detection system, and we consider the possibility of adjusting it so that it can be able to recognize faces in an image or video from a small database of possible persons with the use of neural networks. Radial basis function neural networks have been chosen because they enable adding of new persons in an existing database in a fast and efficient way that has been successfully implemented in this thesis. We have also considered and defined an appropriate training and testing database of faces for the system on which tests and measurements of the systems sensitivity have been made.

• Keywords: Viola-Jones; detekcija lica; raspoznavanje lica; OpenCV; C/C++; MATLAB; slika; video; strojno učenje; radijalne mreže
• Keywords (english): Viola-Jones; face detecetion; face recognition; OpenCV; C/C++; image; video; machine learning; radial basis networks
• Language: croatian
• URN:NBN: urn:nbn:hr:168:917036
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 09:43:01