Detekcija lica na slikama

undergraduate thesis

• Title (english): Face detection
• Author: Josip Matun
• Mentor: Tomislav Pribanić (mentor)
• Committee member: Tomislav Pribanić (predsjednik povjerenstva)
• Committee member: Igor Sunday Pandžić (član povjerenstva)
• Committee member: Vedrana Baličević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-09-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U ovom radu opisan je postupak detektiranja objekata prema Violi i Jonesu. Razmatra se primjena postupka za detekciju lica na slikama. U implementaciji ove metode koristi se kaskada binarnih klasifikatora koji se dobivaju boostanjem slabijih klasifikatora dobivenih direktno iz Haarovih značajki.
U radu je analizirana implementacija algoritma unutar programskog paketa OpenCV te je, također, napravljena vlastita implementacija u jeziku Python 2.7.7.
Također je napravljena evalucija postupka detekcije u sklopu koje su dani rezultati o brzini te točnosti opisanog postupka.

Abstract (english)

This paper considers face detection using Viola – Jones algorithm. In the process of implementation of this method a cascade of binary classifiers is used. Classifiers are created by boosting weaker classiefers based on Haar features.
This paper analyses the implementation of said algorithm within OpenCV program package. Also one's own implementation has been created within Python 2.7.7 language.
An evaluation of implementations was done as well. The evaluation consisted of testing speed and accuracy of described procedure.

• Keywords: računalni vid; lice; detekcija; realno vrijeme; Haarove značajke; binarni klasifikatori; boostanje; strojno učenje; algoritam Viole i Jonesa
• Keywords (english): computer vision; face; detection; real time; Haar features; binary classifiers; boosting; machine learning; Viola and Jones algorithm
• Language: croatian
• URN:NBN: urn:nbn:hr:168:813125
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-05 17:44:33