Pronalaženje grafičkih oblika

undergraduate thesis

• Title (english): Locating of graphical forms
• Author: Stjepan Kurilovčan
• Mentor: Dragan Jevtić (mentor)
• Committee member: Dragan Jevtić (predsjednik povjerenstva)
• Committee member: Aleksandar Antonić (član povjerenstva)
• Committee member: Darko Štriga (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-10, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U ovom je radu opisan postupak detektiranja objekata pomoću raznih metoda a navedene su i smetnje koje otežavaju samu detekciju . Tu je konkretno obrađena detekcijom lica i očiju. U tu svrhu je korištena Viola-Jones metoda za detekciju objekata. Pri implementaciji ove metode korištene su kaskade klasifikatora dobivene ojačavanjem slabih klasifikatora. Ti su klasifikatori direktno dobiveni iz Haar-ovih značajki. Implementacija programa je rađenja u programskom jeziku Python verzije 2.7.13 uz korištenje NumPy i OpenCV biblioteka.

Abstract (english)

In this paper, a concept of detecting objects using various methods was described and some issues that make detection harder were named. Specifically, face and eyes detection was described. Viola-Jones method was used for objects detection. Further, implementing this method, classifier cascades were used that were obtained by strengthening weak classifiers. These classifiers were directly obtained from Haar features. Program implementing was done in programming language Python, version 2.7.13, with the use of NumPy and OpenCV libraries.

• Keywords: Haar-ove značajke; detekcija lica; izrazi lica; osvjetljenje; orijentacija slike; strojno učenje; klasifikatori; Viola-Jones algoritam; računalni vid; realno vrijeme
• Keywords (english): Haar features; face detection; facial expression; illumination; image orientation; machine learning; classifiers; Viola-Jones algorithm; computer vision; real time
• Language: croatian
• URN:NBN: urn:nbn:hr:168:530451
• 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: 2019-03-13 22:08:32