prikaz prve stranice dokumenta Detekcija lica u videosnimkama
No public access
undergraduate thesis
Detekcija lica u videosnimkama
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:862857
Žeger, Ivana
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Žeger, I. (2018). Detekcija lica u videosnimkama (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:862857

Žeger, Ivana. "Detekcija lica u videosnimkama." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:862857

Žeger, Ivana. "Detekcija lica u videosnimkama." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:862857

Žeger, I. (2018). 'Detekcija lica u videosnimkama', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 18 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:862857

Žeger I. Detekcija lica u videosnimkama [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 November 18] Available at: https://urn.nsk.hr/urn:nbn:hr:168:862857

I. Žeger, "Detekcija lica u videosnimkama", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:862857

Metadata
TitleDetekcija lica u videosnimkama
Title (english)Face Detection in Video Sequences
AuthorIvana Žeger
MentorSonja Grgić (mentor)
Committee memberSonja Grgić (predsjednik povjerenstva)
Committee memberTomislav Kos (član povjerenstva)
Committee memberJelena Božek (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
Detekcija lica je metoda lociranja i odvajanja područja lica u samostalnim slikama i nizovima slika u vremenu (videosnimkama). Početni je korak u mnogim primjenama računalnog vida. Iz perspektive računala, predstavlja vrlo kompleksan zadatak. Lica se razlikuju estetski, iskazivanjem emocija, po boji kože, ali i utjecajem vanjskih faktora kao što su osvijetljenost scene, orijentacija lica, kontrast lica i pozadine, zaklonjenost, udaljenost od objektiva, itd. Ne postoji jedinstven kriterij grupiranja metoda detekcije lica. Često korišteni jednostavni algoritmi temelje se na detekciji boje ljudske kože. Ipak, potencijalni problem predstavlja postojanje objekata u nijansama sličnima boji kože u okolini lica te činjenica da pikseli kože ne moraju predstavljati piksele lica. Inženjerima najzanimljiviji metode temeljene su na strojnom učenju i statističkoj analizi, pri čemu se najveća pažnja posvećuje neuronskim mrežama.
Abstract (english)
Face detection is a method of locating and separating facial area in images and image sequences related by time (video sequences). It has been the initial step in various computer vision applications. It represents a highly complex task for a computer system. There is an esthetical distinction between faces, they differentiate by emotion expression, skin color. External factor contribution is not negligible, i.e. lighting condition, facial orientation, face-background contrast, occlusion, scale, etc. Furthermore, no unique grouping criterium for face detection methods exits. Frequently used algorithms are based on human skin color detection. However, the existence of objects with the color tone very similar to the skin color around faces could lead to a potential problem alongside the fact that skin pixels do not necessarily correspond to facial pixels. The most interesting methods for face detection nowadays are based on machine learning and statistical analysis while the greatest attention is given to neural networks.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:862857
Study programmeTitle: Electrical Engineering and Information Technology
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-14 02:24:11