prikaz prve stranice dokumenta Detekcija lica u videu na temelju Viola-Jones algoritma i informacije o dubini scene
No public access
undergraduate thesis
Detekcija lica u videu na temelju Viola-Jones algoritma i informacije o dubini scene
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2015. urn:nbn:hr:168:346531
Backović, Hrvoje
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Backović, H. (2015). Detekcija lica u videu na temelju Viola-Jones algoritma i informacije o dubini scene (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:346531

Backović, Hrvoje. "Detekcija lica u videu na temelju Viola-Jones algoritma i informacije o dubini scene." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2015. https://urn.nsk.hr/urn:nbn:hr:168:346531

Backović, Hrvoje. "Detekcija lica u videu na temelju Viola-Jones algoritma i informacije o dubini scene." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2015. https://urn.nsk.hr/urn:nbn:hr:168:346531

Backović, H. (2015). 'Detekcija lica u videu na temelju Viola-Jones algoritma i informacije o dubini scene', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 16 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:346531

Backović H. Detekcija lica u videu na temelju Viola-Jones algoritma i informacije o dubini scene [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2015 [cited 2024 July 16] Available at: https://urn.nsk.hr/urn:nbn:hr:168:346531

H. Backović, "Detekcija lica u videu na temelju Viola-Jones algoritma i informacije o dubini scene", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2015. Available at: https://urn.nsk.hr/urn:nbn:hr:168:346531

Metadata
TitleDetekcija lica u videu na temelju Viola-Jones algoritma i informacije o dubini scene
Title (english)Face Detection in Video Based on Viola-Jones Algorithm and Scene Depth Information
AuthorHrvoje Backović
MentorSlobodan Ribarić (mentor)
Committee memberSlobodan Ribarić (predsjednik povjerenstva)
Committee memberDarijan Marčetić (član povjerenstva)
Committee memberMartin Soldić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2015-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu prikazan je postupak detekcije lica na video sekvencama koji se temelji na fuziji Viola-Jones algoritma i informaciji o dubini scene. Detekcija se obavlja algoritmom Viola-Jones koji na video sekvenci pronalazi okvire koji su kandidati za lice, a zatim se pomoću informacije o dubini scene odbacuju oni okviri koji ne odgovaraju zadanim uvjetima. Osim teorijskog opisa samog postupka, analizira se i implementacija samog algoritma na vlastito oblikovanoj eksperimentalnoj bazi video sekvenci koja ima pridruženu informaciju o dubini scene. Prikazani su rezultati eksperimentalne provjere vjerodostojnosti algoritma iz kojih se vidi kako dodatna informacija o dubini scene utječe na točnost detekcije lica.
Abstract (english)
This text shows a procedure for face detection in video clips based on the fusion of Viola-Jones algorithm and scene depth information. A detection is made by running the Viola-Jones algorithm which locates candidate frames that may or may not contain faces. After that, depth information is used to reject frames that do not satisfy the given conditions. In addition to the theoretical description of the procedure, the text analyzes an implementation of the algorithm tested on a self made video database which includes the depth information. Experiments have been conducted on this database and the results are shown in this work. From these results you can see how scene depth information affects the accuracy of face detection.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:346531
Study programmeTitle: 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 resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2018-02-06 07:40:18