prikaz prve stranice dokumenta Detekcija i raspoznavanje igraćih karata u slikama
No public access
undergraduate thesis
Detekcija i raspoznavanje igraćih karata u slikama
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. urn:nbn:hr:168:043682
Štetić, Filip
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Štetić, F. (2020). Detekcija i raspoznavanje igraćih karata u slikama (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:043682

Štetić, Filip. "Detekcija i raspoznavanje igraćih karata u slikama." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:043682

Štetić, Filip. "Detekcija i raspoznavanje igraćih karata u slikama." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:043682

Štetić, F. (2020). 'Detekcija i raspoznavanje igraćih karata u slikama', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 27 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:043682

Štetić F. Detekcija i raspoznavanje igraćih karata u slikama [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 November 27] Available at: https://urn.nsk.hr/urn:nbn:hr:168:043682

F. Štetić, "Detekcija i raspoznavanje igraćih karata u slikama", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:043682

Metadata
TitleDetekcija i raspoznavanje igraćih karata u slikama
Title (english)Detection and Recognition of Playing Cards in Images
AuthorFilip Štetić
MentorTomislav Hrkać (mentor)
Committee memberTomislav Hrkać (predsjednik povjerenstva)
Committee memberDino Šantl (član povjerenstva)
Committee memberZoran Medić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-08-27, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U radu se predstavljaju elementi neuronske mreže za detekciju i raspoznavanje objekata. Objašnjeni su neki poznati modeli koji su osvajali popularne izazove računalnog vida unazad par godina. Daje se opis arhitekture od najniže razine, umjetnog neurona, do današnjeg state-of-the-art modela Mask R-CNN-a. Nakon teorijskog uvoda upoznaje se s radnim okvirom za detekciju objekata, Tensorflow API. Pomoću njega trenira se model za prepoznavanje karata za Belot. Dobiva se model sa srednjom prosječnom preciznošću od 71.43% i srednjim prosječnim odzivom od 76.02%.
Abstract (english)
This paper introduces elements of neural networks for detection and recognition of objects. Some well known variants of models, which have won popular challenges of computer vision some years ago, are explained. Description is given of architecture from it’s lowest part, artificial neuron, to todays state-of-the-art model Mask R-CNN. After the theoretical introduction we get familiar with framework for object detection, Tensorflow API. With it’s help a model is trained for recognition of playing cards for the game Belote. Final model has mean average precision of 71.43% and mean average recall of 76.02%.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:043682
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 on2023-01-14 21:49:47