Sustav za detekciju i identifikaciju većeg broja proizvoda putem QR-kôda

master's thesis

• Title (english): System for detection and identification of multiple products via QR code
• Author: Marin Rašić
• Mentor: Daniel Hofman (mentor)
• Committee member: Daniel Hofman (član povjerenstva)
• Committee member: Josip Knezović (član povjerenstva)
• Committee member: Igor Čavrak (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-02-28, Croatia

Abstract

Detekcija objekata je jedan od najznačajnijih problema područja računalnog vida. Moderni modeli detekcije objekata temelje se na dubokom učenju i neuronskim mrežama. Područje detekcije objekata se susreće s mnogim problemima, a jedan od njih je detekcija u stvarnom vremenu većeg broja objekata. QR kodovi su široko rasprostranjeni način kodiranja informacije. U sklopu ovog rada stvoren je program koji koristi YOLO model detekcije objekata za ostvarenje paralelne detekcije više objekata s QR kodovima u stvarnom vremenu.

Abstract (english)

Object detection is one the most significant problems in the field of computer vision. Modern object detection models are based on deep learning and neural networks. The field of object detection faces many problems, one of which is real-time detection of a large number of objects. QR codes are a widespread way of encoding information. As part of this paper, a program was created that uses YOLO object detection model to achieve parallel detection of multiple objects with QR codes in real time.

• Keywords: detekcija objekata; konvolucijske neuronske mreže; YOLO model; QR kod
• Keywords (english): object detection; convolutional neural networks; YOLO model; QR code
• Language: croatian
• URN:NBN: urn:nbn:hr:168:873018
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2024-03-28 07:53:08