Segmentacija objekata na slikama

undergraduate thesis

• Title (english): Object Segmentation
• Author: Fran Čudina
• Mentor: Tomislav Pribanić (mentor)
• Committee member: Tomislav Pribanić (predsjednik povjerenstva)
• Committee member: Kristijan Bartol (član povjerenstva)
• Committee member: David Bojanić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Segmentacija slika, zadnjih nekoliko godina, postala je popularna tema s kojom se ljudi u velikom broju susreću tijekom svog obrazovanja. Zbog velikog opsega zadataka koje rješava, upravo primjena konvolucijskih neuronskih mreža pokazala se jednom od najboljih metoda u prepoznavanju objekata na slikama. U radu je opisana i predstavljena metoda prepoznavanja višestrukih objekata sa slike upotrebom konvolucijskih neuronskih mreža kao jedan od načina segmentacije. Skup podataka, nad kojim je mreža trenirana, sastoji se od slika iz ljudskih svakodnevnih aktivnosti. U radu je detaljno opisan proces koji je mreža prolazila, te rezultate koje je postigla učenjem na navedenom skupu podataka.

Abstract (english)

Image segmentation, over the last few years, has become a popular topic that people encounter in large numbers during their education. Due to the wide range of tasks it solves, the application of convolutional neural networks has proven to be one of the best methods in recognizing objects in images. The paper describes and presents a method of recognizing multiple objects from an image using convolutional neural networks as one of the methods of segmentation. The dataset, over which the network is trained, consists of images from human daily activities. The paper describes in detail the process that the network went through and the results it achieved by learning from the specified dataset.

• Keywords: segmentacija objekata; semantička segmentacija; računalni vid; duboko učenje; duboke neuronske mreže; konvolucijske neuronske mreže
• Keywords (english): object segmentation; semantic segmentation; computer vision; deep learning; deep neural networks; convolutional neural networks
• Language: croatian
• URN:NBN: urn:nbn:hr:168:611588
• 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: 2023-01-14 08:39:19