Detekcija odjevnih predmeta u slikama

master's thesis

• Title (english): Detection of Clothing in Images
• Author: Kristijan Kecerin
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Tomislav Hrkać (član povjerenstva)
• Committee member: Slobodan Ribarić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu opisan je problem detekcije odjevnih predmeta na slikama.
Objašnjene su konvolucijske neuronske mreže, njihova važnost i najbitniji
koncepti koji stoje iza njihova načina rada. Potom slijedi uvid u sposobnost
konvolucijskih neuronskih mreža da obavljaju zadatak semantičke segmentacije.
Konačno, implementiran je jedan od modela potpuno konvolucijskih mreža i
prikazani su rezultati njegova rada u kontekstu semantičke segmentacije
odjevnih predmeta na slikama.

Abstract (english)

This thesis is an overview of an approach to solve the problem of detecting
clothing in images. The explanation of most important concepts behind
convolutional neural networks is given. This is followed by the description of
an insight which enables the convolutional neural networks to be used in
solving the problem of semantic segmentation. Finally, a fully convolutional
network is implemented and its performance evaluated on the task of
semantic segmentation of clothing in images.

• Keywords: semantička segmentacija odjeće; duboko učenje; konvolucijske neuronske mreže; potpuno konvolucijske mreže
• Keywords (english): semantic segmentation of clothing; deep learning; convolutional neural networks; fully convolutional networks
• Language: croatian
• URN:NBN: urn:nbn:hr:168:253972
• 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: 2019-03-13 21:29:13