Primjena nenadziranog strojnog učenja u grupiranju slika

master's thesis

• Title (english): Application of unsupervised machine learning in image clustering
• Author: Iva Kvasina
• Mentor: Sanja Seljan (mentor)
• Committee member: Ivan Dunđer (predsjednik povjerenstva)
• Committee member: Vjera Lopina (član povjerenstva)
• Committee member: Sanja Seljan (član povjerenstva)
• Granter: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences); Zagreb
• Defense date and country: 2024-09-26, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences

Abstract

Diplomski rad je temeljen na dva ključna dijela - teorijskom i praktičnom. U prvom dijelu, fokus će biti na opisu nenadziranih algoritama strojnog učenja. Drugi dio, praktični, obuhvaća istraživanje koje uključuje prikupljanje podataka za treniranje modela te testiranje i evaluaciju. Podaci će biti prikupljeni s javno dostupnih resursa, uz korištenje slika generiranih alatima umjetne inteligencije. Nakon definiranog vremenskog okvira za učenje modela, koristit će se testni podaci za evaluaciju. Konačni cilj rada je testiranje alata za grupiranje slika putem primjene raznolikih algoritama strojnog učenja s posebnim naglaskom na treniranje alata sposobnog prepoznati i kategorizirati raznovrsne haljine temeljem njihovih karakteristika. Na kraju će biti predstavljeni rezultati rada s ciljem ocjene uspješnosti razvijenog modela.

Abstract (english)

The thesis is based on two key parts - theoretical and practical. In the first part, the focus will be on the description of unsupervised machine learning algorithms. The second part, practical, includes research that includes data collection for model training and testing and evaluation. Data will be collected from publicly available resources, using images generated by artificial intelligence tools. After a defined time frame for model learning, test data will be used for evaluation. The final goal of the work is to test a tool for grouping images through the application of various machine learning algorithms with a special emphasis on training a tool capable of recognizing and categorizing various dresses based on their characteristics. At the end, the results of the work will be presented with the aim of evaluating the success of the developed model.

• Keywords: strojno učenje; nenadzirano učenje; grupiranje slika; umjetna inteligencija
• Keywords (english): machine learning; unsupervised learning; clustering images; artificial intelligence
• Language: croatian
• URN:NBN: urn:nbn:hr:131:731040
• Study programme: Title: Information Sciences; specializations in: Archivistics Study, Library Science, Information Sciences (research), Information Sciences (teaching), Museology and heritage management, Informatology; Course: Information Sciences (research); Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra informacijskih znanosti (magistar/magistra informacijskih znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-09-27 22:09:59