prikaz prve stranice dokumenta Automatsko prepoznavanje emocija na fotografijama ljudskih lica
Access restricted to authenticated users
master's thesis
Automatsko prepoznavanje emocija na fotografijama ljudskih lica
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. urn:nbn:hr:179:783004
Ujdur, Petra
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Institutional repository: Repository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Ujdur, P. (2022). Automatsko prepoznavanje emocija na fotografijama ljudskih lica (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:783004

Ujdur, Petra. "Automatsko prepoznavanje emocija na fotografijama ljudskih lica." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:783004

Ujdur, Petra. "Automatsko prepoznavanje emocija na fotografijama ljudskih lica." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:783004

Ujdur, P. (2022). 'Automatsko prepoznavanje emocija na fotografijama ljudskih lica', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 11 July 2024, https://urn.nsk.hr/urn:nbn:hr:179:783004

Ujdur P. Automatsko prepoznavanje emocija na fotografijama ljudskih lica [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 July 11] Available at: https://urn.nsk.hr/urn:nbn:hr:179:783004

P. Ujdur, "Automatsko prepoznavanje emocija na fotografijama ljudskih lica", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:783004

Metadata
TitleAutomatsko prepoznavanje emocija na fotografijama ljudskih lica
Title (english)Automatic recognition of emotions in photographs of human faces
AuthorPetra Ujdur
MentorMaja Braović https://orcid.org/0000-0002-3655-3534 (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-07-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Tema diplomskog rada je automatsko prepoznavanje emocija na fotografijama ljudskih lica. Rad je podijeljen na teorijski i praktični dio. Teorijski dio se bazira na približavanju pojma umjetne inteligencije te njenim područjima i tehnikama koje će se koristiti kod izrade programa. U izradi programa za automatsku detekciju emocija korišten je programski jezik Python, a sami program je nastao u Anaconda razvojnom okruženju uz pomoć Jupyter Notebook web-aplikacije. Predstavljene su baze fotografija koje su dostupne za slobodno korištenje, a odabrana je baza FER2013. Objašnjene su razne metode koje se mogu koristiti za detekciju emocija na fotografijama. Tehnike koje su se koristile kod razvoja programa za automatsko prepoznavanje emocija na fotografijama ljudskih lica su duboko učenje te neuralne mreže koristeći metodu prijenosnog učenja. U praktičnom dijelu rada primjenjuju se sva stečena znanja iz teorijskog dijela. Prvi korak je pripremiti bazu fotografija za ulaz u neuralnu mrežu. Nakon stvaranja modela neuralne mreže koja se sastoji od više kompleksnih slojeva, odvijaju se ključni koraci treniranja mreže te validacija. Validacija neuralne mreže prikazana je preko matrice konfuzije.
Abstract (english)
The topic of the thesis is automatic recognition of emotions in photographs of human faces. The paper is divided into theoretical and practical part. Theoretical part is based on the concept of artificial intelligence and its areas and techniques that will be used in the development of the program. The Python programming language is used to create the automatic emotion detection program, and the program itself was created in the Anaconda development environment with the help of the Jupyter Notebook web application. Databases of pictures that are available for free use are presented and the FER-2013 database is chosen. Various methods that can be used to detect emotions in photos are explained. The techniques used in the development of program for automatic recognition of emotions in photographs of human faces are deep learning and neural networks using the method of transfer learning. In the practical part of the thesis, all acquired knowledge from the theoretical part is applied. The first step is to prepare a database of photos for entering the neural network. After creating a neural network model consisting of several complex layers, the key steps of network training and validation take place. Validation of neutral network is shown through the confusion matrix.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:783004
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-10-03 07:21:26