| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font
First page > Show document

Show document Help

Title:Kombiniranje več modelov razvrščanja vzorcev na primeru ocenjevanja starosti osebe iz digitalnih posnetkov : diplomsko delo
Authors:ID Horvat, Tadej (Author)
ID Potočnik, Božidar (Mentor) More about this mentor... New window
ID Šavc, Martin (Mentor) More about this mentor... New window
Files:.pdf UN_Horvat_Tadej_2023.pdf (1,75 MB)
MD5: 2DD54F565B17E3C0A5F10DDDC4175188
 
Language:Slovenian
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V tej diplomski nalogi se ukvarjamo s kombiniranjem različnih prosto dostopnih modelov konvolucijskih nevronskih mrež za reševanje problema ocenjevanja starosti oseb iz digitalnih posnetkov. Naš cilj je bil implementirati ansambelske metode, ki so bolj uspešne od vsakega posameznega modela v našem ansamblu. Kombinirali smo pet osnovnih modelov konvolucijskih nevronskih mrež, in sicer Xception, ResNet152V2, InceptionV3, InceptionResNetV2 in EfficientNetV2B0. Modele smo kombinirali na nivoju rezultatov in na nivoju značilnic, pri čemer smo implementirali štiri metode kombiniranja na nivoju rezultatov in pet metod kombiniranja na nivoju značilnic. Za učenje posameznih modelov in testiranje metod smo uporabili bazo podatkov UTKFace. Najboljši rezultat smo dosegli z metodo večslojnega »stackinga«, in sicer srednjo absolutno napako 4,526 let nad našo testno množico. Rezultat le malenkost zaostaja za rezultati najboljših sodobnih metod ocenjevanja starosti iz digitalnih posnetkov.
Keywords:ocenjevanje starosti oseb, konvolucijske nevronske mreže, ansambelsko učenje
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[T. Horvat]
Year of publishing:2023
Number of pages:1 spletni vir (1 datoteka PDF (VIII, 44 f.))
PID:20.500.12556/DKUM-85260 New window
UDC:004.8(043.2)
COBISS.SI-ID:170567171 New window
Publication date in DKUM:05.10.2023
Views:424
Downloads:30
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
HORVAT, Tadej, 2023, Kombiniranje več modelov razvrščanja vzorcev na primeru ocenjevanja starosti osebe iz digitalnih posnetkov : diplomsko delo [online]. Bachelor’s thesis. Maribor : T. Horvat. [Accessed 25 March 2025]. Retrieved from: https://dk.um.si/IzpisGradiva.php?lang=eng&id=85260
Copy citation
  
Average score:
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share


Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:23.08.2023

Secondary language

Language:English
Title:Combining multiple pattern classification models for person age estimation from digital images
Abstract:In this diploma thesis, we explore combining different free-to-use models of convolutional neural networks to solve the problem of person age estimation from digital images. Our goal was to implement ensemble methods that outperform each individual model in our ensemble. We combined 5 base models of convolutional neural networks: Xception, ResNet152V2, InceptionV3, InceptionResNetV2, and EfficientNetV2B0. We combined the models on the results and features level, implementing 4 result-level ensemble methods and 5 feature-level ensemble methods. We used the UTKFace dataset to train our individual models and test our methods. We achieved the best result using the multi-layer stacking method, with a mean absolute error of 4.526 years on our test set. Our result falls just short of the best modern age estimation methods from digital images.
Keywords:person age estimation, convolutional neural networks, ensemble learning


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica