prikaz prve stranice dokumenta Klasifikacija slika prirodnog krajolika pomoću konvolucijskih neuralnih mreža
Access restricted to authenticated users
master's thesis
Klasifikacija slika prirodnog krajolika pomoću konvolucijskih neuralnih mreža
2021. urn:nbn:hr:179:776126
Oršulić, Antonela
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Oršulić, A. (2021). Klasifikacija slika prirodnog krajolika pomoću konvolucijskih neuralnih mreža (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:179:776126

Oršulić, Antonela. "Klasifikacija slika prirodnog krajolika pomoću konvolucijskih neuralnih mreža." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:776126

Oršulić, Antonela. "Klasifikacija slika prirodnog krajolika pomoću konvolucijskih neuralnih mreža." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:776126

Oršulić, A. (2021). 'Klasifikacija slika prirodnog krajolika pomoću konvolucijskih neuralnih mreža', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 25 April 2024, https://urn.nsk.hr/urn:nbn:hr:179:776126

Oršulić A. Klasifikacija slika prirodnog krajolika pomoću konvolucijskih neuralnih mreža [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2024 April 25] Available at: https://urn.nsk.hr/urn:nbn:hr:179:776126

A. Oršulić, "Klasifikacija slika prirodnog krajolika pomoću konvolucijskih neuralnih mreža", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:776126

Please login to the repository to save this object to your list.
Metadata
TitleKlasifikacija slika prirodnog krajolika pomoću konvolucijskih neuralnih mreža
Title (english)Classification of natural landscape images using convolutional neural networks
AuthorAntonela Oršulić
MentorMaja Braović (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-09-20, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu su opisane umjetne neuronske mreže, s naglaskom na konvolucijske neuronske mreže. Implementirana je konvolucijska neuronska mreža za semantičku klasifikaciju slika prirodnog krajolika u Keras radnoj okolini. Prilikom implementacije konvolucijske neuralne mreže koristilo se je prijenosno učenje. Na mreži su isprobane dvije baze podataka: Intel Image Classification i FESB MLID. Na kraju su baze opisane te su analizirani rezultati.
Abstract (english)
This thesis describes artificial neural networks, with an emphasis on convolutional neural networks. A convolutional neural network has been implemented for the semantic classification of the natural landscape in the Keras work environment. For the implementation of the convolutional neural network transfer learning was used. Two databases were tested on the neural network: Intel Image Classification i FESB MLID. Finally, the databases are described and the results are analyzed.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:776126
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 on2022-07-06 10:39:58