prikaz prve stranice dokumenta Korištenje strojnog učenja za razlikovanje pasa i mačaka na slikama
Access restricted to students and staff of home institution
undergraduate thesis
Korištenje strojnog učenja za razlikovanje pasa i mačaka na slikama
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. urn:nbn:hr:179:275658
Madunić, Iva
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

Madunić, I. (2021). Korištenje strojnog učenja za razlikovanje pasa i mačaka na slikama (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:275658

Madunić, Iva. "Korištenje strojnog učenja za razlikovanje pasa i mačaka na slikama." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:275658

Madunić, Iva. "Korištenje strojnog učenja za razlikovanje pasa i mačaka na slikama." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:275658

Madunić, I. (2021). 'Korištenje strojnog učenja za razlikovanje pasa i mačaka na slikama', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 21 June 2024, https://urn.nsk.hr/urn:nbn:hr:179:275658

Madunić I. Korištenje strojnog učenja za razlikovanje pasa i mačaka na slikama [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2024 June 21] Available at: https://urn.nsk.hr/urn:nbn:hr:179:275658

I. Madunić, "Korištenje strojnog učenja za razlikovanje pasa i mačaka na slikama", Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:275658

Metadata
TitleKorištenje strojnog učenja za razlikovanje pasa i mačaka na slikama
Title (english)Using machine learning to distinguish dogs and cats in pictures
AuthorIva Madunić
MentorLinda Vicković (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-07-21, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U okviru ovog završnog rada opisani su osnovni koncepti umjetnih neuronskih mreža, jednog od pristupa strojnog učenja. Analizirane su konvolucijske neuronske mreže, posebna klasa neuronskih mreža korištena za klasifikaciju slika. Prikazana je priprema ulaznih podataka korištenih za treniranje, validaciju i testiranje. Razvijen je model mreže čiji je zadatak sortirati slike pasa i mačaka u odgovarajuće kategorije. Za izradu modela korišten je Python programski jezik, Tensorflow platforma za strojno učenje i Keras aplikacijsko programsko sučelje. Pomoću Flask radnog okvira (engl. framework) napravljena je web aplikacija koja korisnicima omogućuje unos slika koje će mreža klasificirati.
Abstract (english)
This undergraduate thesis describes basic concepts of neural networks, one of the approaches used in machine learning. Furthermore, convolutional neural networks, special class of neural networks used for image classification, are analysed. This work also shows preparation of input data used for training, validation and testing. Created model of network is used to sort images of cats and dogs in appropriate categories. Python programming language, Tensorflow machine learning platform and Keras application program interface were used to develop the model. Web application, which enables users to input images which will be used for neural network predictions, was made with Flask framework.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:275658
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2021-12-07 12:52:49