prikaz prve stranice dokumenta Mobilna Android aplikacija za prepoznavanje objekata primjenom postupaka strojnog učenja
  Download
PDF 1.58 MB
undergraduate thesis
Mobilna Android aplikacija za prepoznavanje objekata primjenom postupaka strojnog učenja
2019. urn:nbn:hr:200:231665
Rekić, Tomislav
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Programming Languages and Systems

Cite this document

Rekić, T. (2019). Mobilna Android aplikacija za prepoznavanje objekata primjenom postupaka strojnog učenja (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:231665

Rekić, Tomislav. "Mobilna Android aplikacija za prepoznavanje objekata primjenom postupaka strojnog učenja." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:231665

Rekić, Tomislav. "Mobilna Android aplikacija za prepoznavanje objekata primjenom postupaka strojnog učenja." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:231665

Rekić, T. (2019). 'Mobilna Android aplikacija za prepoznavanje objekata primjenom postupaka strojnog učenja', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 10 December 2024, https://urn.nsk.hr/urn:nbn:hr:200:231665

Rekić T. Mobilna Android aplikacija za prepoznavanje objekata primjenom postupaka strojnog učenja [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2019 [cited 2024 December 10] Available at: https://urn.nsk.hr/urn:nbn:hr:200:231665

T. Rekić, "Mobilna Android aplikacija za prepoznavanje objekata primjenom postupaka strojnog učenja", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:200:231665

Please login to the repository to save this object to your list.
Metadata
TitleMobilna Android aplikacija za prepoznavanje objekata primjenom postupaka strojnog učenja
Title (english)Mobile Android application for object recognition by using machine learning methods
AuthorTomislav Rekić
MentorGoran Martinović (mentor)
Committee memberGoran Martinović (predsjednik povjerenstva)
Committee memberZdravko Krpić (član povjerenstva)
Committee memberDean Vučinić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Programming Languages and Systems)
Osijek
Defense date and country2019-09-27, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Program Engineering
Abstract
Cilj ovoga rada je predložiti algoritam strojnog učenja pogodan za prepoznavanje slika životinja, izraditi primjenjiv model strojnog učenja, te ga ugraditi u mobilnu aplikaciju koja će na temelju snimljene slike omogućiti prepoznavanje životinja i ažuriranje postojeće ugrađene baze podataka životinja rezultatima klasifikacije. Dodatno, cilj rada je opisati popularne metode strojnog učenja, opisati neke od implementacija odabranog algoritma strojnog učenja, dati pregled značajki mobilne aplikacije i ispitati uspješnost odabranog algoritma strojnog učenja. Mobilna aplikacija je razvijena u razvojnom okruženju Android Studio i napisana u programskom jeziku Java, dok je algoritam strojnog učenja implementiran u razvojnom okruženju JupyterLab koristeći biblioteku TensorFlow i napisan u programskom jeziku Python. Baza podataka životinja uključena u mobilnu aplikaciju implementirana koristeći biblioteku SQLite, a opisi klase životinja dohvaćeni koristeći biblioteku Retrofit.
Abstract (english)
The goal of this thesis is to suggest a machine learning algorithm suitable for recognizing pictures of animals, create an applicable machine learning model and to embed it in the mobile application which will on the basis of a captured image allow recognition of animals and updating of an existing embedded database with the results of the classification. The thesis describes popular machine learning methods and some of the implementations of the chosen machine learning algorithm. Furthermore, the goal of this thesis is to describe the popular machine learning methods, describe some of the implementations of the chosen machine learning algorithm, give an insight into the characteristics of the mobile application and to test the success of the chosen machine learning algorithm. The mobile application is developed inside the Android Studio IDE and written in the Java programming language, while the machine learning algorithm is implemented in the JupyterLab IDE using the TensorFlow library and written in the Python programming language. The animal database included in the mobile application is implemented using the SQLite library and the descriptions of animal classes were retrieved using the Retrofit library.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:231665
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
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 conditionsOpen access
Terms of useLicence In copyright icon
Created on2019-12-20 15:46:57