prikaz prve stranice dokumenta Aplikacija za automatsko rješavanje sudokua
Access restricted to authenticated users
master's thesis
Aplikacija za automatsko rješavanje sudokua
2021. urn:nbn:hr:179:036917
Vujasin, Ela
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Linked objects
Aplikacija za automatsko rješavanje sudokua | Appendix
Cite this document

Vujasin, E. (2021). Aplikacija za automatsko rješavanje sudokua (Master's thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:036917

Vujasin, Ela. "Aplikacija za automatsko rješavanje sudokua." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:036917

Vujasin, Ela. "Aplikacija za automatsko rješavanje sudokua." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:036917

Vujasin, E. (2021). 'Aplikacija za automatsko rješavanje sudokua', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 15 March 2023, https://urn.nsk.hr/urn:nbn:hr:179:036917

Vujasin E. Aplikacija za automatsko rješavanje sudokua [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2023 March 15] Available at: https://urn.nsk.hr/urn:nbn:hr:179:036917

E. Vujasin, "Aplikacija za automatsko rješavanje sudokua", 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:179:036917

Please login to the repository to save this object to your list.
Metadata
TitleAplikacija za automatsko rješavanje sudokua
Title (english)Automatic sudoku solver application
AuthorEla Vujasin
MentorMarin Bugarić (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-07-14, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu opisana je aplikacija za rješavanje Sudokua u stvarnom vremenu. Obrađen je SIFT algoritam koji se koristi kako bi zaključili je li na slici Sudoku ili ne. Također su objašnjene metode iz OpenCV biblioteke koje se koriste kako bi pronašli sudoku ploču. Iz pronađene Sudoku ploče „izvuku“ se sve ćelije. Svaka od ćelija koja u sebi sadrži broj se šalje kao ulaz konvolucijskoj neuronskoj mreži (CNN) koja klasificira ulaznu sliku u jednu od 9 klasa. Obrađena su i uspoređena tri algoritma za rješavanje Sudokua: backtracking algoritam, Constraint Propagation algoritam i genetski algoritam
Abstract (english)
This thesis presents a real time Sudoku-solver application. SIFT algorithm which is used to determine whether Sudoku board is present on image or not is described. Methods from OpenCV library that are used to find Sudoku board are explained. Once the board is found, individual cells are extracted. The cells are then passed to a convolution neural network (CNN) that is used to classify input to one of 9 classes. Three algorithms for solving Sudoku are described and compared: Backtracking algorithm, Constraint Propagation algorithm and genetic algorithm.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:036917
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 on2021-11-26 11:40:17