Thesis Details
Mobilní aplikace pro naskenování hry Sudoku z novin a její dohrání
This bachelor thesis describes the creation of a mobile application, that scans sudoku layout from the newspaper and allows its solving. The application is developed for the Android and is implemented in Kotlin. Scanning is done by taking picture of layout with camera. Basic image processing methods such as thresholding or Canny's edge detector are used to detect the sudoku layout. Number recognition is provided by convolution neural network with 99.08 % accuracy. The application allows solving sudoku with hints. Elimination methods and backtracking are used to find solution. Each scanned sudoku is stored in the database so the user can always return to any game. The final version of the application is published in the Google Play store.
sudoku, mobile application, image processing, neural network, android, camerax, opencv, tensorflow, kotlin, backtracking, GUI
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Martínek Tomáš, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Matoušek Petr, doc. Ing., Ph.D., M.A. (DIFS FIT BUT), člen
@bachelorsthesis{FITBT23648, author = "Juraj Lazor\'{i}k", type = "Bachelor's thesis", title = "Mobiln\'{i} aplikace pro naskenov\'{a}n\'{i} hry Sudoku z novin a jej\'{i} dohr\'{a}n\'{i}", school = "Brno University of Technology, Faculty of Information Technology", year = 2021, location = "Brno, CZ", language = "slovak", url = "https://www.fit.vut.cz/study/thesis/23648/" }