20.500.12556/RUL-129625 Optična razpoznava notnih znakov Optical music notations recognition V diplomskem delu sta predstavljena dva pristopa optičnega razpoznavanja notnih znakov: tradicionalni, pri katerem se problem rešuje po strategiji "deli in vladaj", ter novejši, holistični pristop, pri katerem se problem rešuje z globoko nevronsko mrežo. Oba sta podrobneje opisana in primerjana, predstavljeni pa sta tudi njuni implementaciji, optimizaciji ter doseženi rezultati. Opisani sta zbirki notnih incipitov PrIMuS in CorPus, s katerima sta bila modela ocenjena. Predstavljena sta tudi dva različna obstoječa sistema iz tega področja (plačljivi ter odprtokodni). Na koncu so primerjani še rezultati modelov, nastalih v sklopu diplomskega dela, ter rezultati obstoječih sistemov. Najboljše rezultate je dosegla metoda z globoko nevronsko mrežo, optimizirana tradicionalna metoda pa bi bila uporabna pri natančno definirani ali pa omejeni problematiki. The thesis presents two approaches to optical music recognition: the traditional one, in which the problem is solved by the strategy of "divide and rule", and the newer, holistic approach, in which the problem is solved with a deep neural network. Both are described and compared in more detail, and their implementation, optimization and achieved results are also presented. The collections of music incipits PrIMuS and CorPus, with which the models were evaluated, are described. Two different accommodation systems in this field (paid and open source) are also presented. Finally, the results of the models created as part of the diploma thesis and the results of existing systems are compared. The best results were achieved by the method with a deep neural network, while the optimized traditional method could be used with precisely defined or limited problem. Optična razpoznava notnih znakov računalniški vid predprocesiranje slike CRNN Optical music recognition computer vision image pre-processing CRNN true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2021-09-06 10:00:01 2021-09-06 10:00:05 2022-09-08 04:09:40 0000-00-00 00:00:00 2021 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 31102 75930371 Isovski_Matic_-_Opticna_razpoznava_notnih_znakov.pdf Isovski_Matic_-_Opticna_razpoznava_notnih_znakov.pdf 1 9C155D8F8942372E621310C4AD772FA7 8bbd269bc16a8d0f3812ce331977addf726cf40a072d9b14442b9a6f5c385909 34b0c3d0-0ee8-11ec-a523-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=146637 Fakulteta za računalništvo in informatiko 0 0 0