20.500.12556/DKUM-92497 Mobilna aplikacija za pretvorbo slik iz formata raw v format png s pomočjo strojnega učenja diplomsko delo Conversion app for converting images from raw to png format with machine learning V diplomskem delu je prikazan razvoj aplikacije za pretvorbo slik formata RAW v format PNG, pri čemer uporabljamo dva pristopa. Prvi temelji na standardnih algoritmih za pretvorbo slik, drugi pa na strojnem učenju, kar pomeni, da je bil model naučen čim bolj natančno pretvarjati sliko iz enega formata v drugega. Ta aplikacija dobro služi fotografom, ki zajemajo slike v formatu RAW, saj jih lahko na svojem mobilnem telefonu pretvorijo kar na poti. Na koncu sta sledili primerjava in analiza rezultatov za ugotavljanje, kateri postopek prinaša boljše rezultate. Za učenje modela je bilo uporabljenih 16 različnih slik, algoritem pa je bil implementiran s pomočjo knjižnic. Pretvorba z algoritmom je poskrbela za kvalitetnejše slike, vendar je bila pretvorba z modelom včasih hitrejša. Pretvorjene slike so bile primerjane z metrikama PSNR in SSIM ter analizirane. The thesis presents the development of an application for converting images from RAW format to PNG format, using two different approaches. The first approach is based on standard image conversion algorithms, while the second relies on machine learning, meaning that a model was trained to convert images from one format to another as accurately as possible. This application is especially useful for photographers who capture images in RAW format, as it allows them to convert images on the go directly on their mobile phones. In the end, a comparison and analysis of the results were conducted to determine which method yields better results. A total of 16 different images were used to train the model, and the algorithm was implemented using libraries. The algorithm-based conversion produced higher quality images, although the model-based conversion was sometimes faster. The converted images were compared and analyzed using the PSNR and SSIM metrics. raw png slika pretvorba strojno učenje raw png image conversion machine learning true true false [U. Mravljak] Slovenski jezik Angleški jezik Diplomsko delo/naloga 2025-04-14 07:38:13 2025-05-08 14:12:55 2025-05-22 03:11:12 0000-00-00 00:00:00 2025 0 Maribor 0 Maribor 1 spletni vir (1 datoteka PDF (IX, 34 str.)) 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.777:004.932(043.2) 236599043 VS_Mravljak_Uros_2025.pdf VS_Mravljak_Uros_2025.pdf 1 DFED0F0D82640F763AB86BB750BF0B86 28566ea058e6d9103c2456f59d174d53401d62654b8880657695c68fc8083595 4b000b62-1a04-11f0-abed-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=190319 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0