diplomsko delo
Ema Črne (Author), Luka Čehovin (Mentor)

Abstract

Pri združevanju slik se večina pristopov osredotoča na izboljšanje mask, ki ločujejo ospredje od ozadja. Kot alternativo zahtevni in počasni metodi finega izboljševanja mask smo si v nalogi zastavili cilj doseči podobne rezultate samo z uporabo približnih mask in globokega učenja. Približne maske za učenje modela smo izpeljali iz podanih natančnih mask, ki smo jih sami deformirali. V okviru naloge smo preučili vplive različnih parametrov in za končni model izbrali tiste, ki so se izkazali za najuspešnejše. Končni model smo nato preizkusili tudi z raznovrstnimi maskami pridobljenimi z drugimi metodam za določanje mask. Model kljub svoji majhnosti in enostavnosti prikaže obetavne rezultate.

Keywords

združevanje slik;konvolucijske nevronske mreže;samokodirniki;interdisciplinarni študij;univerzitetni študij;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [E. Črne]
UDC: 004.8(043.2)
COBISS: 168447747 Link will open in a new window
Views: 80
Downloads: 22
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Image compositing with non-accurate masks
Secondary abstract: In the field of image compositing most approaches focus on improving the precision of masks that distinguish between foreground and background. As an alternative to computationally intensive and time consuming image matting method, this research aims at achieving similar outcomes using only imprecise masks and the process of deep learning. These imprecise masks were created by deforming given exact masks. The work investigates the impact of different parameters and uses the combination of the most effective ones for the final model. The final model was then tested with a variety of masks obtained from other unrelated methods for foreground mask extraction. Despite its small size and simplicity, the model demonstrates promising results.
Secondary keywords: image compositing;convolutional neural networks;deep learning;autoencoders;computer science;computer and information science;computer science and mathematics;interdisciplinary studies;diploma;Globoko učenje (strojno učenje);Nevronske mreže (računalništvo);Računalništvo;
Type (COBISS): Bachelor thesis/paper
Study programme: 1000407
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 44 str.
ID: 19933624