Institutional Repository of Vilnius University
Skaitmeninių vaizdų suspaudimas pasitelkiant mokymosi pagrindu paremtus neuroninius tinklus /
Abstract
dc:descriptionThis work will examine the problem of the large volume of digital images and its solutions by employing standard digital image compression methods and formats, as well as neural networks based on machine learning. Standard digital image compression methods, formats, and machine learning based neural networks will be analyzed to assess their efficiency in terms of PSNR and MSSSIM metrics. Finally, a Generative Adversarial Network model will be developed, modified, analyzed, and evaluated with the aim of creating a more efficient neural network for digital image compression.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Pranskus, Gediminas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD210647843&prefLang=en_US