Sökning: "Bildsuperupplösning"

Hittade 2 uppsatser innehållade ordet Bildsuperupplösning.

1. 1. En jämförelse av Deep Learning-modeller för Image Super-Resolution

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Rafael Bechara; Max Israelsson; [2023]
   Nyckelord :Bachelor’s thesis; Image Super-Resolution; Deep Learning models; EDSR; LapSRN; ESPCN; FSRCNN; resolution enhancement; low-resolution images; quantitative evaluation; RMSE; PSNR; SSIM; Abyssinian cats; dataset; image quality.; Kandidatexamensarbete; Image Super-Resolution; EDSR; LapSRN; ESPCN; FSRCNN; Djupinlärningsmodeller; upplösningsförbättring; lågupplösta bilder; kvantitativ utvärdering; RMSE; PSNR; SSIM; abyssinska katter; datamängd; bildkvalitet.;

   Sammanfattning : Image Super-Resolution (ISR) is a technology that aims to increase image resolution while preserving as much content and detail as possible. In this study, we evaluate four different Deep Learning models (EDSR, LapSRN, ESPCN, and FSRCNN) to determine their effectiveness in increasing the resolution of lowresolution images. LÄS MER

3. 2. High Resolution Quality Enhancement of Digitized Artwork using Generative Adversarial Networks

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Dennis Magnusson; [2022]
   Nyckelord :Image enhancement; Image style transfer; Image superresolution; Machine Learning; Bildförbättring; Bildstilöversättning; Bildsuperupplösning; Maskininlärning;

   Sammanfattning : Digitization of physical artwork is usually done using image scanning devices in order to ensure that the output is accurate in terms of color and is of sufficiently high resolution, usually over 300 pixels per inch, however the usage of such a device is in some cases unfeasible due to medium or size constraints. Photography of the artwork is another method of artwork digitization, however such methods often produce results containing camera artifacts such as shadows, reflections or low resolution. LÄS MER