Komprese obrázků pomocí autoencodéru

Autoencoder based image compression

Typ dokumentu
bakalářská práce
bachelor thesis
Autor
Gökay Baran Kaya
Vedoucí práce
Peichl Adam
Oponent práce
Cejnek Matouš
Studijní obor
Informační a automatizační technika
Studijní program
Strojírenství
Instituce přidělující hodnost
ústav přístrojové a řídící techniky


Práva
A university thesis is a work protected by the Copyright Act. Extracts, copies and transcripts of the thesis are allowed for personal use only and at one?s own expense. The use of thesis should be in compliance with the Copyright Act http://www.mkcr.cz/assets/autorske-pravo/01-3982006.pdf and the citation ethics http://knihovny.cvut.cz/vychova/vskp.html
Vysokoškolská závěrečná práce je dílo chráněné autorským zákonem. Je možné pořizovat z něj na své náklady a pro svoji osobní potřebu výpisy, opisy a rozmnoženiny. Jeho využití musí být v souladu s autorským zákonem http://www.mkcr.cz/assets/autorske-pravo/01-3982006.pdf a citační etikou http://knihovny.cvut.cz/vychova/vskp.html
Metadata
Zobrazit celý záznam
Abstrakt
This thesis presents a comparative analysis of conventional image compression techniques such as JPEG, WebP, and TIFF, against modern autoencoder-based compression methods. The main objective is to evaluate the performance and quality of autoencoders relative to established algorithms in image compression. Theoretical backgrounds of each compression technique were first explored to provide a better understanding of their principles. Subsequently, an empirical study was conducted where images were compressed using each method. The results were assessed based on image quality by using metrics such as PSNR and SSIM. Findings reveal that images compressed with autoencoders can achieve competitive metric results compared to conventional techniques. This study concludes that autoencoders offer potential for future compression applications.
 
This thesis presents a comparative analysis of conventional image compression techniques such as JPEG, WebP, and TIFF, against modern autoencoder-based compression methods. The main objective is to evaluate the performance and quality of autoencoders relative to established algorithms in image compression. Theoretical backgrounds of each compression technique were first explored to provide a better understanding of their principles. Subsequently, an empirical study was conducted where images were compressed using each method. The results were assessed based on image quality by using metrics such as PSNR and SSIM. Findings reveal that images compressed with autoencoders can achieve competitive metric results compared to conventional techniques. This study concludes that autoencoders offer potential for future compression applications.
 
URI
http://hdl.handle.net/10467/116059
Zobrazit/otevřít
Kolekce