Komprese obrázků pomocí autoencodéru

Abstract

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.