Study of Image Super Resolution Algorithms

dc.contributor.author	 Bouraba Nour El Houda  Rouabeh Lamia
dc.date.accessioned	2022-11-22T09:35:17Z
dc.date.available	2022-11-22T09:35:17Z
dc.date.issued	2022-09-22
dc.identifier.uri	https://dspace.univ-bba.dz:443/xmlui/handle/123456789/2740
dc.description.abstract	Super image resolution (SR) is a group of image processing technologies used in computer vision to improuve the resolution of deteriored images. Deep learning approaches have made great progress in super image resolution in recent years. In this study, we to provide a regular overview of current improuvments in image super resolution techniques using deep learning methodologies. Namely, we will describe and implement three SR algorithms : SRCNN, SRGAN and CAR. The comparative srudy is done in terms of the computation of two critera peak signal to noise ratio (PSNR) and the structure similarity index (SSIM). The obtained results have demonstrate the efficiency of the three amgorithms especialy CAR algorithm	en_US
dc.language.iso	fr	en_US
dc.publisher	faculté des sciences et de la technologie univ bba	en_US
dc.relation.ispartofseries	;EL/M/2022/65
dc.title	Study of Image Super Resolution Algorithms	en_US
dc.type	Thesis	en_US