On Methods of Estimation of Image  Aesthethic

dc.contributor.author	Kostyshyn, Iryna
dc.date.accessioned	2024-02-15T09:33:50Z
dc.date.available	2024-02-15T09:33:50Z
dc.date.issued	2020
dc.identifier.citation	Kostyshyn, Iryna. On Methods of Estimation of Image Aesthethic / Kostyshyn, Iryna; Supervisor: Oles Dobosevych; Ukrainian Catholic University, Department of Computer Sciences. – Lviv: 2020. – 33 p.	uk
dc.identifier.uri	https://er.ucu.edu.ua/handle/1/4517
dc.language.iso	en	uk
dc.title	On Methods of Estimation of Image Aesthethic	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	Evaluation of image aesthetics has been a longstanding problem in image processing and computer vision. Nowadays this topic is discussed more than ever, researchers attempt not only to measure the aesthetic quality of images but also to find new ap- plications of this methods. In this work, we research image assessment methods, their pitfalls. We try to propose new assessment methods for these tasks using acti- vation maps and explore the possibility of using such neural networks for training Image Restoration GANs. This work also incorporates the study of the relevance of existing methods on the example of their work on data not specially prepared for this specific task.	uk