Blind image quality assessment model via patch based learning framework

Alias, Amalina Ashila (2022) Blind image quality assessment model via patch based learning framework. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

	Text (24 Pages) Blind image quality assessment model via patch based learning framework.pdf - Submitted Version Download (410kB)
	Text (Full text) Blind image quality assessment model via patch based learning framework.pdf - Submitted Version Restricted to Repository staff only Download (1MB)

Abstract

The project focuses on an image quality assessment (IQA) model that estimates the quality of an image without the presence of reference information. Most well-known blind image quality assessment (BIQA) models usually follow a two-stage framework whereby various features are first extracted and then used as input to a regression algorithm. The regression algorithm models human perceptual measures based on a training set of distorted images. However, this approach requires an intensive training phase to optimise the regression parameters. This project attempts to overcome this limitation by proposing an alternative BIQA model that predicts image quality using nearest neighbour methods with virtually zero training cost. The project also proposes a learning framework that operates at the patch level. This enables the model to provide local image quality estimation, a property that can be useful for further local processing stages.

Actions (login required)

View Item