A combined full-reference image quality assessment approach based on convolutional activation maps

TL;DR

This paper introduces a novel combined full-reference image quality assessment method using convolutional activation maps and machine learning, achieving superior performance on multiple benchmark datasets.

Contribution

The study proposes a new FR-IQA approach that leverages convolutional activation maps and traditional similarity metrics, demonstrating high accuracy with limited training data.

Findings

Outperforms state-of-the-art on six benchmark IQA datasets

Effective with limited training data

Combines deep features with traditional similarity metrics

Abstract

The goal of full-reference image quality assessment (FR-IQA) is to predict the quality of an image as perceived by human observers with using its pristine, reference counterpart. In this study, we explore a novel, combined approach which predicts the perceptual quality of a distorted image by compiling a feature vector from convolutional activation maps. More specifically, a reference-distorted image pair is run through a pretrained convolutional neural network and the activation maps are compared with a traditional image similarity metric. Subsequently, the resulted feature vector is mapped onto perceptual quality scores with the help of a trained support vector regressor. A detailed parameter study is also presented in which the design choices of the proposed method is reasoned. Furthermore, we study the relationship between the amount of training images and the prediction performance. Specifically, it is demonstrated that the proposed method can be trained with few amount of data to reach high prediction performance. Our best proposal - ActMapFeat - is compared to the state-of-the-art on six publicly available benchmark IQA databases, such as KADID-10k, TID2013, TID2008, MDID, CSIQ, and VCL-FER. Specifically, our method is able to significantly outperform the state-of-the-art on these benchmark databases.