What question did this study set out to answer?

This research aims to predict image quality score distributions rather than relying solely on Mean Opinion Scores.

April 29, 2026Journal of Visual Communication and Image Representation0 citationsOpen Access

Predicting image quality score distribution using deep neural networks

NPNikola PlavacNorwegian University of Science and Technology SASeyed Ali AmirshahiAmirkabir University of Technology MPMarius PedersenNorwegian University of Science and Technology

Key Points

This research aims to predict image quality score distributions rather than relying solely on Mean Opinion Scores.
Developed Image Quality Distribution Network (IQDN) with various architectures including transfer learning models.
Trained models on datasets: KonIQ-10k, CID2013, and NAP540 to predict quality score histograms.
Evaluated performance using distribution similarity metrics and point-wise error analysis.
IQDN with transfer learning improved accuracy in predicting quality distributions.
Models effectively reconstructed Mean Opinion Scores correlating with ground truth values.
Kullback–Leibler divergence enhanced performance across different datasets.

Abstract

Blind objective image quality assessment methods typically predict a single Mean Opinion Score (MOS) to represent perceived image quality. However, MOS discards valuable information about observer variability, as different score distributions can produce the same mean value. Predicting the full quality score distribution provides a richer and more realistic representation of perceptual quality. In this work, we propose an Image Quality Distribution Network (IQDN) in five configurations: a custom convolutional neural network trained from scratch and four transfer learning variants based on ResNet50, VGG16, Xception, and DenseNet121 backbones. The models were trained to predict five-bin normalized quality score histograms on three datasets: KonIQ-10k, CID2013, and a newly introduced NAP540 dataset. Performance was evaluated using multiple point-wise error and distribution similarity metrics. Results show that the Image Quality Distribution Network with Xception backbone consistently performs better than existing state-of-the-art approaches in terms of Earth Mover’s Distance, capturing score distributions more effectively. Furthermore, a hybrid loss function combining Kullback–Leibler (KL) divergence and Huber loss improved performance across datasets. The predicted distributions also reconstruct MOS that closely correlate with ground-truth MOS. Finally, incorporating a quality-aware backbone demonstrates strong potential, particularly in cross-dataset testing scenarios. • Introduce the Image Quality Distribution Network (IQDN), a blind image quality assessment framework designed to predict full quality score distributions rather than single Mean Opinion Score (MOS) values. • Present a systematic evaluation of IQDN architectures on multiple image quality datasets, using a diverse set of distributional and point-wise error metrics. • Analyze the impact of different architectural configurations on the prediction performance, as well as cross-dataset generalization. • The proposed networks showed very good performance, both in predicting the distribution shape and in the Mean Opinion Score (MOS).

AI से पूछें

Bookmark

View Full Paper