APSIPA Transactions on Signal and Information Processing > Vol 13 > Issue 1

Lightweight High-Performance Blind Image Quality Assessment

Zhanxuan Mei, University of Southern California, USA, zhanxuan@usc.edu , Yun-Cheng Wang, University of Southern California, USA, C.-C. Jay Kuo, University of Southern California, USA
 
Suggested Citation
Zhanxuan Mei, Yun-Cheng Wang and C.-C. Jay Kuo (2024), "Lightweight High-Performance Blind Image Quality Assessment", APSIPA Transactions on Signal and Information Processing: Vol. 13: No. 1, e7. http://dx.doi.org/10.1561/116.00000179

Publication Date: 04 Apr 2024
© 2024 Z. Mei, Y-.C. Wang and C.-C. Jay Kuo
 
Subjects
Image and video processing,  Statistical/Machine learning
 
Keywords
Image quality assessmentBlind image quality assessmentGreen learning
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 132 times

In this article:
Introduction 
Related Work 
Proposed GreenBIQA Method 
Experiments 
Conclusion and Future Work 
References 

Abstract

Blind image quality assessment (BIQA) is a task that predicts the perceptual quality of an image without its reference. Research on BIQA attracts growing attention due to the increasing amount of user-generated images and emerging mobile applications where reference images are unavailable. The problem is challenging due to the wide range of content and mixed distortion types. Many existing BIQA methods use deep neural networks (DNNs) to achieve high performance. However, their large model sizes hinder their applicability to edge or mobile devices. To meet the need, a novel BIQA method with a small model, low computational complexity, and high performance is proposed and named “GreenBIQA” in this work. GreenBIQA includes five steps: 1) image cropping, 2) unsupervised representation generation, 3) supervised feature selection, 4) distortion-specific prediction, and 5) regression and decision ensemble. Experimental results show that the performance of GreenBIQA is comparable with that of state-of-the-art deep learning (DL) solutions while demanding a much smaller model size and significantly lower computational complexity.

DOI:10.1561/116.00000179