Sep 2026· Asia Conference onAsia Conference on Advances in Image Processing· Vol 14375, pp. 143750G - 143750G-9· 0 citations· 26 references
Engineering
TL;DR
This study proposes a full-reference image quality assessment (FR-IQA) algorithm, named LSCNN, which conforms to the “large perception, small aggregation” characteristic of the human visual system, and experimental results showed that its performance was superior to some existing FRIQA algorithms.
Abstract
This study proposes a full-reference image quality assessment (FR-IQA) algorithm, named LSCNN, which conforms to the “large perception, small aggregation” characteristic of the human visual system. The LSCNN algorithm extracts important features that conform to human subjective perception by replacing some convolutional layers of the convolutional neural network (CNN) with LSConv (Large-Small Convolution), and uses two layers of fully connected layers for regression prediction. LSConv can achieve global context capture and local feature fusion to optimize convolution efficiency, simulate the feature extraction process of the human visual system, and make the objective prediction of image quality evaluation results closer to the level of human subjective evaluation. The LSCNN algorithm was evaluated on the LIVE, TID2013, CSIQ, SCID and SIQAD datasets, and the experimental results showed that its performance was superior to some existing FRIQA algorithms.
A novel Hierarchical Multi-Scale Cross-Attention Network that effectively captures both local distortion patterns and global semantic information for quality prediction and exhibits superior generalization capability compared to existing approaches is proposed.
Jiakuo Yan, Jun Zeng· International Conference on...· 0 citations
This study has trained a deep Convolutional Neural Network (CNN) using labelled images and focuses on images that are naturally distorted during acquisition, processing, or transmission rather than on synthetically distorted images with discrete distortion levels.
Nisar Ahmed, M. Younus, Kalsoom Safdar· International Journal of Inn...· 0 citations
A full-reference image quality assessment (FR-IQA) is proposed in this work. First, images are transformed into wavelet subbands and color histograms to maintain key visual characteristics of the human visual system (HVS). Second, subtle degradations are amplified via collaborative refinement. Afterward, the Hausdorff...
Xue-Kai Wei, Junyu Zhang, Qin-Lin Hu et al.· ACM Transactions on Multimed...· 0 citations
A Swin Transformer-based NR-IQA method comprising three core modules, which improves Spearman Rank-Order Correlation Coefficient and Pearson Linear Correlation Coefficient over the best-performing comparison method, validating its effectiveness for no-reference image quality prediction.
Xiao-Meng Xia, Jia Yong, Yi-Biao Long et al.· PeerJ Computer Science· 0 citations
A CNN-based edge-aware artifact reduction framework (CNN-AR) is proposed that integrates an enhanced deep super-resolution (EDSR) backbone with a holistically nested edge detection (HED) guided loss, enabling superior artifact suppression while preserving fine structural details.
Nupur, Nishant Kumar, Sajal Suhane et al.· International Journal of Onl...· 0 citations
Results indicate that the proposed method more closely approximates subjective perception, providing reliable support for visual enhancement, intelligent compression, and perceptual coding.