Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hua-Wen Chang, Ya-Chong Lu, Rui-Jie Sha, Hua Yang
Format: Artículo Open Access
Publié: Wiley 2026
Sujets:
Accès en ligne:https://onlinelibrary.wiley.com/doi/10.1155/ijdm/3539519
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1867021264616423424
author Hua-Wen Chang
Ya-Chong Lu
Rui-Jie Sha
Hua Yang
author_facet Hua-Wen Chang
Ya-Chong Lu
Rui-Jie Sha
Hua Yang
Hua-Wen Chang
Ya-Chong Lu
Rui-Jie Sha
Hua Yang
collection Wiley Open Access
contents Blind Image Quality Assessment Using Visual Neuron Model and Visual Attention Mechanism Hua-Wen Chang Ya-Chong Lu Rui-Jie Sha Hua Yang International Journal of Digital Multimedia Broadcasting In this paper, a blind image quality assessment (BIQA) method is proposed, which leverages both a visual neuron model and visual attention mechanism. The research of BIQA is aimed at evaluating the perceptual quality of images without access to reference images. In order to make the quality scores of the BIQA methods more in line with the visual perception, modeling the human visual system (HVS) is an effective approach. The neurons in the visual cortex are the key components of the HVS, and their response characteristics can be described by scene statistics models. Therefore, we design a visual neuron model to simulate cortical responses. This model is implemented using kernel principal component analysis (KPCA) to simulate the complexity of neural responses, thereby enabling the extraction of perceptually relevant statistical features. The attention mechanism of the HVS allows it to focus on the most salient regions of an image. The visual attention network (VAN), utilizing large‐kernel convolutions, effectively captures long‐range dependencies and global information within an image, making it suitable for extracting attention features. The extracted statistical and attention features are then fused and input into a regression network to predict the image quality score. Experimental results on multiple benchmark datasets demonstrate that the proposed method outperforms state‐of‐the‐art IQA models. 10.1155/ijdm/3539519 https://creativecommons.org/licenses/by/4.0/
doi_str_mv 10.1155/ijdm/3539519
format Artículo Open Access
id wiley_oa_10_1155_ijdm_3539519
institution Wiley Open Access
license_str_mv https://creativecommons.org/licenses/by/4.0/
publishDate 2026
publisher Wiley
record_format wiley_oa
spellingShingle Blind Image Quality Assessment Using Visual Neuron Model and Visual Attention Mechanism
Hua-Wen Chang
Ya-Chong Lu
Rui-Jie Sha
Hua Yang
International Journal of Digital Multimedia Broadcasting
Blind Image Quality Assessment Using Visual Neuron Model and Visual Attention Mechanism Hua-Wen Chang Ya-Chong Lu Rui-Jie Sha Hua Yang International Journal of Digital Multimedia Broadcasting In this paper, a blind image quality assessment (BIQA) method is proposed, which leverages both a visual neuron model and visual attention mechanism. The research of BIQA is aimed at evaluating the perceptual quality of images without access to reference images. In order to make the quality scores of the BIQA methods more in line with the visual perception, modeling the human visual system (HVS) is an effective approach. The neurons in the visual cortex are the key components of the HVS, and their response characteristics can be described by scene statistics models. Therefore, we design a visual neuron model to simulate cortical responses. This model is implemented using kernel principal component analysis (KPCA) to simulate the complexity of neural responses, thereby enabling the extraction of perceptually relevant statistical features. The attention mechanism of the HVS allows it to focus on the most salient regions of an image. The visual attention network (VAN), utilizing large‐kernel convolutions, effectively captures long‐range dependencies and global information within an image, making it suitable for extracting attention features. The extracted statistical and attention features are then fused and input into a regression network to predict the image quality score. Experimental results on multiple benchmark datasets demonstrate that the proposed method outperforms state‐of‐the‐art IQA models. 10.1155/ijdm/3539519 https://creativecommons.org/licenses/by/4.0/
title Blind Image Quality Assessment Using Visual Neuron Model and Visual Attention Mechanism
topic International Journal of Digital Multimedia Broadcasting
url https://onlinelibrary.wiley.com/doi/10.1155/ijdm/3539519