Journal
DISPLAYS
Volume 74, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.displa.2022.102188
Keywords
Multi-exposure fusion; Image quality assessment; Local reference information; Global reference information
Categories
Funding
- Zhejiang Natural ScienceFoundation [LR22F020002]
- Natural Science Foundation of China [61901236]
- Natural Science Foundation of Ningbo [202003N4155]
- Fundamental Research Funds for the Provincial Universities of Zhejiang [SJLZ2020003]
Ask authors/readers for more resources
This paper proposes a novel full-reference image quality assessment method for multi-exposure fusion (MEF) images by generating local and global intermediate references. Experimental results show that the proposed method achieves higher consistency with subjective quality scores compared to existing relevant methods.
Multi-exposure fusion (MEF) takes a sequence of images with different exposure levels as input and generates a fused image that is more informative and perceptually appealing than any of the input images as output. During the past decades, many MEF algorithms have been proposed. Therefore, how to effectively compare the per-formance of different MEF algorithms is of great significance. Despite of this, research efforts on objective image quality assessment (IQA) of MEF images remain limited. In this paper, we propose a novel full-reference (FR) IQA method for MEF images by generating Local and Global Intermediate References (LGIR) from the input multiple images. Specifically, the intermediate reference features are synthesized in gradient domain, structural tensor domain, and global perception domain, respectively. The gradient and structure tensor domains reflect the local structural perception of the human visual system (HVS), while the global perception domain integrately con-siders the overall perception. In each domain, a single quality measure is estimated to reflect the visual quality of the fused image from a specific perspective. In addition, on considering the multi-scale property of the HVS, we estimate those quality measures at multiple scales, and fuse them together to predict the final quality score. Experimental results demonstrate the superiority of LGIR, achieving higher consistency with subjective quality scores than existing relevant FR-IQA methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
Article
Computer Science, Hardware & Architecture
A comprehensive system for 3D display: From image capture to autostereoscopic playback
Chen Wen, Zhang Di, Ma Jingjing, Wu Guowen
Summary: This article presents a comprehensive array of remedies for the challenges in acquiring, processing, and displaying 3D content. It proposes a strategic framework divided into three key modules and introduces two novel convolutional neural networks for depth map and virtual viewpoint image generation and optimization. The results demonstrate the efficacy of the proposed system in improving the efficiency of 3D content production while reducing costs.
DISPLAYS (2024)
Article
Computer Science, Hardware & Architecture
Crop type recognition of VGI road-side images via hierarchy structure based on semantic segmentation model Deeplabv3+
YingHong Tian, Kun Zhang, Xingbo Hu, Yue Lu
Summary: The application of artificial intelligence in agricultural crop type recognition is important. This study proposes a hierarchical semantic segmentation structure based on Deeplabv3+ to recognize crop types. By combining remote sensing and volunteered geographic information, the model achieves fine recognition of crops in multiple stages. Experimental results show that this method performs well in crop type recognition for VGI images.
DISPLAYS (2024)
Article
Computer Science, Hardware & Architecture
Designing the color of electric motorcycle products emotionally based on the dynamic field theory and deep learning
Man Ding, Haocheng Qin, Xinxin Zhang, Liwen Ma
Summary: This paper proposes a novel method for Product Color Emotional Design (PCED) by integrating dynamic field theory with deep learning. The method establishes a system capable of generating color design schemes that align with users' emotional needs based solely on user feature labels.
DISPLAYS (2024)
Article
Computer Science, Hardware & Architecture
Consent notices are obstructing my view: Viewing sticky elements on responsive websites under the magnifying glass
Frode Eika Sandnes
Summary: This study explores the implications of consent notices on websites for low vision users who rely on browser magnification. The study finds that a significant number of websites have blocking consent notices and permanent elements that obstruct screen real estate when magnified. The study also provides recommendations for improving accessibility for users relying on magnification in narrow viewports.
DISPLAYS (2024)
Article
Computer Science, Hardware & Architecture
A high-haze liquid crystal grating device with asymmetric anchoring energies
Chan-Hee Han, Seung-Won Oh
Summary: This study presents the development of a new two-dimensional liquid crystal grating device with asymmetric surface anchoring. By using a waffle-shaped electrode on one substrate, a two-dimensional electric field is generated. The introduction of weak anchoring energy on one of the substrates allows for easier rotation of liquid crystal molecules between the electrodes upon voltage application in an asymmetrically anchored device. As a result, the proposed grating device exhibits a significant spatial phase difference in any direction, resulting in a high haze value in the opaque state.
DISPLAYS (2024)