A reference-free underwater image quality assessment metric in frequency domain

Yang, Ning; Zhong, Qihang; Li, Kun; Cong, Runmin; Zhao, Yao

doi:10.1016/j.image.2021.116218

Cited by 60 publications

(12 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluated the Spearman's rank correlation coefficient (SRCC) between the reconstructed subjective scores and objective scores of a few state-of-the-art objective IQA methods, including four full-reference (FR) IQA methods (i.e., PSNR, SSIM [16], VSI [19], SCQI [20]) and three no-reference (NR) underwater IQA methods, namely UIQM [21], UCIQE [22], and FDUM [23].…”

Section: Data Analysis and Resultsmentioning

confidence: 99%

Crowdsourced Quality Assessment of Enhanced Underwater Images - a Pilot Study

Men

Yan

Ren

et al. 2022

2022 14th International Conference on Quality of Multimedia Experience (QoMEX)

View full text Add to dashboard Cite

QoMEX) scale, we applied pair comparison to the enhanced images generated by 10 UIE algorithms in the 3D TURBID benchmark [3]. By reconstructing the quality scales from the pair comparison, we arrived at two results. (1) The existing IQA metrics are not suitable for assessing the perceived quality of enhanced underwater images. (2) The overall performance and ranking of 10 UIE algorithms on the benchmark.

show abstract

Section: Data Analysis and Resultsmentioning

confidence: 99%

Crowdsourced Quality Assessment of Enhanced Underwater Images - a Pilot Study

Men

Yan

Ren

et al. 2022

2022 14th International Conference on Quality of Multimedia Experience (QoMEX)

View full text Add to dashboard Cite

show abstract

“…content enhancement [35]- [46], and quality assessment [47], [48]. Chen et al [21] developed a method to make full use of global context.…”

Section: A Salient Object Detection In Single Image and Image Groupmentioning

confidence: 99%

PSNet: Parallel Symmetric Network for Video Salient Object Detection

Cong¹,

Song²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

For the video salient object detection (VSOD) task, how to excavate the information from the appearance modality and the motion modality has always been a topic of great concern. The two-stream structure, including an RGB appearance stream and an optical flow motion stream, has been widely used as a typical pipeline for VSOD tasks, but the existing methods usually only use motion features to unidirectionally guide appearance features or adaptively but blindly fuse two modality features. However, these methods underperform in diverse scenarios due to the uncomprehensive and unspecific learning schemes. In this paper, following a more secure modeling philosophy, we deeply investigate the importance of appearance modality and motion modality in a more comprehensive way and propose a VSOD network with up and down parallel symmetry, named PSNet. Two parallel branches with different dominant modalities are set to achieve complete video saliency decoding with the cooperation of the Gather Diffusion Reinforcement (GDR) module and Crossmodality Refinement and Complement (CRC) module. Finally, we use the Importance Perception Fusion (IPF) module to fuse the features from two parallel branches according to their different importance in different scenarios. Experiments on four dataset benchmarks demonstrate that our method achieves desirable and competitive performance. The code and results can be found from the link of https://rmcong.github.io/proj PSNet.html.

show abstract

“…However, these two metrics fail to take into account the perception characteristics of the HVS, so their evaluation results are not consistent with the human subjective judgments [14][15][16][17][18][19]. In the past two decades, many IQE models have been proposed by using the HVS properties, such as structural information, contrast [20], frequency [21], and gradient information [22]. Among the previously proposed image quality metrics (IQMs), the structural similarity (SSIM) is one of the most widely influential [6].…”

Section: Introductionmentioning

confidence: 98%

Image Quality Evaluation Based on Gradient, Visual Saliency, and Color Information

Chang

et al. 2022

International Journal of Digital Multimedia Broadcasting

View full text Add to dashboard Cite

This paper proposes an image quality evaluation (IQE) metric by considering gradient, visual saliency, and color information. Visual saliency and gradient information are two types of effective features for quality evaluation research. Different regions within an image are not uniformly important for IQE. Visual saliency can find the most attractive regions to the human visual system in a given image. These attractive image regions are more strongly correlated with image quality results. In addition, the degradation of gradient information is related to the structure distortion which is a very important factor for image quality. However, the two types of features cannot accurately evaluate the color distortion of images. In order to evaluate chromatic distortion, this paper proposes the color similarity which is measured in the YIQ color space. The computation of the proposed method begins with the similarity calculation of local gradient information, visual saliency, and color information. Then, the final quality score is obtained by the standard deviation on each similarity component. The experimental results on five benchmark databases (i.e., CSIQ, IVC, LIVE, TID2013, and TID2008) show that the proposed IQE method performs better than other methods in the correlation with subjective quality judgment.

show abstract

A reference-free underwater image quality assessment metric in frequency domain

Cited by 60 publications

References 36 publications

Crowdsourced Quality Assessment of Enhanced Underwater Images - a Pilot Study

Crowdsourced Quality Assessment of Enhanced Underwater Images - a Pilot Study

PSNet: Parallel Symmetric Network for Video Salient Object Detection

Image Quality Evaluation Based on Gradient, Visual Saliency, and Color Information

Contact Info

Product

Resources

About