Full Reference Light Field Image Quality Evaluation Based on Angular-Spatial Characteristic

Meng, Chunli; An, Ping; Yang, Chao; Liu, Deyang

doi:10.1109/lsp.2020.2982060

Cited by 35 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-view FR IQA metrics include morphological pyramids PSNR (MP-PSNR) (Sandić-Stanković et al, 2015 ), morphological wavelets PSNR (MW-PSNR) (Sandić-Stanković et al, 2015 ), MW-PSNRreduc (Sandić-Stanković et al, 2015 ), and 3DSwIM (Battisti et al, 2015 ). LFI FR IQA metrics include the algorithms in Min et al ( 2020 ) and Meng et al ( 2020 ). LFI NR IQA metrics include BELIF (Shi et al, 2019 ), Tensor-NLFQ (Zhou et al, 2020 ), and VBLIF (Xiang et al, 2020 ).…”

Section: Resultsmentioning

confidence: 99%

“…Meng et al ( 2019 ) used some camera parameters provided by the EPFL database (Honauer et al, 2016 ) when calculating the optimal parallax range, while some databases do not have these parameters. Therefore, in combination with the experiments of refocusing factors in section 4.7, we set the focusing range of Meng et al ( 2020 ) as [−3, 3] over all databases for the sake of fairness. Min et al ( 2020 ) computed the quality of LF images through the global–local spatial quality and the angular consistency measurement.…”

Section: Resultsmentioning

confidence: 99%

“…It is necessary to note that the angular resolution of all databases is set as 9 × 9 in the comparison experiment for fairness. Therefore, the performance of both Meng et al (2020) and Min et al (2020) presented in Tables 2, 3 is not optimal.…”

Section: Performance Analysis Of Image Quality Metricsmentioning

confidence: 99%

See 2 more Smart Citations

Image Quality Evaluation of Light Field Image Based on Macro-Pixels and Focus Stack

Meng

Yang

et al. 2022

Front. Comput. Neurosci.

Self Cite

View full text Add to dashboard Cite

Due to the complex angular-spatial structure, light field (LF) image processing faces more opportunities and challenges than ordinary image processing. The angular-spatial structure loss of LF images can be reflected from their various representations. The angular and spatial information penetrate each other, so it is necessary to extract appropriate features to analyze the angular-spatial structure loss of distorted LF images. In this paper, a LF image quality evaluation model, namely MPFS, is proposed based on the prediction of global angular-spatial distortion of macro-pixels and the evaluation of local angular-spatial quality of the focus stack. Specifically, the angular distortion of the LF image is first evaluated through the luminance and chrominance of macro-pixels. Then, we use the saliency of spatial texture structure to pool an array of predicted values of angular distortion to obtain the predicted value of global distortion. Secondly, the local angular-spatial quality of the LF image is analyzed through the principal components of the focus stack. The focalizing structure damage caused by the angular-spatial distortion is calculated using the features of corner and texture structures. Finally, the global and local angular-spatial quality evaluation models are combined to realize the evaluation of the overall quality of the LF image. Extensive comparative experiments show that the proposed method has high efficiency and precision.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Image Quality Evaluation of Light Field Image Based on Macro-Pixels and Focus Stack

Meng

Yang

et al. 2022

Front. Comput. Neurosci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Compared with traditional imaging that can only obtain the intensity information of a single image plane, light field imaging can not only obtain the three-dimensional image information and shape of the target, but also capture the deep original target information, reflecting the mutual occlusion relationship of the objects in the space. Spectral characteristics, but different from the traditional imaging "what you see is what you get" imaging form, light field imaging is a computational imaging technology that requires a series of digital processing algorithms to obtain [7][8].…”

Section: Light Field Imaging Technology (1) Light Field Imagingmentioning

confidence: 99%

Retina 3D Perception Reconstruction Algorithm Based on Visual Light Field Image

Jiang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

As an important part of the eye, the retina is very important to the human body. At present, the diagnosis and treatment of patients with retinal damage or detached blindness in clinical medicine rely on medical imaging technology and ophthalmological equipment. However, the three-dimensional image of the retina constructed by the existing imaging equipment has major defects, which is not conducive to the medical staff's treatment of the lesion, careful observation and precise judgment. Therefore, this paper proposes a three-dimensional perceptual reconstruction of the retina based on visual light field images. Computer vision lighting technology is used to create four-dimensional spaces for retinal images, and to enable this, four-dimensional light data is connected to the three-dimensional retinal reconstruction. The resulting retinal image not only contains three-dimensional information, but also has four-dimensional optical shapes, providing physicians with well-thought-out and accurate images for diagnosing and treating diseases. This article first collected a large amount of data through the literature survey method, introduced in detail the related theories and algorithm processes of computer vision, light field imaging technology and 3D reconstruction technology, laying a sufficient theoretical foundation for the 3D perception reconstruction of the retina. Combining the light field imaging technology with 3D reconstruction technology, a 3D reconstruction based on visual light field images is proposed, taking 10 retinal images from the ophthalmology department of the Provincial Hospital as an example, the 3D perception of the retina based on visual light field images is carried out. Finally, a comprehensive comparison and analysis of several algorithms in the process of retina 3D perception reconstruction found that the logarithmic transformation method is better than the histogram equalization method in the enhanced image contrast algorithm; compared with the traditional median filter denoising algorithm, the adaptive weighted median filter denoising method proposed in this paper has better effect; in the retinal image registration algorithm, the Powell algorithm handles the details of the image more in place, preserves the edge of the image intact, and the image quality is better; and the inter-layer interpolation algorithm. In this paper, the image obtained by the adaptive optimization interpolation algorithm proposed is better than the image obtained by the nearest neighbor interpolation and linear interpolation algorithm.

show abstract

“…Some existing objective quality assessment studies include deblocking images, screen content images, multiple distorted images, and noisy images, etc. ( Gao et al, 2008 ; Min et al, 2019 ; Liu et al, 2020 ; Meng et al, 2020 ). For instance, in early work, Wang et al (2004) developed structural similarity (SSIM) index based on the subjective perception of image structure information, which achieved a breakthrough in the objective evaluation of image quality.…”

Section: Introductionmentioning

confidence: 99%

Medical image fusion quality assessment based on conditional generative adversarial network

et al. 2022

View full text Add to dashboard Cite

Multimodal medical image fusion (MMIF) has been proven to effectively improve the efficiency of disease diagnosis and treatment. However, few works have explored dedicated evaluation methods for MMIF. This paper proposes a novel quality assessment method for MMIF based on the conditional generative adversarial networks. First, with the mean opinion scores (MOS) as the guiding condition, the feature information of the two source images is extracted separately through the dual channel encoder-decoder. The features of different levels in the encoder-decoder are hierarchically input into the self-attention feature block, which is a fusion strategy for self-identifying favorable features. Then, the discriminator is used to improve the fusion objective of the generator. Finally, we calculate the structural similarity index between the fake image and the true image, and the MOS corresponding to the maximum result will be used as the final assessment result of the fused image quality. Based on the established MMIF database, the proposed method achieves the state-of-the-art performance among the comparison methods, with excellent agreement with subjective evaluations, indicating that the method is effective in the quality assessment of medical fusion images.

show abstract

Full Reference Light Field Image Quality Evaluation Based on Angular-Spatial Characteristic

Cited by 35 publications

References 26 publications

Image Quality Evaluation of Light Field Image Based on Macro-Pixels and Focus Stack

Image Quality Evaluation of Light Field Image Based on Macro-Pixels and Focus Stack

Retina 3D Perception Reconstruction Algorithm Based on Visual Light Field Image

Medical image fusion quality assessment based on conditional generative adversarial network

Contact Info

Product

Resources

About