A Novel Just-Noticeable-Difference-Based Saliency-Channel Attention Residual Network for Full-Reference Image Quality Predictions

Seo, Soomin; Ki, Sehwan; Kim, Munchurl

doi:10.1109/tcsvt.2020.3030895

Cited by 47 publications

(23 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each point on the scatter plots corresponds to one test image with JPEG compression. Scatter plots are shown for four image datasets, three of which are publicly available -LIVE (Sheikh et al, 2006) (with 29 original images), CSIQ (Larson & Chandler, 2010) (with 30 original images) and VCL@FER (Zarić et al, 2012) (with 23 reference images). The fourth image dataset, marked with LWIR, will be publicly available soon, and can be obtained by sending an inquiry to the authors who created it (Merrouche et al, 2018).…”

Section: Jnd Prediction and Image Quality Analysismentioning

confidence: 99%

“…One of the characteristics is related to the just noticeable difference (JND) threshold. JND, as a perceptual threshold in image processing, is used in perceptual image compression (Tian et al, 2020), (Wang et al, 2019), and can also be used in objective image quality assessment (Toprak & Yalman, 2017), (Seo et al, 2021). The first and most significant JND threshold/point refers to the transition between a pristine and an image with visible distortions, or rather the transition from perceptually lossless to perceptually lossy encoding (Huang et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Picture-wise just noticeable difference prediction model for JPEG image quality assessment

Bondžulić¹,

Pavlović²,

Stojanović³

et al. 2022

Vojnotehnički glasnik

View full text Add to dashboard Cite

Introduction/purpose: The paper presents interesting research related to the performance analysis of the picture-wise just noticeable difference (JND) prediction model and its application in the quality assessment of images with JPEG compression. Methods: The performance analysis of the JND model was conducted in an indirect way by using the publicly available results of subject-rated image datasets with the separation of images into two classes (above and below the threshold of visible differences). In the performance analysis of the JND prediction model and image quality assessment, five image datasets were used, four of which come from the visible wavelength range, and one dataset is intended for remote sensing and surveillance with images from the infrared part of the electromagnetic spectrum. Results: The pap 86 er shows that using a picture-wise JND model, subjective image quality assessment scores can be estimated with better accuracy, leading to significant performance improvements of the traditional peak signal-to-noise ratio (PSNR). The gain achieved by introducing the picture-wise JND model in the objective assessment depends on the chosen dataset and the results of the initial simple to compute PSNR measure, and it was obtained on all five datasets. The mean linear correlation coefficient (for five datasets) between subjective and PSNR objective quality estimates increased from 74% (traditional PSNR) to 90% (picture-wise JND PSNR). Conclusion: Further improvement of the JND-based objective measure can be obtained by improving the picture-wise model of JND prediction.

show abstract

Section: Jnd Prediction and Image Quality Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Picture-wise just noticeable difference prediction model for JPEG image quality assessment

Bondžulić¹,

Pavlović²,

Stojanović³

et al. 2022

Vojnotehnički glasnik

View full text Add to dashboard Cite

show abstract

“…In the literature [19] , the Squeeze-and-Excitation (SE) module [31][32] is introduced in MobileFaceNet. The structure is shown in Figure 9, and it can be seen from the experimental results that the channel attention mechanism using the feature repositioning [33] strategy improve the recognition rate of the MobileFaceNet model in some cases, but it has some impact on the memory and computational power occupied by the model.…”

Section: Eca Modulementioning

confidence: 99%

“…In this paper, we use the CASIA-Webface [33] face dataset as the training dataset. Using MTCNN [35] face detection method is used to re-detect the images in the dataset, and the detected face images are cropped to 96 × 96.…”

Section: Data Processingmentioning

confidence: 99%

A Lightweight Face Recognition Model based on MobileFaceNet for Limited Computation Environment

Xiao¹,

Jiang²,

Liu³

2022

EAI Endorsed Trans IoT

View full text Add to dashboard Cite

The face recognition method based on deep convolutional neural network is difficult to deploy in the embedding devices. In this work, we optimize the MobileFaceNet face recognition network MobileFaceNet so as to deploy it in embedding environment. Firstly, we reduce the model parameters by reducing the number of layers in MobileFaceNet. Then, the h-ReLU6 activation function is used to replace PReLU in the original model. Finally, the effective channel attention module efficient channel attention is introduced to obtain the importance of each feature channel by learning. After the optimization, the MobileFaceNet parameters are compressed to 3.4 MB, which is smaller than the original model (4.9 MB), and the mAPs reach 98.52%, 97.54% and 91.33% on the test sets of LFW, VGGFace2 and the self-built database, respectively, and the recognition time is about 85 ms/photo. It shows that the proposed method achieves a good balance between the model complexity and model performance.

show abstract

“…CNNs are involved in various image processing tasks, such as image segmentation, object detection and, image classification. The inherited models are often exploited to regress the quality scores by means of transfer learning and/or by learning HVS-based features [8,9].…”

Section: Introductionmentioning

confidence: 99%

Perceptually-Weighted Cnn For 360-Degree Image Quality Assessment Using Visual Scan-Path And Jnd

Sendjasni¹,

Larabi²,

Cheikh³

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Image quality assessment of immersive content and more specifically 360-degree one is still in its infancy. There are many challenges regarding sphere vs. projected representation, human visual system (HVS) properties in a 360-degree environment, etc. In this paper, we propose the use of CNNs to design a no reference model to predict visual quality of 360-degree images. Instead of feeding the CNN with ERPs, visually important viewports are extracted based on visual scan-path prediction and given to a multi-channel CNN using DenseNet-121. Moreover, information about visual fixations and just noticeable difference are used to account for the HVS properties and make the network closer to human judgment. The scan-path is also used to create multiple instances of the database so as to perform a robust generalization analysis and compensate for the lack of databases.

show abstract

A Novel Just-Noticeable-Difference-Based Saliency-Channel Attention Residual Network for Full-Reference Image Quality Predictions

Cited by 47 publications

References 70 publications

Picture-wise just noticeable difference prediction model for JPEG image quality assessment

Picture-wise just noticeable difference prediction model for JPEG image quality assessment

A Lightweight Face Recognition Model based on MobileFaceNet for Limited Computation Environment

Perceptually-Weighted Cnn For 360-Degree Image Quality Assessment Using Visual Scan-Path And Jnd

Contact Info

Product

Resources

About