Quality Assessment of Screen Content Images in Wavelet Domain

Cheraaqee, Pooryaa; Maviz, Zahra; Mansouri, Azadeh; Mahmoudi-Aznaveh, Ahmad

doi:10.1109/tcsvt.2021.3067627

Cited by 10 publications

(3 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SCI images are mostly distinct, with a greater emphasis on structure and edges. Also, the human visual system mainly extracts these structures, and super-resolution with a loss function that prioritizes sharp edges and structures is required for SCIs [7]. In 2019, Jun Wu proposed a perception-aware evaluation of eight state-of-the-art SR algorithms and evaluated them with nine Image Quality Assessment (IQA) methods to prove that modifying the algorithm for screen content images is necessary [8].…”

Section: Screen Content Imagesmentioning

confidence: 99%

“…WS-HV is mainly designed for screen content (SCIs) quality evaluation, so we choose it for better comparison as well. Referring to [7], the WS-HV has a better correlation than the other SCI quality assessment metrics with Human Visual System (HVS) [21,22]. Same as SSIM, its values vary between 0 and 1, and a higher value indicates better quality.…”

Section: Quality Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

DCT-based Perceptual Loss For Screen Content Image Super-Resolution

Sekhavaty-Moghadam,

Hosseinkhani,

Mansouri

2024

Preprint

View full text Add to dashboard Cite

The acceptable results of deep learning led to the use of the deep neural network on a wide range of models, including image super-resolution. The performance of the deep neural network is directly affected by its loss function. Most methods use intensity loss, such as MSE, which computes the difference between the predicted image and the ground truth. Since the structural information of a scene is more sensitive to the human visual system, it is desired that the loss function could measure the impact of the structural error. In addition, the use of screen content images has become widespread because of many applications such as desktop-sharing and remote computing. As a result, super-resolution of screen content images becomes a crucial technique to enhance the quality of low-resolution images. In the presented loss function, the structural error is weighted by employing DCT components. The model is trained and tested using the screen content images, and the experimental subjective and objective results illustrate the effectiveness of the presented loss for screen content images.

show abstract

Section: Screen Content Imagesmentioning

confidence: 99%

Section: Quality Evaluationmentioning

confidence: 99%

DCT-based Perceptual Loss For Screen Content Image Super-Resolution

Sekhavaty-Moghadam,

Hosseinkhani,

Mansouri

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…It is easy to see that the histograms are very different. Also the effect of coding artifacts in the two types of images can be different [8]. For instance, quality loss near the edges is a common side effect of compressing natural images; yet, if done right, it may be imperceptible.…”

Section: Introductionmentioning

confidence: 99%

Multi-Task Learning for Screen Content Image Coding

Zamanshoar¹,

Bajić²

2023

Preprint

View full text Add to dashboard Cite

With the rise of remote work and collaboration, compression of screen content images (SCI) is becoming increasingly important. While there are efficient codecs for natural images, as well as codecs for purely-synthetic images, those SCIs that contain both synthetic and natural content pose a particular challenge. In this paper, we propose a learning-based image coding model developed for such SCIs. By training an encoder to provide a latent representation suitable for two tasks -input reconstruction and synthetic/natural region segmentation -we create an effective SCI image codec whose strong performance is verified through experiments. Once trained, the second task (segmentation) need not be used; the codec still benefits from the segmentation-friendly latent representation.

show abstract

A Hybrid Method for Objective Quality Assessment of Binary Images

Okarma

Kopytek

2023

IEEE Access

View full text Add to dashboard Cite

Quality Assessment of Screen Content Images in Wavelet Domain

Cited by 10 publications

References 67 publications

DCT-based Perceptual Loss For Screen Content Image Super-Resolution

DCT-based Perceptual Loss For Screen Content Image Super-Resolution

Multi-Task Learning for Screen Content Image Coding

A Hybrid Method for Objective Quality Assessment of Binary Images

Contact Info

Product

Resources

About