Blind Quality Assessment for Cartoon Images

Chen, Yuan; Zhao, Yang; Li, Shujie; Zuo, Wangmeng; Jia, Wei; Li, Xiaoping

doi:10.1109/tcsvt.2019.2931589

Cited by 21 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) Visualization A simulation is inseparable from visualization [76,77] , and the visualization of simulation results has become a convention of a simulation. However, because the modeling of complex systems is also extremely difficult, the introduction of visualization in the early stage [78,79] not only makes the modeling of complex systems more clear and visible but also contributes to the early participation of human thinking. It can promote the correctness of modeling and the understanding of the nature of complex systems to a certain extent.…”

Section: Many Other Methods Have Also Been Proposedmentioning

confidence: 99%

State-of-the-Art Development of Complex Systems and Their Simulation Methods

Tang

Liu

2021

Complex Syst. Model. Simul.

Self Cite

View full text Add to dashboard Cite

The research on complex systems is different from that on general systems because the former must consider self-organization, emergence, uncertainty, predetermination, and evolution. As an important method to transform the world, a simulation is one of the most important skills to discover complex systems. In this study, we provide a survey on complex systems and their simulation methods. Initially, the development history of complex system research is summarized from two main lines. Then, the eight common characteristics of the most complex systems are presented. Furthermore, the simulation methods of complex systems are introduced in detail from four aspects, namely, meta-synthesis methods, complex networks, intelligent technologies, and other methods. From the overall point of view, intelligent technologies are the driving force, and complex networks are the advanced structure. Meta-synthesis methods are the integration strategy, and other methods are the supplements. In addition, we show three complex system simulation examples: digital reactor simulation, simulation of a logistics system in the industrial site, and crowd evacuation simulation. The examples show that a simulation is a useful means and an important method in complex system research.Finally, the future development prospects for complex systems and their simulation methods are suggested.

show abstract

Section: Many Other Methods Have Also Been Proposedmentioning

confidence: 99%

State-of-the-Art Development of Complex Systems and Their Simulation Methods

Tang

Liu

2021

Complex Syst. Model. Simul.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep Image Structure and Texture Similarity measure (DISTS) [26] is proposed based on the pre-trained VGG network to unify the structure and texture similarity. The recent work [28] also developed the blind image quality assessment (BIQA) algorithm for cartoon image. In addition, many works [29], [30] integrated Just Noticeable Difference (JND) models [31]- [33] for image/video quality assessment and achieved good performance.…”

Section: Perceptual Image Quality Assessmentmentioning

confidence: 99%

Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generation

Sun¹,

Jin²,

Wang³

2022

Preprint

View full text Add to dashboard Cite

Deep learning models are found to be vulnerable to adversarial examples, as wrong predictions can be caused by small perturbation in input for deep learning models. Most of the existing works of adversarial image generation try to achieve attacks for most models, while few of them make efforts on guaranteeing the perceptual quality of the adversarial examples. High quality adversarial examples matter for many applications, especially for the privacy preserving. In this work, we develop a framework based on the Minimum Noticeable Difference (MND) concept to generate adversarial privacy preserving images that have minimum perceptual difference from the clean ones but are able to attack deep learning models. To achieve this, an adversarial loss is firstly proposed to make the deep learning models attacked by the adversarial images successfully. Then, a perceptual quality-preserving loss is developed by taking the magnitude of perturbation and perturbation-caused structural and gradient changes into account, which aims to preserve high perceptual quality for adversarial image generation. To the best of our knowledge, this is the first work on exploring qualitypreserving adversarial image generation based on the MND concept for privacy preserving. To evaluate its performance in terms of perceptual quality, the deep models on image classification and face recognition are tested with the proposed method and several anchor methods in this work. Extensive experimental results demonstrate that the proposed MND framework is capable of generating adversarial images with remarkably improved performance metrics (e.g., PSNR, SSIM, and MOS) than that generated with the anchor methods.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Although previous methods own low computational complexity, the evaluation results are not reasonable when sharp edge is lacking. Therefore, some methods were proposed based on Tchebichef moment, which obtained better results [8,9]. Based on the observation that human beings have difficulty in perceiving differences between a blurred image and the same re-blurred image, Crete et al [10] proposed a method in which the blurriness was evaluated by comparison between intensity variations of neighbouring pixels of an input image before and after applying a low-pass filter.…”

Section: Introductionmentioning

confidence: 99%

A no‐reference blurred colourful image quality assessment method based on dual maximum local information

Chen

2021

IET Signal Processing

View full text Add to dashboard Cite

Images can be blurred due to the imperfection of the imaging system and blurriness is one of the challenging problems for image quality assessment (IQA). No-reference blurred IQA methods have been proposed in the literature to calculate image blurriness. Inspired by image processing-based auto-focussing and maximum local information theories, a no-reference blurred colourful IQA method based on Dual Maximum Local Information is proposed here. First, a window extraction method that combines the maximum gradient with local entropy is proposed to obtain the region of interest (ROI) for subsequent processing. Second, an improved maximum gradient method that leverages information from different channel images is presented to calculate the maximum gradient variation within the ROI for final sharpness score. Experimental results illustrated that the proposed method has better performance under various measurements compared with the state-of-the-art methods on LIVE, CSIQ, TID2008, TID2013, VCL@FER, IVC image databases.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

show abstract

Blind Quality Assessment for Cartoon Images

Cited by 21 publications

References 42 publications

State-of-the-Art Development of Complex Systems and Their Simulation Methods

State-of-the-Art Development of Complex Systems and Their Simulation Methods

Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generation

A no‐reference blurred colourful image quality assessment method based on dual maximum local information

Contact Info

Product

Resources

About