We present a deep neural network-based approach to image quality assessment (IQA). The network is trained end-to-end and comprises ten convolutional layers and five pooling layers for feature extraction, and two fully connected layers for regression, which makes it significantly deeper than related IQA models. Unique features of the proposed architecture are that: 1) with slight adaptations it can be used in a no-reference (NR) as well as in a full-reference (FR) IQA setting and 2) it allows for joint learning of local quality and local weights, i.e., relative importance of local quality to the global quality estimate, in an unified framework. Our approach is purely data-driven and does not rely on hand-crafted features or other types of prior domain knowledge about the human visual system or image statistics. We evaluate the proposed approach on the LIVE, CISQ, and TID2013 databases as well as the LIVE In the wild image quality challenge database and show superior performance to state-of-the-art NR and FR IQA methods. Finally, cross-database evaluation shows a high ability to generalize between different databases, indicating a high robustness of the learned features.

Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment

Quality of Experience (QoE) has received much attention over the past years and has become a prominent issue for delivering services and applications. A significant amount of research has been devoted to understanding, measuring, and modelling QoE for a variety of media services. The next logical step is to actively exploit that accumulated knowledge to improve and manage the quality of multimedia services, while at the same time ensuring efficient and cost-effective network operations. Moreover, with many different players involved in the end-to-end service delivery chain, identifying the root causes of QoE impairments and finding effective solutions for meeting the end users’ requirements and expectations in terms of service quality is a challenging and complex problem. In this article, we survey state-of-the-art findings and present emerging concepts and challenges related to managing QoE for networked multimedia services. Going beyond a number of previously published survey articles addressing the topic of QoE management, we address QoE management in the context of ongoing developments, such as the move to softwarized networks, the exploitation of big data analytics and machine learning, and the steady rise of new and immersive services (e.g., augmented and virtual reality). We address the implications of such paradigm shifts in terms of new approaches in QoE modeling and the need for novel QoE monitoring and management infrastructures.

A Survey of Emerging Concepts and Challenges for QoE Management of Multimedia Services

Concentration and immersion belong to a similar mental state in which a person is preoccupied with a particular task. In this study, we investigated a possibility of diagnosing two mental states with a subtle difference. Concentration and immersion states were induced to analyze the electroencephalography (EEG) changes during these states. Thirty-two college students in their 20s participated in the study. For concentration, subjects were asked to focus on a red dot at the center of a white screen, and for immersion they were asked to focus on playing a computer game. Relative to rest, Alpha waves decreased during concentration and immersion. Relative to rest, Theta waves decreased at almost all channels during concentration and, on the other hand, increased at all channels during immersion. Beta waves increased during concentration and immersion in the frontal and occipital lobes, with a higher increase in immersion. In the temporal lobe, Beta waves decreased during concentration and increased during immersion. In the central region, Beta waves decreased during concentration and immersion, and the decrease during immersion was larger. Such evident differences between the EEG results for concentration and immersion can imply diagnostic capabilities of various other mental states.

https://www.mdpi.com/1424-8220/19/7/1669/pdf

Comparison between Concentration and Immersion Based on EEG Analysis.

A lightweight evaluation system, which can be deployed on common user equipment in commercial mobile networks, is proposed for measuring the user experience of multimedia services. The user experience evaluation system can measure the key quality indicators of traditional and emerging services in different scenarios. In contrast to traffic models, this system models typical user behavior to construct complex scenarios of communication networks. In commercial network experiments, the proposed evaluation system achieves stable and efficient performance in complex scenarios, which consist of different types of services and typical user behaviors.

A Lightweight End-Side User Experience Data Collection System for Quality Evaluation of Multimedia Communications

Over the last decade, there has been an exponential growth of services over the Internet. Services such as online gaming are gaining popularity, whereas, Voice over Internet (VoIP) has been well established. Storage, management and processing of data have moved away from the devices to the cloud. Quality of experience (QoE) defined as the user’s perception of service quality is utilized in different technologies, services and products for improving end user satisfaction and provides quality of service (QoS) according to their demands. In this paper, we describe the utilization of QoE in different technologies, services and products for improving end user satisfaction. Specifically, we present the latest developments in QoE in multimedia services, network management, VoIP, web development, games and cloud computing. Finally, we discuss the current research, solutions and present open issues of future research in QoE.

/pdf/application-of-quality-of-experience-in-networked-services-dzr0m6l4jd.pdf

Application of Quality of Experience in Networked Services: Review, Trend & Perspectives

We present a survey of psychophysiology-based assessment for quality of experience (QoE) in advanced multimedia technologies. We provide a classification of methods relevant to QoE and describe related psychological processes, experimental design considerations, and signal analysis techniques. We summarize multimodal techniques and discuss several important aspects of psychophysiology-based QoE assessment, including the synergies with psychophysical assessment and the need for standardized experimental design. This survey is not considered to be exhaustive but serves as a guideline for those interested to further explore this emerging field of research.

/pdf/psychophysiology-based-qoe-assessment-a-survey-26en4sug5e.pdf

Daniel P. Darcy

Papers

Psychophysiology-Based QoE Assessment: A Survey