Visual quality assessment: recent developments, coding applications and future trends

Abstract

Research on visual quality assessment has been active during the last decade. In this work, we provide an in-depth review of recent developments in the field. As compared with existing survey papers, our current work has several unique contributions. First, besides image quality databases and metrics, we put equal emphasis on video quality databases and metrics as this is a less investigated area. Second, we discuss the application of visual quality evaluation to perceptual coding as an example for applications. Third, we benchmark the performance of state-of-the-art visual quality metrics with experiments. Finally, future trends in visual quality assessment are discussed.

Content-aware objective video quality assessment

“…2 Subjective assessment is typically performed by a group of humans, who evaluate videos according to certain welldefined criteria such as those defined in the related International Telecommunication Union (ITU) Standards. 3 Often, the result of such an assessment is a mean opinion score (MOS) or a difference-MOS (DMOS) per assessed video sequence.…”

“…Therefore, it is unpractical for real time video processing and hard to incorporate into a system design process. 2 For this reason, many researchers have proposed objective (numerical) methods for predicting PVQ directly from the video data, termed video quality metrics (VQMs). Currently, there exists a large variety of objective methods, ranging from simple ones employing local spatiotemporal statistics, detail losses, and additive impairments, to more complex ones, such as those based on the results of physiological and/or psychovisual experiments.…”

“…Currently, there exists a large variety of objective methods, ranging from simple ones employing local spatiotemporal statistics, detail losses, and additive impairments, to more complex ones, such as those based on the results of physiological and/or psychovisual experiments. 2,[7][8][9][10][11] However, these objective methods are computationally too complex and/or not generic enough for a wide variety of video content scenes. The latter problem is mainly due to the strong dependency of VQMs on the video content.…”

“…25 TPB full-reference quality measure use pixel-wise operations for computing differences between images and/or video sequences, for instance, PSNR is the most simple but still widely used TPB full-reference quality measure. 2 NVC methods use statistical measures (mean, variance, histograms) in local neighborhoods and/or visual features (blurring, blocking, texture, visual impairments) for computing numerical scores. For example, SOVQM 7 is computed by using local spatiotemporal statistics which are computed on blocks of a fixed size.…”

Improved visual information fidelity based on sensitivity characteristics of digital images

“…Image quality assessment plays a crucial role in many applications, such as image enhancement [1][2], acquisition [3], watermarking [33], compression [34] and transmission [35]. The assessment methods are divided into subjective and objective quality measures.…”