Image quality assessment (IQA) is critically important for the image-processing field. IQA aims to build a computational model to predict human perceived image quality, accurately and automatically. Until now, great efforts have been employed to design IQA metrics. In this paper, we systematically and comprehensively review the fundamental, brief history, and state-of-the-art developments of IQA, with emphasis on natural image quality assessment (NIQA). First, the definition of image quality is discussed, which contains three aspects and lead to different philosophies of designing IQA metrics. Afterwards, classic NIQA metrics are presented with some further discussions. Widely used databases and the performances of classic NIQA metrics on them are also listed. We highlight the most significant works and some open issues about the developments of IQA, and provide the benchmarks for the researchers and scholars who work on IQA.

This paper investigates how to blindly evaluate the visual quality of an image by learning rules from linguistic descriptions. Extensive psychological evidence shows that humans prefer to conduct evaluations qualitatively rather than numerically. The qualitative evaluations are then converted into the numerical scores to fairly benchmark objective image quality assessment (IQA) metrics. Recently, lots of learning-based IQA models are proposed by analyzing the mapping from the images to numerical ratings. However, the learnt mapping can hardly be accurate enough because some information has been lost in such an irreversible conversion from the linguistic descriptions to numerical scores. In this paper, we propose a blind IQA model, which learns qualitative evaluations directly and outputs numerical scores for general utilization and fair comparison. Images are represented by natural scene statistics features. A discriminative deep model is trained to classify the features into five grades, corresponding to five explicit mental concepts, i.e., excellent, good, fair, poor, and bad. A newly designed quality pooling is then applied to convert the qualitative labels into scores. The classification framework is not only much more natural than the regression-based models, but also robust to the small sample size problem. Thorough experiments are conducted on popular databases to verify the model's effectiveness, efficiency, and robustness.

Image quality assessment (IQA) has thrived for decades, and researchers continue to explore how the human brain perceives visual stimuli. Psychological evidence shows that humans prefer qualitative descriptions when evaluating image quality, yet most researches still concentrate on numerical descriptions. Furthermore, handcrafting features are widely used in this community, which constrains the models' flexibility. A novel model is proposed with two major advantages: the saliency-guided feature learning can learn features unsupervisedly, and the deep framework recasts IQA as a classification problem, analogous to human qualitative evaluation. Experiments validate the proposed model's effectiveness.

图像质量的客观评价是图像处理领域中的一个重要分支.其评价指标可以作为一种测度或者准则用来校准图像处理系统,或用于图像处理算法的优化及参数的优选.部分参考型图像质量客观评价方法已经成为图像质量评价领域研究的热点之一.考虑到人眼对图像质量感知的模糊性,将图像质量空间划分为若干模糊集,利用自然场景统计特征,将图像质量评价问题转化为模糊分类问题,提出了一种快速、有效的部分参考型图像质量评价方法.该方法与经典的部分参考型图像质量评价方法相比,主观感知的相关系数平均提高,计算代价显著降低,与人类主观感知有很好的一致性.

The technique of visual saliency detection supports video surveillance systems by reducing redundant information and highlighting the critical, visually important regions. It follows that information about the image might be of great importance in depicting the visual saliency. However, the majority of existing methods extract contrast-like features without considering the contribution of information content. Based on the hypothesis that information divergence leads to visual saliency, a two-stage framework for saliency detection, namely information divergence model (IDM), is introduced in this paper. The term ''information divergence'' is used to express the non-uniform distribution of the visual information in an image. The first stage is constructed to extract sparse features by employing independent component analysis (ICA) and difference of Gaussians (DoG) filter. The second stage improves the Bayesian surprise model to compute information divergence across an image. A visual saliency map is finally obtained from the information divergence. Experiments are conducted on nature image databases, psychological patterns and video surveillance sequences. The results show the effectiveness of the proposed method by comparing it with 13 state-of-the-art visual saliency detection methods.

As the performance indicator of the image processing algorithms or systems, image quality assessment (IQA) has attracted the attention of many researchers. Aiming to the widely used compression standards, JPEG and JPEG2000, we propose a new no reference (NR) metric for compressed images to do IQA. This metric exploits the causes of distortion by JPEG and JPEG2000, employs the directional discrete cosine transform (DDCT) to obtain the detail and directional information of the images and incorporates with the visual perception to obtain the image quality index. Experimental results show that the proposed metric not only has outstanding performance on JPEG and JPEG2000 images, but also applicable to other types of artifacts.

Image quality evaluation is to use some computational models to predict the quality of the specified image automatically and accurately. Since human eyes are ultimate receptor of images, it is better to mimic human visual system (HVS) to perceive the image quality. Based on the properties of the HVS, a novel bionic image quality metric (IQA) is proposed, which adopts several bionic characteristics, e.g. multi-channel decomposition, contrast sensitivity function, center-surround operation and lateral inhibition mechanism. Experimental results demonstrate that the performance of the proposed IQA method outperforms those of the existing methods.