Existing Image Quality Metrics Research Articles

Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies

Many challenges that deal with processing of HDR material remain very much open for the film industry, whose extremely demanding quality standards are not met by existing automatic methods. Therefore, when dealing with HDR content, substantial work by very skilled technicians has to be carried out at every step of the movie production chain. Based on recent findings and models from vision science, we propose in this work effective tone mapping and inverse tone mapping algorithms for production, post-production and exhibition. These methods are automatic and real-time, and they have been both fine-tuned and validated by cinema professionals, with psychophysical tests demonstrating that the proposed algorithms outperform both the academic and industrial state-of-the-art. We believe these methods bring the field closer to having fully automated solutions for important challenges for the cinema industry that are currently solved manually or sub-optimally. Another contribution of our research is to highlight the limitations of existing image quality metrics when applied to the tone mapping problem, as none of them, including two state-of-the-art deep learning metrics for image perception, are able to predict the preferences of the observers.

Perceptual Image Quality Assessment for Various Viewing Conditions and Display Systems

From complete darkness to direct sunlight, real-world displays operate in various viewing conditions often resulting in a non-optimal viewing experience. Most existing Image Quality Assessment (IQA) methods, however, assume ideal environments and displays, and thus cannot be used when viewing conditions differ from the standard. In this paper, we investigate the influence of ambient illumination level and display luminance on human perception of image quality. We conduct a psychophysical study to collect a novel dataset of over 10000 image quality preference judgments performed in illumination conditions ranging from 0 lux to 20000 lux. We also propose a perceptual IQA framework that allows most existing image quality metrics (IQM) to accurately predict image quality for a wide range of illumination conditions and display parameters. Our analysis demonstrates strong correlation between human IQA and the predictions of our proposed framework combined with multiple prominent IQMs and across a wide range of luminance values.

Dataset and Metrics for Predicting Local Visible Differences

A large number of imaging and computer graphics applications require localized information on the visibility of image distortions. Existing image quality metrics are not suitable for this task as they provide a single quality value per image. Existing visibility metrics produce visual difference maps, and are specifically designed for detecting just noticeable distortions but their predictions are often inaccurate. In this work, we argue that the key reason for this problem is the lack of large image collections with a good coverage of possible distortions that occur in different applications. To address the problem, we collect an extensive dataset of reference and distorted image pairs together with user markings indicating whether distortions are visible or not. We propose a statistical model that is designed for the meaningful interpretation of such data, which is affected by visual search and imprecision of manual marking. We use our dataset for training existing metrics and we demonstrate that their performance significantly improves. We show that our dataset with the proposed statistical model can be used to train a new CNN-based metric, which outperforms the existing solutions. We demonstrate the utility of such a metric in visually lossless JPEG compression, super-resolution and watermarking.

АНАЛИЗ И ПРОГНОЗИРОВАНИЕ ЭФФЕКТИВНОСТИ ФИЛЬТРАЦИИ С ИСПОЛЬЗОВАНИЕМ БЕЗЭТАЛОННЫХ МЕР ВИЗУАЛЬНОГО КАЧЕСТВА ИЗОБРАЖЕНИЙ

Images are subject to noise during acquisition, transmission and processing. Image denoising is highly desirable, not only to provide better visual quality, but also to improve performance of the subsequent operations such as compression, segmentation, classification, object detection and recognition. In the past decades, a large number of image denoising algorithms has been developed, ranging from simple linear methods to complex methods based on similar blocks search and deep convolutional neural networks. However, most of existing denoising techniques have a tendency to oversmooth image edges, fine details and textures. Thus, there are cases when noise reduction leads to loss of image features and filtering does not produce better visual quality. According to this, it is very important to evaluate denoising result and hence to undertake a decision whether denoising is expedient. Despite the fact that image denoising has been one of the most active research areas, only a little work has been dedicated to visual quality evaluation for denoised images. There are many approaches and metrics to characterize image quality, but adequateness of these metrics is of question. Existing image quality metrics, especially no-reference ones, have not been thoroughly studies for image denoising. In terms of using visual quality metrics, it is usually supposed that the higher the improvement for a given metric, the better visual quality for denoised image. However, there are situations when denoising does not result in visual quality enhancement, especially for texture images. Thus, it would be desirable to predict human subjective evaluation for denoised image. Then, this information will clarify when denoising can be expedient. The purpose of this paper is to give analysis of denoising expedience using no-reference (NR) image quality metrics. In addition, this work considers possible ways to predict human subjective evaluation of denoised images based on several input parameters. More in details, two denoising techniques, namely the standard sliding window DCT filter and the BM3D filter have been considered. Using a specialized database of test images SubjectiveIQA, performance evaluation of existing state-of-the-art objective no-reference quality metrics for denoised images is carried out

Continuous wavelet transform-based no-reference quality assessment of deblocked images

An image when passed through a compression process either gains noise or loses some information, resulting in a degraded image. JPEG is considered to be one of the most commonly used compression standards whose resulting images are found to be subjected to blocking artifacts at low bit rates. There exist a few deblocking algorithms which have been proposed in the literature to reduce the blocking artifacts in compressed images. However, unfortunately these deblocking techniques introduce blur distortion in the images and hence the deblocked images may contain multiple distortions. Existing image quality metrics have limitations in evaluating the quality of deblocked images as they are not designed for multiply distorted images. To overcome this issue, we propose a no-reference quality assessment technique for deblocked images using continuous wavelet transform. We evaluate the proposed technique on DBID database which consists of general deblocked images. Experimental results show that the proposed quality assessment technique outperforms the existing image quality assessment techniques for deblocked images.

Perceptual quality evaluation for image defocus deblurring

Blur is one of the most common distortion types in image acquisition. Image deblurring has been widely studied as an effective technique to improve the quality of blurred images. However, little work has been done to the perceptual evaluation of image deblurring algorithms and deblurred images. In this paper, we conduct both subjective and objective studies of image defocus deblurring. A defocus deblurred image database (DDID) is first built using state-of-the-art image defocus deblurring algorithms, and subjective test is carried out to collect the human ratings of the images. Then the performances of the deblurring algorithms are evaluated based on the subjective scores. With the observation that the existing image quality metrics are limited in predicting the quality of defocus deblurred images, a quality enhancement module is proposed based on Gray Level Co-occurrence Matrix (GLCM), which is mainly used to measure the loss of texture naturalness caused by deblurring. Experimental results based on the DDID database demonstrate the effectiveness of the proposed method.

A ParaBoost Method to Image Quality Assessment.

An ensemble method for full-reference image quality assessment (IQA) based on the parallel boosting (ParaBoost) idea is proposed in this paper. We first extract features from existing image quality metrics and train them to form basic image quality scorers (BIQSs). Then, we select additional features to address specific distortion types and train them to construct auxiliary image quality scorers (AIQSs). Both BIQSs and AIQSs are trained on small image subsets of certain distortion types and, as a result, they are weak performers with respect to a wide variety of distortions. Finally, we adopt the ParaBoost framework, which is a statistical scorer selection scheme for support vector regression (SVR), to fuse the scores of BIQSs and AIQSs to evaluate the images containing a wide range of distortion types. This ParaBoost methodology can be easily extended to images of new distortion types. Extensive experiments are conducted to demonstrate the superior performance of the ParaBoost method, which outperforms existing IQA methods by a significant margin. Specifically, the Spearman rank order correlation coefficients (SROCCs) of the ParaBoost method with respect to the LIVE, CSIQ, TID2008, and TID2013 image quality databases are 0.98, 0.97, 0.98, and 0.96, respectively.

General-purpose image quality assessment based on distortion-aware decision fusion

General-purpose image quality metrics aiming for quality prediction across various distortion types exhibit, on the whole, very limited effectiveness. In this paper, we propose a two-stage scheme to alleviate this limitation. At the first stage, probabilistic knowledge about the image distortion types is obtained based on a support-vector classification method. At the second stage, decision fusion of three existing image quality metrics is performed using the k-nearest-neighbor (k-NN) regression where the aforementioned probabilistic knowledge is utilized under an adaptive weighting scheme. We evaluate our method on the TID2008 database that is the largest publicly available image quality database containing 17 distortion types. The results strongly support the effectiveness and robustness of our method.

Learning to Predict Localized Distortions in Rendered Images

AbstractIn this work, we present an analysis of feature descriptors for objective image quality assessment. We explore a large space of possible features including components of existing image quality metrics as well as many traditional computer vision and statistical features. Additionally, we propose new features motivated by human perception and we analyze visual saliency maps acquired using an eye tracker in our user experiments. The discriminative power of the features is assessed by means of a machine learning framework revealing the importance of each feature for image quality assessment task. Furthermore, we propose a new data‐driven full‐reference image quality metric which outperforms current state‐of‐theart metrics. The metric was trained on subjective ground truth data combining two publicly available datasets. For the sake of completeness we create a new testing synthetic dataset including experimentally measured subjective distortion maps. Finally, using the same machine‐learning framework we optimize the parameters of popular existing metrics.

RCBM: a rough content-based image quality assessment metric

A generalised content-based image quality assessment technique is proposed in this paper. Different from many existing image quality metrics, where the digital image quality is evaluated by comparing with a reference image and a single ‘exact’ value is provided for the purpose of ‘accurately’ quantifying the image quality, our proposed method defines the image quality metric based on the theory of the rough fuzzy integral and a region (with a pair of the boundary values) is presented to estimate the image quality instead of a scalar value. The new philosophy for the proposed ‘rough’ content-based image quality metric lays on the acceptance of the uncertainty of subjective image quality assessment through the human visual system (HVS) and addresses this kind of uncertainty by applying the rigorous mathematical concept of the rough and fuzzy set on the standard content-based image quality analysis. Therefore, the proposed method is a good mimicking of the subjective image quality assessment and meets the ac...

A Psychovisual Quality Metric in Free-Energy Principle

In this paper, we propose a new psychovisual quality metric of images based on recent developments in brain theory and neuroscience, particularly the free-energy principle. The perception and understanding of an image is modeled as an active inference process, in which the brain tries to explain the scene using an internal generative model. The psychovisual quality is thus closely related to how accurately visual sensory data can be explained by the generative model, and the upper bound of the discrepancy between the image signal and its best internal description is given by the free energy of the cognition process. Therefore, the perceptual quality of an image can be quantified using the free energy. Constructively, we develop a reduced-reference free-energy-based distortion metric (FEDM) and a no-reference free-energy-based quality metric (NFEQM). The FEDM and the NFEQM are nearly invariant to many global systematic deviations in geometry and illumination that hardly affect visual quality, for which existing image quality metrics wrongly predict severe quality degradation. Although with very limited or even without information on the reference image, the FEDM and the NFEQM are highly competitive compared with the full-reference SSIM image quality metric on images in the popular LIVE database. Moreover, FEDM and NFEQM can measure correctly the visual quality of some model-based image processing algorithms, for which the competing metrics often contradict with viewers' opinions.

Framework for optimal region of interest–based quality assessment in wireless imaging

Images usually exhibit regions that particularly attract the viewer's attention. These regions are typically referred to as regions of interest (ROI), and the underlying phenomenon in the human visual system is known as visual attention (VA). In the context of image quality, one can expect that distortions occurring in the ROI are perceived as being more annoying compared to distortions in the background. However, VA is seldom taken into account in existing image quality metrics. In this work, we provide a VA framework to extend existing image quality metrics with a simple VA model. The performance of the framework is evaluated on three contemporary image quality metrics. We further consider the context of wireless imaging where a broad range of artifacts can be observed. To facilitate the VA-based metric design, we conduct subjective experiments to both obtain a ground truth for the subjective quality of a set of test images and to identify ROI in the corresponding reference images. A methodology is further discussed to optimize the VA metrics with respect to quality prediction accuracy and generalization ability. It is shown that the quality prediction performance of the three considered metrics can be significantly improved by deploying the proposed framework.