Field Of Image Quality Assessment Research Articles

No-reference image quality assessment based on global awareness.

In the field of computer vision, the application of hand-crafted as well as computer-learning-based methods in the field of image quality assessment has yielded remarkable results. However, in the field of no-reference image distortion, it is still challenging to accurately perceive and determine the quality of an image. To address the difficulties of Image Quality Assessment (IQA) in the field of authentic distorted images, we consider the use of the Swin Transformer (ST) to extract features. To enable the model to focus on both spatial and channel information of features, we design a plug-and-play Global Self-Attention Block (GSAB). At the same time, we introduce a Transformer block in the model to enhance the model's ability to capture long-range dependencies. Finally, we derive the prediction of image quality scores through a Dual-Branching structure. Our method is experimented on four synthetic datasets as well as two authentic datasets, and the results of the experiments are weighted according to the size of the datasets, and the results show that our method outperforms all the current methods and works well in the Generalization ability test, which proves that our method has a good generalization ability. The code will be posted subsequently at https://github.com/yanggege-new/NR-IQA-based-on-global-awareness.

Full-Reference Image Quality Assessment Based on Multi-Channel Visual Information Fusion

This study focuses on improving the objective alignment of image quality assessment (IQA) algorithms with human visual perception. Existing methodologies, predominantly those based on the Laplacian of Gaussian (LoG) filter, often neglect the impact of color channels on human visual perception. Consequently, we propose a full-reference IQA method that integrates multi-channel visual information in color images. The methodology begins with converting red, green, blue (RGB) images into the luminance (L), red–green opponent color channel (M), blue–yellow opponent color channel (N) or LMN color space. Subsequently, the LoG filter is separately applied to the L, M, and N channels. The convoluted components are then fused to generate a contrast similarity map using the root-mean-square method, while the chromaticity similarity map is derived from the color channels. Finally, multi-channel LoG filtering, contrast, and chromaticity image features are connected. The standard deviation method is then used for sum pooling to create a full-reference IQA computational method. To validate the proposed method, distorted images from four widely used image databases were tested. The evaluation, based on four criteria, focused on the method’s prediction accuracy, computational complexity, and generalizability. The Pearson linear correlation coefficient (PLCC) values, recorded from the databases, ranged from 0.8822 (TID2013) to 0.9754 (LIVE). Similarly, the Spearman rank-order correlation coefficient (SROCC) values spanned from 0.8606 (TID2013) to 0.9798 (LIVE). In comparison to existing methods, the proposed IQA method exhibited superior visual correlation prediction accuracy, indicating its promising potential in the field of image quality assessment.

Investigating pretrained self-supervised vision transformers for reference-based quality assessment

Reference-based image quality assessment techniques use information from an undistorted reference image of the same scene to estimate the quality of a distorted target image. The main challenge in designing algorithms for quality assessment is to incorporate the behavior of the human visual system into the algorithms. The advent of deep learning (DL) techniques has garnered sufficient interest among researchers in the field of image quality assessment. The common limitation of applying deep learning for image quality assessment is its dependence on a large amount of subjective training data. Recent advances in the field of patch-based self-supervised vision transformers have achieved remarkable results for tasks like object segmentation, copy detection, etc. and other downstream computer vision tasks. In this paper, we study how the distance between the pretrained self-supervised vision transformer features applied on pristine and distorted images is related to the human visual system. Experiments carried out on three publicly available image quality databases (namely KADID-10K, TID2013, and MDID2016) have yielded promising results that can be further exploited to design perceptual reference-based image quality assessment methods.

Rumor Classification through a Multimodal Fusion Framework and Ensemble Learning.

The proliferation of rumors on social media has become a major concern due to its ability to create a devastating impact. Manually assessing the veracity of social media messages is a very time-consuming task that can be much helped by machine learning. Most message veracity verification methods only exploit textual contents and metadata. Very few take both textual and visual contents, and more particularly images, into account. Moreover, prior works have used many classical machine learning models to detect rumors. However, although recent studies have proven the effectiveness of ensemble machine learning approaches, such models have seldom been applied. Thus, in this paper, we propose a set of advanced image features that are inspired from the field of image quality assessment, and introduce the Multimodal fusiON framework to assess message veracIty in social neTwORks (MONITOR), which exploits all message features by exploring various machine learning models. Moreover, we demonstrate the effectiveness of ensemble learning algorithms for rumor detection by using five metalearning models. Eventually, we conduct extensive experiments on two real-world datasets. Results show that MONITOR outperforms state-of-the-art machine learning baselines and that ensemble models significantly increase MONITOR’s performance.

No-reference image quality assessment based on automatic machine learning

In different applications in deep learning, due to different required features, it is necessary to design specialized Neural Network structure. However, the design of the structure largely depends on the relevant subject knowledge of researchers and lots of experiments, resulting in huge waste of manpower. Therefore, in the field of Image Quality Assessment (IQA), the authors propose a method to apply Neural Architecture Search (NAS) to IQA. Mainly through the Differentiable Architecture Search algorithm, the structure of the modular Neural Network unit is searched by the stochastic gradient descent algorithm with better training performance by relaxing the operation features into a continuous space. Also, the idea of weight sharing is used to further save. The authors use the mainstream IQA database LIVE to search for Neural Network structures, and retrain and validate the searched structures in four datasets. A large number of experiments show that the model obtained by the search experiment achieves the effect of the best algorithm at this stage, and has a certain quality. The main contributions of this paper are: Transform the DARTS algorithm to adapt the regression problem, and introduce the Neural Architecture Search algorithm into the IQA field and conduct experimental verification.

Deep Learning in Image Quality Assessment: Past, Present, and What Lies Ahead

Quality assessment of images plays an important role in different applications in image processing and computer vision. While subjective quality assessment of images is the most accurate approach due to issues objective quality metrics have been the go to approach. Until recently most such metrics have taken advantage of different handcrafted features. Similar (but with a slower speed) to other applications in image processing and computer vision, different machine learning techniques, more specifically Convolutional Neural Networks (CNNs) have been introduced in different tasks related to image quality assessment. In this short paper which is a supplement to a focal talk given with the same title at the London Imaging Meeting (LIM) 2021 we aim to provide a short timeline on how CNNs have been used in the field of image quality assessment so far, how the field could take advantage of CNNs to evaluate the image quality, and what we expect will happen in the near future.

A Document Image Dataset for Quality Assessment

Mobile device plays an very important role in capturing document image. However, the quality of the captured image is influenced by many factors, such as device quality and shooting conditions. In this context, it is necessary to automatically assess the quality of captured document image. Although there has a lot of work in the filed of image quality assessment (IQA), insufficient attention has been paid to the establishment of document images dataset. Thus, we propose a large dataset of document images containing 19,943 images which are collected by mobile devices. During the process of image acquisition, many factors such as light intensity, distortion type, document material are considered. After capturing images, multiple volunteers participated in the evaluation and collection of Mean Opinion Score (MOS) of the document images. We use two no-reference image quality assessment algorithms to test the proposed dataset. The experimental results show the validity of our dataset and the reliability of MOS. The proposed dataset can be used in the field of image quality assessment and Optical Character Recognition.

Multi-Channel Decomposition in Tandem With Free-Energy Principle for Reduced-Reference Image Quality Assessment

The visual quality of perceptions is highly correlated with the mechanisms of the human brain and visual system. Recently, the free-energy principle, which has been widely researched in brain theory and neuroscience, is introduced to quantize the perception, action, and learning in human brain. In the field of image quality assessment (IQA), on one hand, the free-energy principle can resort to the internal generative model to simulate the visual stimulus of the human beings. On the other hand, abundant psychological and neurobiological studies reveal that different frequency and orientation components of one visual stimulus arouse different neurons in the striate cortex, and the striate cortex processes visual information in the cerebral cortex. Motivated by these two aspects, a novel reduce-reference IQA metric called the multi-channel free-energy based reduced-reference quality metric is proposed in this paper. First, a two-level discrete Haar wavelet transform is used to decompose the input reference and distorted images. Next, to simulate the generative model in the human brain, the sparse representation is leveraged to extract the free-energy-based features in subband images. Finally, the overall quality metric is obtained through the support vector regressor. Extensive experimental comparisons on four benchmark image quality databases (LIVE, CSIQ, TID2008, and TID2013) demonstrate that the proposed method is highly competitive with the representative reduced-reference and classical full-reference models.

Feature comparison and analysis for new challenging research fields of image quality assessment

Nowadays, objective image quality assessment (IQA) issue becomes increasingly important for both the practical application and scientific research in digital image processing systems. In this paper, we conduct feature comparison and analysis on new challenging research fields including contrast-distorted, screen content, multiply-distorted, tone-mapped, Depth Image Based Rendering (DIBR) and authentically distorted IQA. We describe the performance criteria, design rationale, and benchmark databases for validating IQA metrics in accordance with human perceptions. Then we provide some important conclusions of feature selection in terms of different IQA problems. In this work, our goal is dominantly towards judging the robustness of mainstream features used in the IQA field, which can help current and emerging researchers for better and faster grasping the speciality of each of novel IQA directions reported.

Objective assessment of low contrast detectability in computed tomography with Channelized Hotelling Observer

PurposeIterative algorithms introduce new challenges in the field of image quality assessment. The purpose of this study is to use a mathematical model to evaluate objectively the low contrast detectability in CT. Materials and methodsA QRM 401 phantom containing 5 and 8 mm diameter spheres with a contrast level of 10 and 20 HU was used. The images were acquired at 120 kV with CTDIvol equal to 5, 10, 15, 20 mGy and reconstructed using the filtered back-projection (FBP), adaptive statistical iterative reconstruction 50% (ASIR 50%) and model-based iterative reconstruction (MBIR) algorithms. The model observer used is the Channelized Hotelling Observer (CHO). The channels are dense difference of Gaussian channels (D-DOG). The CHO performances were compared to the outcomes of six human observers having performed four alternative forced choice (4-AFC) tests. ResultsFor the same CTDIvol level and according to CHO model, the MBIR algorithm gives the higher detectability index. The outcomes of human observers and results of CHO are highly correlated whatever the dose levels, the signals considered and the algorithms used when some noise is added to the CHO model. The Pearson coefficient between the human observers and the CHO is 0.93 for FBP and 0.98 for MBIR. ConclusionThe human observers' performances can be predicted by the CHO model. This opens the way for proposing, in parallel to the standard dose report, the level of low contrast detectability expected. The introduction of iterative reconstruction requires such an approach to ensure that dose reduction does not impair diagnostics.

Study Algorithms which Assessed Quality of the Blurred Images

No-reference measurement of blurring artifacts in images is a difficult problem in image quality assessment field. In this paper, we present a no-reference blur metric to measure the quality of the images. These images are degraded using Gaussian blurring. Suggestion method depends on developing the Mean of Locally Standard deviation and Mean of the image (MLSD) model, this method is called Blur Quality Metric (BQM) and it calculates from numerical integral of the function in this model. And the BQM is compared with the No-reference Perceptual Blur Metrics (PBM) and the Entropy of the First Derivative (EFD) Image; the BQM is a simple metric and gives good accuracy in metrics the quality for the Gaussian blurred image if it compared with another algorithms.

Image Sharpness Measure for Blurred Images in Frequency Domain

One of the most challenging problems for researchers in the field of image processing is image quality assessment. A very important factor in image quality assessment is image sharpness/blurriness. The goal of researchers in the field of image quality assessment is to design and develop algorithms and measures for detecting sharpness and blurriness in an image. In this pape r a new technique is proposed to calculate image sharpness/blurriness measure in frequency domain.

A structural difference based image clutter metric with brain cognitive model constraints

Previous clutter metrics have less than the desired accuracy in predicting targeting performance, in this paper, a structural difference based image clutter metric is proposed based on the given definition of image clutter metric. According to the sensitivity of human visual perception to image structural information, a structural similarity measure between the target and clutter images is firstly established. Previous clutter metrics not considering brain cognitive characteristics, we define an information content weight measure by introducing the widely accepted brain cognitive information extracting model in the field of image quality assessment (IQA), and then, pool the structural similarity measure to be a clutter metric, which can be entitled BSD metric. Comparative field tests show that BSD metric makes a more significant improvement than previously proposed metrics in predicting target acquisition performance including detection probability and search time.

Image fusion quality assessment based on discrete cosine transform and human visual system

With the rapid development of image fusion technology, image fusion quality evaluation plays a very important guiding role in selecting or designing image fusion algorithms. Objective image quality assessment is an interesting research subject in the field of image quality assessment. The ideal objective evaluation method is consistent with human perceptual evaluation. A new fusion image quality assessment method according with human vision system and discrete cosine transform (DCT) is introduced. Firstly, using the Sobel operator to calculate to gradient images for the source images and fused image, the gradient images are divided into 8×8 blocks and calculating the DCT coefficients for each block, and then based on the characteristics of human visual system, calculates the luminance masking, contrast masking to form the perceptual error matrix between input images and fused images. Finally, weighs the perceptual error matrix using the structural similarity. Experiments demonstrate that the new assessment maintains better consistency with human subjective perception.

A New Image Distortion Measure Based on Natural Scene Statistics Modeling

In the field of Image Quality Assessment (IQA), this paper examines a Reduced Reference (RRIQA) measure based on the bi-dimensional empirical mode decomposition. The proposed measure belongs to Natural Scene Statistics (NSS) modeling approaches. First, the reference image is decomposed into Intrinsic Mode Functions (IMF); the authors then use the Generalized Gaussian Density (GGD) to model IMF coefficients distribution. At the receiver side, the same number of IMF is computed on the distorted image, and then the quality assessment is done by fitting error between the IMF coefficients histogram of the distorted image and the GGD estimate of IMF coefficients of the reference image, using the Kullback Leibler Divergence (KLD). In addition, the authors propose a new Support Vector Machine-based classification approach to evaluate the performances of the proposed measure instead of the logistic function-based regression. Experiments were conducted on the LIVE dataset.

A Vector Approach for Image Quality Assessment and Some Metrological Considerations

The main purpose of this paper is to present a metrology-based view of the image quality assessment (IQA) field. Three main topics are developed. First, the state of the art in the field of IQA is presented, providing a classification of some of the most important objective and subjective IQA methods. Then, some aspects of the field are analyzed from a metrological point of view, also through a comparison with the software quality measurement area. In particular, a statistical approach to the evaluation of the uncertainty for IQA objective methods is presented, and the topic of measurement modeling for subjective IQA methods is analyzed. Finally, a vector approach for full-reference IQA is discussed, with applications to images corrupted by impulse and Gaussian noise. For these applications, the vector root mean squared error (VRMSE) and fuzzy VRMSE are introduced. These vector parameters provide a possible way to overcome the main limitations of the mean-squared-error-based IQA methods.