Blind Image Quality Assessment Method Research Articles

G2NPAN: GAN-guided nuance perceptual attention network for multimodal medical fusion image quality assessment.

Multimodal medical fusion images (MMFI) are formed by fusing medical images of two or more modalities with the aim of displaying as much valuable information as possible in a single image. However, due to the different strategies of various fusion algorithms, the quality of the generated fused images is uneven. Thus, an effective blind image quality assessment (BIQA) method is urgently required. The challenge of MMFI quality assessment is to enable the network to perceive the nuances between fused images of different qualities, and the key point for the success of BIQA is the availability of valid reference information. To this end, this work proposes a generative adversarial network (GAN) -guided nuance perceptual attention network (G2NPAN) to implement BIQA for MMFI. Specifically, we achieve the blind evaluation style via the design of a GAN and develop a Unique Feature Warehouse module to learn the effective features of fused images from the pixel level. The redesigned loss function guides the network to perceive the image quality. In the end, the class activation mapping supervised quality assessment network is employed to obtain the MMFI quality score. Extensive experiments and validation have been conducted in a database of medical fusion images, and the proposed method is superior to the state-of-the-art BIQA method.

Blind Image Quality Assessment via Deep Response Feature Decomposition and Aggregation

Image quality is related to image content and distortion information. Most learning-based image quality assessment (IQA) methods extract quality-oriented features with auxiliary tasks like detecting the distortion type and level. However, the perceptual quality degradation caused by the same distortion type and level varies substantially for different content in an image. To deal with this problem, in this paper, we propose a blind IQA method based on Deep Response fEAture decoMposition and aggregation (DREAM), which considers two factors affecting the image quality simultaneously. First, we use a convolutional neural network (CNN) to extract the basic features from the input image. Second, several parallel fully connected (FC) layers are employed to decompose these basic features into response features related to the image content, distortion type, and distortion level. Third, the graph attention network (GAT) is leveraged to aggregate these response features corresponding to the visual quality. Finally, a regression network is used to predict the quality score. The success of our method lies in the feature decomposition to obtain the response features of different content to a specific distortion in the given distorted image and the quality-oriented features obtained by feature aggregation using the internal relation of these response features. Experimental results indicate that our proposed DREAM achieves state-of-the-art (SOTA) performance on both synthetic and authentic distortion IQA datasets.

Data-Efficient Image Quality Assessment with Attention-Panel Decoder

Blind Image Quality Assessment (BIQA) is a fundamental task in computer vision, which however remains unresolved due to the complex distortion conditions and diversified image contents. To confront this challenge, we in this paper propose a novel BIQA pipeline based on the Transformer architecture, which achieves an efficient quality-aware feature representation with much fewer data. More specifically, we consider the traditional fine-tuning in BIQA as an interpretation of the pre-trained model. In this way, we further introduce a Transformer decoder to refine the perceptual information of the CLS token from different perspectives. This enables our model to establish the quality-aware feature manifold efficiently while attaining a strong generalization capability. Meanwhile, inspired by the subjective evaluation behaviors of human, we introduce a novel attention panel mechanism, which improves the model performance and reduces the prediction uncertainty simultaneously. The proposed BIQA method maintains a light-weight design with only one layer of the decoder, yet extensive experiments on eight standard BIQA datasets (both synthetic and authentic) demonstrate its superior performance to the state-of-the-art BIQA methods, i.e., achieving the SRCC values of 0.875 (vs. 0.859 in LIVEC) and 0.980 (vs. 0.969 in LIVE). Checkpoints, logs and code will be available at https://github.com/narthchin/DEIQT.

A dual-stream hybrid model for blind image quality assessment

Blind image quality assessment (BIQA) is a fundamental task in computer vision. Humans can evaluate image quality from local and global aspects without information on reference images. Inspired by this, we propose a BIQA method named DS-IQA by mimicking human visual system (HVS). A dual-stream hybrid module is established to get dual-stream quality-aware features. A CNN branch is used to mimic the active inference process of HVS to extract local quality-aware features. An enhanced Transformer-branch is used to extract global quality-aware features by modeling nonlocal relations of image patches. Finally, a quality evaluator based on Transformer layers is developed to map the dual-stream features and output the final quality score. The proposed approach is evaluated on five databases. The PLCC of DS-IQA reaches 0.975, 0.938, and 0.963 respectively on synthetic databases (LIVE, TID2013, CSIQ), and individual distortion experimental on TID2013 shows that DS-IQA outperforms in 8 of the 24 distortion categories on TID2013. On authentic databases (LIVEC, KonIQ-10k), the PLCC of DS-IQA reaches 0.887, 0.918, experiments show the superiority of the proposed method over other state-of-the-art BIQA metrics.

An End-to-End Blind Image Quality Assessment Method Using a Recurrent Network and Self-Attention

In this paper, we propose a blind image quality assessment (BIQA) method using self-attention and a recurrent neural network (RNN); this approach can effectively capture both local and global information from an input image. The implementation of our constructed deep no-reference (NR) assessment framework does not rely on any convolutional operations. First, the capture step for obtaining locally significant information is performed by a self-attention operation inside a divided window. Second, we design a serialized feature input memory subnetwork to fuse the global features of the image. Finally, all the integrated features are uniformly mapped to the target score. The experimental results obtained on publicly available benchmark IQA databases show that our approach outperforms other state-of-the-art algorithms.

Dual-branch vision transformer for blind image quality assessment

Blind image quality assessment (BIQA) has always been a challenging problem due to the absence of reference images. In this paper, we propose a novel dual-branch vision transformer for BIQA, which simultaneously considers both local distortions and global semantic information. It first extracts dual-scale features from the backbone network, and then each scale feature is fed into one of the transformer encoder branches as a local feature embedding to consider the scale-variant local distortions. Each transformer branch obtains the context of global image distortion as well as the local distortion by adopting content-aware embedding. Finally, the outputs of the dual-branch vision transformer are combined by using multiple feed-forward blocks to predict the image quality scores effectively. Experimental results demonstrate that the proposed BIQA method outperforms the conventional methods on the six public BIQA datasets.

Toward a blind image quality evaluator in the wild by learning beyond human opinion scores

Nowadays, most existing blind image quality assessment (BIQA) models inthewild heavily rely on human ratings, which are extraordinarily labor-expensive to collect. Here, we propose an opinion−free BIQA method that learns from multiple annotators to assess the perceptual quality of images captured in the wild. Specifically, we first synthesize distorted images based on the pristine counterparts. We then randomly assemble a set of image pairs from the synthetic images, and use a group of IQA models to assign pseudo-binary labels for each pair indicating which image has higher quality as the supervisory signal. Based on the newly established pseudo-labeled dataset, we train a deep neural network (DNN)-based BIQA model to rank the perceptual quality, optimized for consistency with the binary rank labels. Since there exists domain shift, e.g., distortion shift and content shift, between the synthetic and in-the-wild images, we leverage two ways to alleviate this issue. First, the simulated distortions should be similar to authentic distortions as much as possible. Second, an unsupervised domain adaptation (UDA) module is further applied to encourage learning domain-invariant features between two domains. Extensive experiments demonstrate the effectiveness of our proposed opinion−free BIQA model, yielding SOTA performance in terms of correlation with human opinion scores, as well as gMAD competition. Our code is available at: https://github.com/wangzhihua520/OF_BIQA.

A Multiscale Approach to Deep Blind Image Quality Assessment.

Faithful measurement of perceptual quality is of significant importance to various multimedia applications. By fully utilizing reference images, full-reference image quality assessment (FR-IQA) methods usually achieves better prediction performance. On the other hand, no-reference image quality assessment (NR-IQA), also known as blind image quality assessment (BIQA), which does not consider the reference image, makes it a challenging but important task. Previous NR-IQA methods have focused on spatial measures at the expense of information in the available frequency bands. In this paper, we present a multiscale deep blind image quality assessment method (BIQA, M.D.) with spatial optimal-scale filtering analysis. Motivated by the multi-channel behavior of the human visual system and contrast sensitivity function, we decompose an image into a number of spatial frequency bands by multiscale filtering and extract features for mapping an image to its subjective quality score by applying convolutional neural network. Experimental results show that BIQA, M.D. compares well with existing NR-IQA methods and generalizes well across datasets.

CSPP-IQA: a multi-scale spatial pyramid pooling-based approach for blind image quality assessment.

The traditional image quality assessment (IQA) methods are usually based on convolutional neural networks (CNNs). For these IQA methods using CNNs, limited by the feature size of the fully connected layer, the input image needs be tailored to a pre-defined size, which usually results in destroying the original structure and content of the input image and thus reduces the accuracy of the quality assessment. In this paper, a blind image quality assessment method (named CSPP-IQA), which is based on multi-scale spatial pyramid pooling, is proposed. CSPP-IQA allows inputting the original image when assessing the image quality without any image adjustment. Moreover, by facilitating the convolutional block attention module and image understanding module, CSPP-IQA achieved better accuracy, generalization and efficiency than traditional IQA methods. The result of experiments running on real-scene IQA datasets in this study verified the effectiveness and efficiency of CSPP-IQA.

Unsupervised blind image quality assessment based on joint structure and natural scene statistics features

Compared with the widely used supervised blind image quality assessment (BIQA) models, unsupervised BIQA models require little prior knowledge for calculating the objective quality scores of distorted images. In this paper, we propose an unsupervised BIQA method that aims to achieve both good performance and generalization capability with low computational complexity. Carefully selected and extensive structure and natural scene statistics (NSS) features can better represent image quality. First, we employ phase congruency (PC) and finely selected gradient magnitude map and Laplacian of Gaussian response (GM-LOG) features to represent image structure information. Second, we calculate the local mean-subtracted and contrast-normalized (MSCN) coefficients and the Karhunen–Loéve transform (KLT) coefficients to represent the naturalness of the distorted images. Last, multivariate Gaussian (MVG) model with joint features extracted from both the pristine images and the distorted images is adopted to calculate the objective image quality. Extensive experiments conducted on nine IQA databases demonstrate that the proposed method achieves better performance than the state-of-the-art BIQA methods.

Blind image quality assessment based on progressive multi-task learning

Due to the lack of adequate training data and sufficient mining of prior knowledge related to perceived quality, most existing image quality assessment (IQA) methods show limited generalization performance. In this paper, we study the prior knowledge from the factors affecting perceived quality, and introduce a novel progressive multi-task learning based blind IQA method. Inspired by the definition of IQA: human comprehensive perception for degradation of image content, we firstly deconstruct IQA into three elements, i.e., image content, pattern of degradation, and intensity of degradation. Based on these elements, we design the corresponding auxiliary tasks for instructing the network to learn IQA. By statistical analysis on a great deal of data, we find that there is progressive relevance among the four tasks. Furthermore, we mathematically derive that introducing the progressive relevance into a multi-task learning network can effectively constrain the hypothesis space of the main task. Under the guidance of the derivation, we propose an end-to-end IQA framework based on progressive multi-task learning. Experimental results demonstrate the excellent generalization capability of the proposed method, which achieves state-of-the-art performance against these existing IQA methods.

Blind Image Quality Assessment of Screen Content Images via Fisher Vector Coding

This paper presents an effective blind image quality assessment (BIQA) method for screen content images (SCIs) based on Fisher vector encoding, with the hypothesis that local statistics will be altered with the change of distortions, and can be characterized by the fusion of statistical models and direction vectors. Firstly, a specific Gaussian mixture model (GMM) is generated from a corpus of pristine SCIs to simulate the local distribution of SCIs in spatial domain. Then, discriminative features are generated to characterize the quality of test image with Fisher vector coding and generated GMM. Finally, support vector regression is adopted to learn the mapping between discriminative features and subjective opinion scores. To validate the performance of our method, extensive experiments are conducted on three public SCI databases and the results well confirm its superiority over the existing relevant BIQA method of SCIs.

GMANet: Gradient Mask Attention Network for Finding Clearest Human Fecal Microscopic Image in Autofocus Process

The intelligent recognition of formed elements in microscopic images is a research hotspot. Whether the microscopic image is clear or blurred is the key factor affecting the recognition accuracy. Microscopic images of human feces contain numerous items, such as undigested food, epithelium, bacteria and other formed elements, leading to a complex image composition. Consequently, traditional image quality assessment (IQA) methods cannot accurately assess the quality of fecal microscopic images or even identify the clearest image in the autofocus process. In response to this difficulty, we propose a blind IQA method based on a deep convolutional neural network (CNN), namely GMANet. The gradient information of the microscopic image is introduced into a low-level convolutional layer of the CNN as a mask attention mechanism to force high-level features to pay more attention to sharp regions. Experimental results show that the proposed network has good consistency with human visual properties and can accurately identify the clearest microscopic image in the autofocus process. Our proposed model, trained on fecal microscopic images, can be directly applied to the autofocus process of leucorrhea and blood samples without additional transfer learning. Our study is valuable for the autofocus task of microscopic images with complex compositions.

Blind quality assessment of night-time image

High-quality night-time imaging is crucial to video surveillance, automatic drive and consumer electronics. However, different from day-time imaging, night-time imaging suffers from some disadvantages, such as low light, uneven illumination, difficult focusing, etc., which raises a great concern to the night-time imaging quality. Accordingly, a practical night-time image quality evaluation method is very promising to control and improve the night-time imaging system. Toward this end, in this paper, we propose a blind image quality assessment (BIQA) method to quantify the night-time image quality. Specifically, in the proposed method, we measure the night-time image quality by investigating the fundamental image properties, which are highly relevant to the image quality, such as the brightness, saturation, sharpness, noiseness, contrast and the semantics. Specific features are designed to characterize the image properties properly. Then we employ the support vector regression (SVR) method to infer the image quality with the extracted quality-aware features. The proposed BIQA method for night-time images is thoroughly evaluated on a representative night-time image database. Experimental results demonstrate that the proposed BIQA method for night-time images achieves superior prediction performance to other state-of-the-art BIQA methods.

Blind quality assessment for multiply distorted stereoscopic images towards IoT-based 3D capture systems

Empowered by 5G mobile communication networks, multimedia processing has been considered as a very promising application of Internet-of-Things (IoT). Stereoscopic image quality assessment (SIQA), as an important part of 3D capture system, can be embedded in the cloud or fog servers to automatically monitor the perceptual quality of the collected stereoscopic images. In this paper, a novel blind image quality assessment method towards IoT-based 3D capture systems is developed for multiply-distorted stereoscopic images (MDSIs), in which five complementary channels, including left view, right view, cyclopean map, summation map and difference map, are jointly considered in dictionary learning for characterizing the monocular receptive field (MRF) and binocular receptive field (BRF) properties of the visual cortex in response to MDSIs. Additionally, the high order statistics scheme is adopted by utilizing the statistical differences between the codebook and images to ensure the stable and robust quality prediction performance for MDSIs. The proposed method shows competitive prediction performances on four benchmark databases compared with the existing SIQA metrics.

No-Reference Image Quality Assessment Based on Multi-Order Gradients Statistics

Abstract A new blind image quality assessment method called No-Reference Image Quality Assessment Based on Multi-Order Gradients Statistics is proposed, which is aimed at solving the problem that the existing no-reference image quality assessment methods cannot determine the type of image distortion and that the quality evaluation has poor robustness for different types of distortion. In this article, an 18-dimensional image feature vector is constructed from gradient magnitude features, relative gradient orientation features, and relative gradient magnitude features over two scales and three orders on the basis of the relationship between multi-order gradient statistics and the type and degree of image distortion. The feature matrix and distortion types of known distorted images are used to train an AdaBoost_BP neural network to determine the image distortion type; the feature matrix and subjective scores of known distorted images are used to train an AdaBoost_BP neural network to determine the image distortion degree. A series of comparative experiments were carried out using Laboratory of Image and Video Engineering (LIVE), LIVE Multiply Distorted Image Quality, Tampere Image, and Optics Remote Sensing Image databases. Experimental results show that the proposed method has high distortion type judgment accuracy and that the quality score shows good subjective consistency and robustness for all types of distortion. The performance of the proposed method is not constricted to a particular database, and the proposed method has high operational efficiency.

Unsupervised Blind Image Quality Evaluation via Statistical Measurements of Structure, Naturalness, and Perception

Most existing blind image quality assessment (BIQA) methods belong to supervised methods, which always need a large number of image samples and expensive subjective scores for training a quality prediction model. In this paper, we focus our attention on the unsupervised BIQA methods and put forward a novel unsupervised approach. The main idea of our method is to quantify the image quality degradation through measuring the structure, naturalness, and the perception quality variations of the distorted image from the pristine natural images. In specific, the structure variation is captured by the deviations of the image phase congruency and gradients distributions. The naturalness variation is characterized through the distributions variations of the locally mean subtracted and contrast normalized (MSCN) coefficients and the products of pairs of the adjacent MSCN coefficients. Compared with existing unsupervised methods, we initiatively introduce the perception quality measurement into the construction of unsupervised BIQA method, which is conducted by characterizing the prediction discrepancy between the image and its brain prediction based on the free-energy principle in the newly revealed brain theory. After feature extraction, we learn a pristine multivariate Gaussian (MVG) model with the extracted features from a set of pristine natural images. The quality of a new image is finally defined as the distance between its MVG model and the learned pristine MVG model. The extensive experiments conducted on LIVE, TID2013, CSIQ, Toyama, CID2013, and the Waterloo Exploration databases demonstrate that the proposed method achieves comparative prediction performance with the state-of-the-art BIQA methods.

Blind Image Quality Assessment With Joint Entropy Degradation

Blind image quality assessment (BIQA) aims to evaluate the quality of an image without pristine image objectively, which is highly desired in many perception-oriented image processing systems. Distortions degrade the visual contents and cause image quality degradation. Moreover, the visual contents of an image suffer from individual degradations by different types and different levels of distortions, which makes us difficult to analyze the quality degradation. From the perspective of information theory, there is a decrease in the amount of the visual contents when images are distorted. Therefore, in this paper, the image quality is assessed through its visual entropy degradation. Researches on the neuroscience indicate that the simple cells in the local receptive field can be characterized as being spatially localized and oriented, then the local intensity, gradient, and orientation features are extracted to represent the visual contents of an image. By deducing the joint entropy equation, the joint entropy is related to the statistical distributions. Next, in order to measure the visual entropy, the joint statistical distributions of those features are calculated. Finally, by measuring the degradations on these distributions of distorted images, a novel BIQA method is proposed. The experimental results on the databases of LIVE, CSIQ, and TID2013 show that the proposed method has superior performance than other state-of-the-art BIQA methods.

Blind image quality assessment with hierarchy: Degradation from local structure to deep semantics

Though blind image quality assessment (BIQA) is highly desired in perceptual-oriented image processing systems, it is extremely difficult to design a reliable BIQA method. With the help of the prior knowledge, the human visual system (HVS) hierarchically perceives the quality degradation during the visual recognition. Inspired by this, we suggest different levels of distortion generate individual degradations on hierarchical features, and propose to consider the degradations on both low and high level features for quality prediction. By mimicking the orientation selectivity (OS) mechanism in the primary visual cortex, an OS based local structure is designed for low-level visual information representation. At the meantime, the deep residual network, which possesses multiple levels for feature integration, is employed to extract the deep semantics for high-level visual content representation. By fusing the local structure and the deep semantics, a hierarchical feature set is acquired. Next, the correlations between the degradations of image qualities and their corresponding hierarchical feature sets are analyzed, and a novel hierarchical feature degradation (HFD) based BIQA (HFD-BIQA) method is built. Experimental results on the legacy and wild image quality assessment databases demonstrate the prediction accuracy of the proposed HFD-BIQA method, and verify that the HFD-BIQA performs highly consistent with the subjective perception.

Blind image quality assessment based on joint log-contrast statistics

During recent years, quality-aware features extracted from natural scene statistics (NSS) models have been used in development of blind image quality assessment (BIQA) algorithms. Generally, the univariate distributions of bandpass coefficients are used to fit a parametric probabilistic model and the model parameters serve as the quality-aware features. However, the inter-location, inter-direction and inter-scale correlations of natural images cannot be well exploited by such NSS models, as it is hard to capture such dependencies using univariate marginal distributions. In this paper, we build a novel NSS model of joint log-contrast distribution to take into account the across space and direction correlations of natural images (inter-scale correlation to be explored as the next step). Furthermore, we provide a new efficient approach to extract quality-aware features as the gradient of log-likelihood on the NSS model, instead of using model parameters directly. Finally, we develop an effective joint-NSS model based BIQA metric called BJLC (BIQA based on joint log-contrast statistics). Extensive experiments on four public large-scale image databases have validated that objective quality scores predicted by the proposed BIQA method are in higher accordance with subjective ratings generated by human observers compared with existing methods.