Blind Image Quality Assessment With Active Inference

Using HVS Dual-Pathway and Contrast Sensitivity to Blindly Assess Image Quality

Blind image quality assessment (BIQA) aims to evaluate image quality in a way that closely matches human perception. To achieve this goal, the strengths of deep learning and the characteristics of the human visual system (HVS) can be combined. In this paper, inspired by the ventral pathway and the dorsal pathway of the HVS, a dual-pathway convolutional neural network is proposed for BIQA tasks. The proposed method consists of two pathways: the "what" pathway, which mimics the ventral pathway of the HVS to extract the content features of distorted images, and the "where" pathway, which mimics the dorsal pathway of the HVS to extract the global shape features of distorted images. Then, the features from the two pathways are fused and mapped to an image quality score. Additionally, gradient images weighted by contrast sensitivity are used as the input to the "where" pathway, allowing it to extract global shape features that are more sensitive to human perception. Moreover, a dual-pathway multi-scale feature fusion module is designed to fuse the multi-scale features of the two pathways, enabling the model to capture both global features and local details, thus improving the overall performance of the model. Experiments conducted on six databases show that the proposed method achieves state-of-the-art performance.

Stochastic surprisal: An inferential measurement of free energy in neural networks

This paper conjectures and validates a framework that allows for action during inference in supervised neural networks. Supervised neural networks are constructed with the objective to maximize their performance metric in any given task. This is done by reducing free energy and its associated surprisal during training. However, the bottom-up inference nature of supervised networks is a passive process that renders them fallible to noise. In this paper, we provide a thorough background of supervised neural networks, both generative and discriminative, and discuss their functionality from the perspective of free energy principle. We then provide a framework for introducing action during inference. We introduce a new measurement called stochastic surprisal that is a function of the network, the input, and any possible action. This action can be any one of the outputs that the neural network has learnt, thereby lending stochasticity to the measurement. Stochastic surprisal is validated on two applications: Image Quality Assessment and Recognition under noisy conditions. We show that, while noise characteristics are ignored to make robust recognition, they are analyzed to estimate image quality scores. We apply stochastic surprisal on two applications, three datasets, and as a plug-in on 12 networks. In all, it provides a statistically significant increase among all measures. We conclude by discussing the implications of the proposed stochastic surprisal in other areas of cognitive psychology including expectancy-mismatch and abductive reasoning.

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 achieve 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 through multiscale filtering and extract features to map 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.

Hybrid No-Reference Quality Assessment for Surveillance Images

Intelligent video surveillance (IVS) technology is widely used in various security systems. However, quality degradation in surveillance images (SIs) may affect its performance on vision-based tasks, leading to the difficulties in the IVS system extracting valid information from SIs. In this paper, we propose a hybrid no-reference image quality assessment (NR IQA) model for SIs that can help to identify undesired distortions and provide useful guidelines for IVS technology. Specifically, we first extract two main types of quality-aware features: the low-level visual features related to various distortions, and the high-level semantic information, which is extracted by a state-of-the-art (SOTA) vision transformer backbone. Then, we fuse these two kinds of features into the final quality-aware feature vector, which is mapped into the quality index through the feature regression module. Our experimental results on two surveillance content quality databases demonstrate that the proposed model achieves the best performance compared to the SOTA on NR IQA metrics.

Saliency-Guided Local Full-Reference Image Quality Assessment

Research and development of image quality assessment (IQA) algorithms have been in the focus of the computer vision and image processing community for decades. The intent of IQA methods is to estimate the perceptual quality of digital images correlating as high as possible with human judgements. Full-reference image quality assessment algorithms, which have full access to the distortion-free images, usually contain two phases: local image quality estimation and pooling. Previous works have utilized visual saliency in the final pooling stage. In addition to this, visual saliency was utilized as weights in the weighted averaging of local image quality scores, emphasizing image regions that are salient to human observers. In contrast to this common practice, visual saliency is applied in the computation of local image quality in this study, based on the observation that local image quality is determined both by local image degradation and visual saliency simultaneously. Experimental results on KADID-10k, TID2013, TID2008, and CSIQ have shown that the proposed method was able to improve the state-of-the-art’s performance at low computational costs.

Fine-Grained Image Quality Caption With Hierarchical Semantics Degradation

Blind image quality assessment (BIQA), which is capable of precisely and automatically estimating human perceived image quality with no pristine image for comparison, attracts extensive attention and is of wide applications. Recently, many existing BIQA methods commonly represent image quality with a quantitative value, which is inconsistent with human cognition. Generally, human beings are good at perceiving image quality in terms of semantic description rather than quantitative value. Moreover, cognition is a needs-oriented task where humans are able to extract image contents with local to global semantics as they need. The mediocre quality value represents coarse or holistic image quality and fails to reflect degradation on hierarchical semantics. In this paper, to comply with human cognition, a novel quality caption model is inventively proposed to measure fine-grained image quality with hierarchical semantics degradation. Research on human visual system indicates there are hierarchy and reverse hierarchy correlations between hierarchical semantics. Meanwhile, empirical evidence shows that there are also bi-directional degradation dependencies between them. Thus, a novel bi-directional relationship-based network (BDRNet) is proposed for semantics degradation description, through adaptively exploring those correlations and degradation dependencies in a bi-directional manner. Extensive experiments demonstrate that our method outperforms the state-of-the-arts in terms of both evaluation performance and generalization ability.

Visual Perceptual Quality Assessment Based on Blind Machine Learning Techniques

This paper presents the construction of a new objective method for estimation of visual perceiving quality. The proposal provides an assessment of image quality without the need for a reference image or a specific distortion assumption. Two main processes have been used to build our models: The first one uses deep learning with a convolutional neural network process, without any preprocessing. The second objective visual quality is computed by pooling several image features extracted from different concepts: the natural scene statistic in the spatial domain, the gradient magnitude, the Laplacian of Gaussian, as well as the spectral and spatial entropies. The features extracted from the image file are used as the input of machine learning techniques to build the models that are used to estimate the visual quality level of any image. For the machine learning training phase, two main processes are proposed: The first proposed process consists of a direct learning using all the selected features in only one training phase, named direct learning blind visual quality assessment DLBQA. The second process is an indirect learning and consists of two training phases, named indirect learning blind visual quality assessment ILBQA. This second process includes an additional phase of construction of intermediary metrics used for the construction of the prediction model. The produced models are evaluated on many benchmarks image databases as TID2013, LIVE, and LIVE in the wild image quality challenge. The experimental results demonstrate that the proposed models produce the best visual perception quality prediction, compared to the state-of-the-art models. The proposed models have been implemented on an FPGA platform to demonstrate the feasibility of integrating the proposed solution on an image sensor.

Analysis of Benford’s Law for No-Reference Quality Assessment of Natural, Screen-Content, and Synthetic Images

With the tremendous growth and usage of digital images, no-reference image quality assessment is becoming increasingly important. This paper presents in-depth analysis of Benford’s law inspired first digit distribution feature vectors for no-reference quality assessment of natural, screen-content, and synthetic images in various viewpoints. Benford’s law makes a prediction for the probability distribution of first digits in natural datasets. It has been applied among others for detecting fraudulent income tax returns, detecting scientific fraud, election forensics, and image forensics. In particular, our analysis is based on first digit distributions in multiple domains (wavelet coefficients, DCT coefficients, singular values, etc.) as feature vectors and the extracted features are mapped onto image quality scores. Extensive experiments have been carried out on seven large image quality benchmark databases. It has been demonstrated that first digit distributions are quality-aware features, and it is possible to reach or outperform the state-of-the-art with them.

No-Reference Image Quality Assessment with Multi-Scale Orderless Pooling of Deep Features

The goal of no-reference image quality assessment (NR-IQA) is to evaluate their perceptual quality of digital images without using the distortion-free, pristine counterparts. NR-IQA is an important part of multimedia signal processing since digital images can undergo a wide variety of distortions during storage, compression, and transmission. In this paper, we propose a novel architecture that extracts deep features from the input image at multiple scales to improve the effectiveness of feature extraction for NR-IQA using convolutional neural networks. Specifically, the proposed method extracts deep activations for local patches at multiple scales and maps them onto perceptual quality scores with the help of trained Gaussian process regressors. Extensive experiments demonstrate that the introduced algorithm performs favorably against the state-of-the-art methods on three large benchmark datasets with authentic distortions (LIVE In the Wild, KonIQ-10k, and SPAQ).

Image Quality Assessment without Reference by Combining Deep Learning-Based Features and Viewing Distance

An abundance of objective image quality metrics have been introduced in the literature. One important essential aspect that perceived image quality is dependent on is the viewing distance from the observer to the image. We introduce in this study a novel image quality metric able to estimate the quality of a given image without reference for different viewing distances between the image and the observer. We first select relevant patches from the image using saliency information. For each patch, a feature vector is extracted from a convolutional neural network model and concatenated at the viewing distance, for which the quality is predicted. The resulting vector is fed to fully connected layers to predict subjective scores for the considered viewing distance. The proposed method was evaluated using the Colourlab Image Database: Image Quality and Viewing Distance-changed Image Database. Both databases provide subjective scores at two different viewing distances. In the Colourlab Image Database: Image Quality we obtain a Pearson correlation of 0.87 at both 50 cm and 100 cm viewing distances, while in the Viewing Distance-changed Image Database we obtained a Pearson correlation of 0.93 and 0.94 at viewing distance of four and six times the image height. The results show the efficiency of our method and its generalization ability.