Evaluating Convolutional Neural Networks for No -Reference Image Quality Assessment

An optimized CNN-based quality assessment model for screen content image

No-reference image quality assessment in contourlet domain

We present a no-reference (NR) image quality assessment (IQA) algorithm that is inspired by the representation of visual scenes in the primary visual cortex of the human visual system. Specifically, we use the sparse coding model of the area V1 to construct an overcomplete dictionary for sparsely representing pristine (undistorted) natural images. First, we empirically demonstrate that the distribution of the sparse representation coefficients of natural images have sharp peaks and heavy tails, and can therefore be modeled using a Univariate Generalized Gaussian Distribution (UGGD). We then show that the UGGD model parameters form good features for distortion estimation and formulate our no-reference IQA algorithm based on this observation. Subsequently, we find UGGD model parameters that are representative of the class of pristine natural images. This is achieved using a training set of undistorted natural images. The perceptual quality of a test image is then defined to be the likelihood of its sparse coefficients being generated from the pristine UGGD model. We show that the proposed algorithm correlates well with subjective evaluation over several standard image databases. Further, the proposed method allows us to construct a distortion map that has several useful applications like distortion localization, adaptive rate allocation etc. Finally and importantly, the proposed NR-IQA algorithm does not make use of any distortion information or subjective scores during the training process.

Low-dose Computed Tomography (CT) imaging minimizes radiation exposure but often results in degraded image quality, making diagnosis challenging. Image Quality Assessment (IQA) is a process of quantitatively evaluating the visual quality of images and plays a crucial role in determining whether these CT scans meet the necessary standards for accurate diagnosis. IQA methods help identify issues such as noise, blurriness, or artifacts that may compromise the diagnostic value of the scans. Traditional quality assessment measures how closely an image matches an ideal or reference image. Since obtaining a high-quality reference image is often challenging, an automated quality assessment framework (diagnosis based IQA) using No-Reference Image Quality Assessment (NRIQA) techniques is proposed, allowing quality evaluation and eliminating the need for a high-quality reference image. In this approach, various statistical and structural features are extracted from low-dose CT scans and mapped to radiologist-assigned quality scores, which are subjective evaluations given by experts to train and compare various predictive models. The framework undergoes 100-fold validation, to ensure the reliability of the proposed model. CT images with predicted quality scores of 2 and below undergo spatial domain enhancement to improve their diagnostic value. These enhanced images are then reassessed using the diagnosis based IQA (trained Support Vector Regression) model, demonstrating an improvement in predicted quality scores. In addition, the enhanced images were verified by a radiologist, confirming the effectiveness of the enhancement process. This two-stage approach, automated NRIQA-based quality prediction and selective enhancement provides a reliable, and objective method for assessing and improving low-dose CT image quality.

Image Quality Assessment (IQA) is essential for the accuracy of systems for automatic recognition of tree species for wood samples. In this study, a No-Reference IQA (NR-IQA), wood NR-IQA (WNR-IQA) metric was proposed to assess the quality of wood images. Support Vector Regression (SVR) was trained using Generalized Gaussian Distribution (GGD) and Asymmetric Generalized Gaussian Distribution (AGGD) features, which were measured for wood images. Meanwhile, the Mean Opinion Score (MOS) was obtained from the subjective evaluation. This was followed by a comparison between the proposed IQA metric, WNR-IQA, and three established NR-IQA metrics, namely Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), deepIQA, Deep Bilinear Convolutional Neural Networks (DB-CNN), and five Full Reference-IQA (FR-IQA) metrics known as MSSIM, SSIM, FSIM, IWSSIM, and GMSD. The proposed WNR-IQA metric, BRISQUE, deepIQA, DB-CNN, and FR-IQAs were then compared with MOS values to evaluate the performance of the automatic IQA metrics. As a result, the WNR-IQA metric exhibited a higher performance compared to BRISQUE, deepIQA, DB-CNN, and FR-IQA metrics. Highest quality images may not be routinely available due to logistic factors, such as dust, poor illumination, and hot environment present in the timber industry. Moreover, motion blur could occur due to the relative motion between the camera and the wood slice. Therefore, the advantage of WNR-IQA could be seen from its independency from a “perfect” reference image for the image quality evaluation.

BackgroundMore than 79.2 million confirmed COVID-19 cases and 1.7 million deaths were caused by SARS-CoV-2; the disease was named COVID-19 by the World Health Organization. Control of the COVID-19 epidemic has become a crucial issue around the globe, but there are limited studies that investigate the global trend of the COVID-19 pandemic together with each country’s policy measures.ObjectiveWe aimed to develop an online artificial intelligence (AI) system to analyze the dynamic trend of the COVID-19 pandemic, facilitate forecasting and predictive modeling, and produce a heat map visualization of policy measures in 171 countries.MethodsThe COVID-19 Pandemic AI System (CPAIS) integrated two data sets: the data set from the Oxford COVID-19 Government Response Tracker from the Blavatnik School of Government, which is maintained by the University of Oxford, and the data set from the COVID-19 Data Repository, which was established by the Johns Hopkins University Center for Systems Science and Engineering. This study utilized four statistical and deep learning techniques for forecasting: autoregressive integrated moving average (ARIMA), feedforward neural network (FNN), multilayer perceptron (MLP) neural network, and long short-term memory (LSTM). With regard to 1-year records (ie, whole time series data), records from the last 14 days served as the validation set to evaluate the performance of the forecast, whereas earlier records served as the training set.ResultsA total of 171 countries that featured in both databases were included in the online system. The CPAIS was developed to explore variations, trends, and forecasts related to the COVID-19 pandemic across several counties. For instance, the number of confirmed monthly cases in the United States reached a local peak in July 2020 and another peak of 6,368,591 in December 2020. A dynamic heat map with policy measures depicts changes in COVID-19 measures for each country. A total of 19 measures were embedded within the three sections presented on the website, and only 4 of the 19 measures were continuous measures related to financial support or investment. Deep learning models were used to enable COVID-19 forecasting; the performances of ARIMA, FNN, and the MLP neural network were not stable because their forecast accuracy was only better than LSTM for a few countries. LSTM demonstrated the best forecast accuracy for Canada, as the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) were 2272.551, 1501.248, and 0.2723075, respectively. ARIMA (RMSE=317.53169; MAPE=0.4641688) and FNN (RMSE=181.29894; MAPE=0.2708482) demonstrated better performance for South Korea.ConclusionsThe CPAIS collects and summarizes information about the COVID-19 pandemic and offers data visualization and deep learning–based prediction. It might be a useful reference for predicting a serious outbreak or epidemic. Moreover, the system undergoes daily updates and includes the latest information on vaccination, which may change the dynamics of the pandemic.

No-reference image quality assessment based on spatial and spectral entropies

Blind quality assessment for screen content images by combining local and global features

Measuring visual quality, as perceived by human observers, is becoming increasingly important in many applications where humans are the ultimate consumers of visual information. Significant progress has been made for assessing the subjective quality of natural images, such as those taken by optical cameras. Natural Scene Statistics (NSS) is an important tool for no-reference visual quality assessment of natural images, where the reference image is not needed for comparison. In this paper, we take an important step towards using NSS to automate visual quality assessment of photorealistic synthetic scenes typically found in video games and animated movies. Our primary contributions are (1) conducting subjective tests on our publicly available ESPL Synthetic Image Database containing 500 distorted images (20 distorted images for each of the 25 original images) in 1920 × 1080 format, and (2) evaluating the performance of 17 no-reference image quality assessment (IQA) algorithms using synthetic scene statistics. We find that similar to natural scenes, synthetic scene statistics can be successfully used for IQA and certain statistical features are good for certain image distortions.

This study investigates data standardization methods based on the grid search (GS) algorithm for energy load forecasting, including zero-mean, min-max, max, decimal, sigmoid, softmax, median, and robust, to determine the hyperparameters of deep learning (DL) models. The considered DL models are the convolutional neural network (CNN) and long short-term memory network (LSTMN). The procedure is made over (i) setting the configuration for CNN and LSTMN, (ii) establishing the hyperparameter values of CNN and LSTMN models based on epoch, batch, optimizer, dropout, filters, and kernel, (iii) using eight data standardization methods to standardize the input data, and (iv) using the GS algorithm to search the optimal hyperparameters based on the mean absolute error (MAE) and mean absolute percent error (MAPE) indexes. The effectiveness of the proposed method is verified on the power load data of the Australian state of Queensland and Vietnamese Ho Chi Minh city. The simulation results show that the proposed data standardization methods are appropriate, except for the zero-mean and min-max methods.

With the rapid development of deep learning, no-reference image quality assessment (NR-IQA) based on convolutional neural network (CNN) plays an important role in image processing. Currently, most CNN-based NR-IQA methods focus primarily on the global features of images while ignoring detail-rich local features and channel dependencies. In fact, there are subtle differences in detail between distorted and reference images, as well as differences in the contribution of different channels to IQA. Furthermore, multi-scale feature extraction can be used to fuse the detailed information from images with different resolutions, and the combination of global and local features is critical in extracting image features. As a result, in this paper, a multi-scale residual CNN with an attention mechanism (MsRCANet) is proposed for NR-IQA. Specifically, a multi-scale residual block is first used to extract features from distorted images. Then, the residual learning with active weighted mapping strategy and channel attention mechanism is used to further process image features to obtain more abundant information. Finally, the fusion strategy and full connection layer are used to evaluate image quality. The experimental results on four synthetic databases and three in-the-wild IQA databases, as well as cross-database validation results, show that the proposed method has good generalization ability and can be compared with the most advanced methods.

Research in many fields has shown that transfer learning (TL) is well-suited to improve the performance of deep learning (DL) models in datasets with small numbers of samples. This empirical success has triggered interest in the application of TL to cognitive decoding analyses with functional neuroimaging data. Here, we systematically evaluate TL for the application of DL models to the decoding of cognitive states (e.g., viewing images of faces or houses) from whole-brain functional Magnetic Resonance Imaging (fMRI) data. We first pre-train two DL architectures on a large, public fMRI dataset and subsequently evaluate their performance in an independent experimental task and a fully independent dataset. The pre-trained DL models consistently achieve higher decoding accuracies and generally require less training time and data than model variants that were not pre-trained, while also outperforming linear baseline models trained from scratch, clearly underlining the benefits of pre-training. We demonstrate that these benefits arise from the ability of the pre-trained models to reuse many of their learned features when training with new data, providing deeper insights into the mechanisms giving rise to the benefits of pre-training. Yet, we also surface nuanced challenges for whole-brain cognitive decoding with DL models when interpreting the decoding decisions of the pre-trained models, as these have learned to utilize the fMRI data in unforeseen and counterintuitive ways to identify individual cognitive states.

The direct use of a deep convolutional neural network (CNN) in no-reference image quality assessment (NR-IQA) usually struggles for a good performance due to a lack of training data, which can be alleviated by transfer learning. However, depending on the similarity between the source and target tasks, the final performance differs vastly. In particular, various kinds of distortion types exist in IQA, which requires different kinds of features to predict visual quality. In this paper, to make the transferred model robust to various distortion types, we propose a Multiple-level Feature-based Image Quality Assessor (MFIQA) which considers multiple levels of features simultaneously. Through rigorous experiments, we prove that MFIQA consistently yields state-of-the-art performance regardless of the distortion types including synthetic and authentic corruption.

The last decade has witnessed great advances in digital images. These images are subjected to many processing stages during storing, transmitting, or sharing over a network connection. Unfortunately, these processing stages could potentially add visual degradation to original image. These degradations reduce the perceived visual quality which leads to an unsatisfactory experience for human viewers. Therefore, image quality assessment (IQA) has become a topic of high interest and intense research over the last decade. This study mainly focuses on the most challenging category of IQA general-purpose No-Reference Image Quality Assessment (NR-IQA), where the goal is to assess the quality of images without information about the reference images and without prior knowledge about the types of distortions in the tested image. A novel NR-IQA approach is presented, by utilizing multiple deep belief networks (DBNs) with multiple regression models. It consists of four DBNs. Each DBN is associated with one type of distortion. The authors have evaluated the performance of the proposed and some existing models on a fair basis. The obtained results show that their model gives better results and yield a significant improvement.

In recent years, deep learning has achieved significant progress in many respects. However, unlike other research fields with millions of labeled data such as image recognition, only several thousand labeled images are available in image quality assessment (IQA) field for deep learning, which heavily hinders the development and application for IQA. To tackle this problem, in this paper, we proposed an error self-learning semi-supervised method for no-reference (NR) IQA (ESSIQA), which is based on deep learning. We employed an advanced full reference (FR) IQA method to expand databases and supervise the training of network. In addition, the network outputs of expanding images were used as proxy labels replacing errors between subjective scores and objective scores to achieve error self-learning. Two weights of error back propagation were designed to reduce the impact of inaccurate outputs. The experimental results show that the proposed method yielded comparative effect.