Quality Assessment Metrics Research Articles

Влияние проблемы многозначности меток классов системных журналов на защищенность компьютерных сетей

The security of information circulating in a computer network is related to the security of the supporting infrastructure. An important problem in the intelligent processing of syslog data is the existence of multi-label datasets. Among the Russian-language scientific publications, the problem under consideration in the context of information security of computer networks is not presented. Purpose: increase the security of computer networks by using multi-label learning methods when solving the problem of classifying system logs class labels. Results: A comparative analysis of single-valued and multi-label classifiers was carried out in a computational experiment on the Mean accuracy metric. A non-linear relationship was found between the proportion of experimental data sections containing multi-label class labels and the overall accuracy of data classification. Despite the fact that multilabel plots in the studied experimental data are only 3%, the gain in accuracy reaches 23% according to the specified metric. According to the results of the analysis, 80% of unambiguous classifiers were inferior in classification accuracy according to the Mean accuracy multi-label metric to their analogues, which may signal a strong influence of multi-label class labels on the models under consideration. It is shown that the considered structure of experimental data in a tabular form is affected by the multi-label problem much more strongly than it can be estimated by a standard frequency check, which actualizes further research in this direction. Practical relevance: The practical significance of the results obtained lies in increasing the security of computer networks through the use of a multi-label approach in the classification problem. The tasks of information security solved by multi-label classification may include: the area of monitoring, detection or prevention of violations and computer attacks in computer networks. Discussion: Since the predictive power of frequency testing of the influence of multi-label class label results on the classification results of unambiguous classifiers is low, further research on this topic is planned. It is planned to expand the list of classification quality assessment metrics in future experiments.

Spectrum Similarity-Based Quality Assessment Metric

Spectrum Similarity-Based Quality Assessment Metric

Predicting visual difference maps for computer‐generated images by integrating human visual system model and deep learning

The quality of images generated by computer graphics rendering algorithms is mainly affected by visible distortion at some pixel locations. Image quality assessment (IQA) metrics are commonly utilized to assess the quality of rendered images, but their results are a global difference value, which does not provide pixel-wise differences to optimize the renderings. In contrast, visibility difference models including visual perception models and deep learning models can calculate pixel-wise visibility difference between distorted images and reference images. However, they either are only applied to a single type of visible distortion or are seriously dependent on datasets. To this end, the authors propose a novel model, dubbed Human Visual Perception and Deep Learning Image Difference Metric (HPDL-IDM), which combines the Human Visual System (HVS) model and deep learning. HPDL-IDM primarily consists of two modules: (i) the visual perception feature calculation module, which calculates difference maps between various kinds of features extracted from the reference image and the distorted image according to the visual characteristics of human eyes and concatenates them, and (ii) the deep learning module, which utilizes a neural network of encoder–decoder structure to train on the LocvisVC and VisTexRes datasets whose input and output are these concatenated feature difference maps and the final image distortion visibility difference map respectively. Additionally, the authors pool the final difference map into a global difference value between 0 and 1 to apply their model to many image processing tasks related to Image quality metrics (IQMs). Experimental results show that HPDL-IDM's generalization capacity and accuracy are improved by a large margin compared to other models.

Nonintrusive Perceptual Audio Quality Assessment for User-Generated Content Using Deep Learning

With the boom of social media communication, teleconferencing, and online classes, audiovisual communication over bandwidth strained networks has become an integral part of our lives. Consequently, the growing demand for the quality of experience necessitates developing algorithms to measure and enrich user experience. Prior studies have mainly focused on assessing speech quality and intelligibility with reference to audio quality assessment, while other categories in user-generated multimedia (UGM) are less explored. Moreover, frequency-domain properties of speech and UGM audio are significantly different from each other. Furthermore, there is a lack of a standard dataset for the quality assessment of UGM. Considering these limitations, in this article, we first develop the IIT-JMU-UGM audio dataset consisting of 1150 audio clips, with diverse context, content, and types of degradation commonly observed in real-world scenarios and annotated with the subjective quality scores. Finally, we propose a non-intrusive audio quality assessment metric using a stacked gated-recurrent-unit-based deep learning framework. The proposed model outperforms several baseline methods, including state-of-the-art non-intrusive and intrusive approaches. The resulting Pearson’s correlation coefficient of 0.834 indicates that the proposed method efficiently mirrors human auditory perception.

Hand-drawn face sketch recognition using rank-level fusion of image quality assessment metrics

Hand-drawn face sketch recognition using rank-level fusion of image quality assessment metrics

Non-intrusive speech quality assessment using context-aware neural networks

To meet the human perceived quality of experience (QoE) while communicating over various Voice over Internet protocol (VoIP) applications, for example Google Meet, Microsoft Skype, Apple FaceTime, etc. a precise speech quality assessment metric is needed. The metric should be able to detect and segregate different types of noise degradations present in the surroundings before measuring and monitoring the quality of speech in real-time. Our research is motivated by the lack of clear evidence presenting speech quality metric that can firstly distinguish different types of noise degradations before providing speech quality prediction decision. To that end, this paper presents a novel non-intrusive speech quality assessment metric using context-aware neural networks in which the noise class (context) of the degraded or noisy speech signal is first identified using a classifier then deep neutral networks (DNNs) based speech quality metrics (SQMs) are trained and optimized for each noise class to obtain the noise class-specific (context-specific) optimized speech quality predictions (MOS scores). The noisy speech signals, that is, clean speech signals degraded by different types of background noises are taken from the NOIZEUS speech corpus. Results demonstrate that even in the presence of less number of speech samples available from the NOIZEUS speech corpus, the proposed metric outperforms in different contexts compared to the metric where the contexts are not classified before speech quality prediction.

A Novel Image Focus Metric based on Power of Companion Matrix and Gerschgorin Circle Bound

ABSTRACT In this paper, a simple and efficient no-reference image quality assessment metric is proposed. It is based on the concept of polynomial coefficients, power of companion matrix, and Gerschgorin circles bound. The polynomial coefficient-based companion matrix captures the main features and dynamics of an image. Moreover, the Gerschgorin circles bound is used to define the focus metric. The proposed focus metric is tested on various real as well as synthetic image data sets. It is observed that the presented metric is unimodal to noise and invariant to the contrast changes that occur due to the variation in illumination effect. Moreover, it is robust under the varying salt-and-pepper and Gaussian noise. The performance of the proposed focus metric is also compared with the various existing focus metrics.

Virtual labeling of mitochondria in living cells using correlative imaging and physics-guided deep learning.

Mitochondria play a crucial role in cellular metabolism. This paper presents a novel method to visualize mitochondria in living cells without the use of fluorescent markers. We propose a physics-guided deep learning approach for obtaining virtually labeled micrographs of mitochondria from bright-field images. We integrate a microscope's point spread function in the learning of an adversarial neural network for improving virtual labeling. We show results (average Pearson correlation 0.86) significantly better than what was achieved by state-of-the-art (0.71) for virtual labeling of mitochondria. We also provide new insights into the virtual labeling problem and suggest additional metrics for quality assessment. The results show that our virtual labeling approach is a powerful way of segmenting and tracking individual mitochondria in bright-field images, results previously achievable only for fluorescently labeled mitochondria.

NNCD-IQA: A new neural networks based compressed database for image quality assessment

Objective and subjective quality assessment is still a challenging problem in various image processing tasks. For instance, in the context of image compression, most of the conducted studies have focused on image datasets encoded using standard algorithms such as JPEG and JPEG2000. In this paper, we propose to further investigate the quality assessment issue in the presence of neural networks-based compressed images. More precisely, a new database of compressed images has been firstly built using JPEG2000 standard as well as four recent neural networks based coding schemes. Then, subjective experiments are performed to obtain the mean opinion scores of the generated distorted images. Finally, an extensive evaluation and analysis of objective image quality assessment metrics is achieved. For instance, in addition to conventional and machine learning metrics, we have considered different deep learning based models, which have been trained on our database. The new subjective database with its associated mean opinion scores as well as the learned models are publicly available at https://github.com/zakopz/NNCD-IQA-Database . The obtained results show the interest of deep learning based metrics in the context of neural networks-based compressed images.

Multiple Degradation Skilled Network for Infrared and Visible Image Fusion Based on Multi-Resolution SVD Updation

Existing infrared (IR)-visible (VIS) image fusion algorithms demand source images with the same resolution levels. However, IR images are always available with poor resolution due to hardware limitations and environmental conditions. In this correspondence, we develop a novel image fusion model that brings resolution consistency between IR-VIS source images and generates an accurate high-resolution fused image. We train a single deep convolutional neural network model by considering true degradations in real time and reconstruct IR images. The trained multiple degradation skilled network (MDSNet) increases the prominence of objects in fused images from the IR source image. In addition, we adopt multi-resolution singular value decomposition (MRSVD) to capture maximum information from source images and update IR image coefficients with that of VIS images at the finest level. This ensures uniform contrast along with clear textural information in our results. Experiments demonstrate the efficiency of the proposed method over nine state-of-the-art methods using five image quality assessment metrics.

A Reliable Image Quality Assessment Metric: Evaluation Using Camera Impacts

A Reliable Image Quality Assessment Metric: Evaluation Using Camera Impacts

IMAGE ENHANCEMENT AND DE-NOISING TECHNIQUES OF MAGNETIC RESONANCE IMAGES

Medical images have noise, such as salt and pepper, speckle, and gaussian noise. So, getting the accuracy of magnetic resonance images is challenging always. The accuracy of brain images is essential for the clinical diagnosis process. The nonlinear method of median and morphological filters is used for enhancement, contrast adjustment, and histogram equalization for medical images and speech processing, to preserve them from noise and edge features. Because of its edge-preserving properties, this median spatial filter window is critically important and better for removing impulsive noise and speckle noise. Nine different shapes of windows and five different sizes of windows and five noise density injections are used for evaluating the performance of the median filter. The first person J.W.Tukey, did the smoothing process by median rank selection filter. The denoising using morphological process is also considered for analysis. These two nonlinear methods like median filtering and morphological methods are used for the restoration of noise from the original image. These two methods are applied in normal and seizure-affected images to calculate quality assessment metrics and also the performance evaluation metrics from magnetic resonance images. Any image needs to be denoised to get the accuracy, precision, and F-measure kind of common feature evaluation metrics. This paper evaluates two nonlinear filtering methods and their performance evaluated based on shapes and size of windows and for suppressing or de-noising to produce original noise-free images to assist clinically.

Suitability Classification of Retinal Fundus Images for Diabetic Retinopathy Using Deep Learning

Diabetic retinopathy (DR) is the primary cause of blindness in developing and developed countries. Early-stage DR detection reduces the risk of blindness in Diabetes Mellitus (DM) patients. There has been a sharp rise in the prevalence of DM in recent years, especially in low- and middle-income countries. In this context, automated artificial intelligence-based DM screening is a crucial tool to help classify the considerable amount of Retinal Fundus Images (RFI). However, retinal image quality assessment has shown to be fundamental in real-world DR screening processes to avoid out-of-distribution data, drift, and images lacking relevant anatomical information. This work analyzes the spatial domain features and image quality assessment metrics for carrying out Deep Learning (DL) classification and detecting notable features in RFI. In addition, a novel lightweight convolutional neural network is proposed specifically for binary classification at a low computational cost. The training results are comparable to state-of-the-art neural networks, which are widely used in DL applications. The implemented architecture achieves 98.6% area under the curve, and 97.66%, and 98.33% sensitivity and specificity, respectively. Moreover, the object detection model trained achieves 94.5% mean average precision. Furthermore, the proposed approach can be integrated into any automated RFI analysis system.

Qualitative Evaluation of Quality Measurement Within Emergency Clinician–Staffed Telehealth Programs

Emergency clinician-staffed telehealth programs seek to provide equitable, safe, efficient, effective, and patient-centered care. However, early studies show conflicting evidence on whether this aim is accomplished. Furthermore, how programs track the efficacy and safety of their programs remains largely unexplored. We sought to characterize ongoing quality monitoring among emergency clinician-staffed telehealth programs. We identified representatives at emergency clinician-staffed telehealth programs through professional networks and published literature. Qualitative interviews were conducted, assessing quality metrics captured as well as motivations for and barriers to quality measurement. We classified quality metric measurement using the National Quality Forum Telehealth Measurement Framework Domains and Subdomains. We developed a codebook from interview transcripts for qualitative analysis to classify motivations for and barriers to quality measurement. We held 8 qualitative interviews with physician representatives at primarily academic (7/8) and urban institutions (5/8). Most widely used quality metrics were related to patient and care team experience (7/8) as well as to access to care (6/8) and effectiveness (6/8). Few programs (2/8) measured finance-related quality metrics. Motivations for quality measurement varied considerably. Common barriers to implementation included technology challenges, data availability, and the lack of quality metric standardization. We identified variation in the use and content of quality metrics across emergency clinician-staffed telehealth programs. Most commonly, programs used metrics related to clinical experience; financial metrics were rarely captured. Technology barriers to quality measurement were often cited across programs. Further work is needed to support the standardization and implementation of future quality measurement initiatives.

A Survey on Monitoring Quality Assessment for Wireless Visual Sensor Networks

Wireless visual sensor networks have been adopted in different contexts to provide visual information in a more flexible and distributed way, supporting the development of different innovative applications. Although visual data may be central for a considerable set of applications in areas such as Smart Cities, Industry 4.0, and Vehicular Networks, the actual visual data quality may be not easily determined since it may be associated with many factors that depend on the characteristics of the considered application scenario. This entails several aspects from the quality of captured images (sharpness, definition, resolution) to the characteristics of the networks such as employed hardware, power consumption, and networking efficiency. In order to better support quality analysis and performance comparisons among different wireless visual sensor networks, which could be valuable in many monitoring scenarios, this article surveys this area with special concern on assessment mechanisms and quality metrics. In this context, a novel classification approach is proposed to better categorize the diverse applicable metrics for quality assessment of visual monitoring procedures. Hence, this article yields a practical guide for analyzing different visual sensor network implementations, allowing fairer evaluations and comparisons among a variety of research works. Critical analysis are also performed regarding the relevance and usage of the proposed categories and identified quality metrics. Finally, promising open issues and research directions are discussed in order to guide new developments in this research field.

The Effect of Peripheral Contrast Sensitivity Functions on the Performance of the Foveated Wavelet Image Quality Index

The Contrast Sensitivity Function (CSF) is an integral part of objective foveated image/video quality assessment metrics. In this paper, we investigate the effect of a new eccentricity-dependent CSF model on the performance of the foveated wavelet image quality index (FWQI). Our results do not show a considerable change in FWQI performance when it is evaluated against the LIVE-FBT-FCVR 2D dataset. We argue that the resolution of the head-mounted display used in the subjective experiment limits our ability to reveal the anticipated effect of the new CSF on FWQI performance.

Gated Recurrent Unit Framework for Ideological and Political Teaching System in Colleges

College ideological and political education has always been the primary content of national spiritual civilization construction. The current teaching methods are more flexible, resulting in the quality of ideological and political teaching not being reasonably assessed. To address this problem, we propose a method for assessing the quality of ideological and political teaching based on the gated recurrent unit (GRU) network and construct an automatic assessment system for ideological and political teaching. We draw on the migration learning model to improve the loss function by using the generalized intersection set over the joint loss function to compensate for the shortcoming of the small number of ideological and political teaching datasets. We use a masking algorithm to enhance the local features of teaching data sequences for different classes of ideological and political teaching quality assessment metrics. In addition, we use the minimum outer matrix algorithm to extract the sequence features of different assessment dimensions to improve the accuracy of the model for the quality assessment of ideological and political teaching. To meet the quality assessment conditions of ideological and political teaching, we compiled and produced ideological and political teaching datasets according to the teaching data coverage. The experimental results proved that our method performed best in comprehensive quality assessment accuracy in ideological and political teaching, with the assessment accuracy rate above 90%. Compared with traditional machine learning methods and deep learning methods, our method has higher accuracy and better robustness.

Automatic contrast enhancement with reversible data hiding using bi-histogram shifting

Aiming at resolving artificial distortions in marked images and increasing embedding capacity, this paper presents an automatic contrast enhancement (CE) method with reversible data hiding (RDH) using bi-histogram shifting (BHS). Current CE methods introduce distortions in marked images as embedding capacity increases. This paper focuses on resolving these artificial distortions by achieving better CE and increasing embedding capacity in marked images. The proposed method adaptively selects two peak bins and two lower bins based on four conditions depending on image brightness using the brightness preservation (BP) method. The two peak bins are used as splitting and embedding bins, whereas the lower bins are used as combining bins. The proposed method pairs each peak bin with a lower bin and performs BHS in the opposite direction to achieve histogram equalization (HE) while embedding secret data in marked images. The proposed method is compared with existing methods and evaluated with PSNR, SSIM, RCE, REE, RMBE, and VIF quality assessment metrics. Experimental results show that the proposed method's marked images are visually and qualitatively superior to existing works, with an average increase in embedding capacity of 37.6%. The proposed method is reversible and performs the extraction of embedded data to retrieve the original images losslessly.

LGGD+: Image Retargeting Quality Assessment by Measuring Local and Global Geometric Distortions

Numerous image retargeting algorithms have been proposed to achieve adaptive image resizing during the past years. To compare different image retargeting algorithms, reliable objective image retargeting quality assessment (IRQA) metrics are highly desired. Given that image retargeting usually introduces geometric distortions, this paper presents an objective IRQA metric by measuring both local and global geometric distortions (LGGD). Since human visual system perception is highly dependent on edges and the geometric distortions caused by image retargeting usually cause edge deformation, a sketch token-based local edge descriptor (ST-LED) is introduced to represent geometric-aware features in LGGD. First, ST-LED is first applied on both source and retargeted images for edge pattern representation. Second, pixel-level backward registration is conducted to enable estimating local geometric distortion (LGD) and a spatial pyramid-improved Bag-of-Token (BoT) model is built to enable estimating global geometric distortion (GGD). Since the proposed LGGD metric only focuses on geometric distortion while image retargeting quality is related with more aspects, we further fuse LGGD and an existing (EXT) IRQA metric to build a final version called LGGD+ for IRQA. Experiments on two benchmark databases demonstrate the superiority of LGGD+ and the excellent compatibility of our proposed LGGD for further improving a wide range of existing IRQA metrics (including both geometric distortion and non-geometric distortion metrics). In addition, the effectiveness of our LGGD metric is also demonstrated in another relevant task, i.e., quality evaluation of depth-image-based rendering (DIBR)-synthesized images, which also calls for accurate estimation of geometric distortion.

Quality assessment for terrestrial digital video broadcast over optical wireless communication‐passive optical network under moderately turbulent regime with spatial diversity

SummaryThe preceding decade has seen successful rollout of 5G and convergence of broadcast broadband and telecom sector. The near future bandwidth demands for services such as advanced immersive multimedia are even more challenging. This has led to advent of 6G. The access technologies need to provide virtually unlimited data rates to support majority of applications in 6G. The optical wireless communication (OWC) with its inherent advantages is a potential enabler in this scenario. However, phenomenon such as atmospheric turbulence poses a serious degradation to performance of such systems. For multimedia services, end user perception is the ultimate quality indicator. To ascertain this quality in quantitative terms, full reference quality metrics are employed for communication purposes. In this paper, digital video broadcasting terrestrial (DVB‐T) videos with varying complexities are transmitted over OWC‐passive optical network (PON) architecture. For performance enhancement 2 × 2 repetitive coding MIMO is employed with maximal ratio combining receiver. A total of 6 video quality assessment (VQA) metrics are evaluated for the system w.r.t channel parameter as Rytov variance. For all the VQA metrics, an enhancement in the performance is observed by using MIMO technique. This performance improvement is more prominent for more complex video as compared to less complex video. As for the limiting case BER of 10−3 gives a limiting link distance of 1350 m; however with VQA metrics, the limiting case distance is 1280 m. By the use of 2 × 2 MIMO techniques, this distance enhances by 20–25 m.