No-Reference Image Quality Assessment with Global Statistical Features

Varga, Domonkos

doi:10.3390/jimaging7020029

Cited by 27 publications

(14 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To tackle the wide variety of authentic distortions, a broad spectrum of statistical local and global features were applied. Artificial distortions (such as JPEG or JPEG2000 compression) are usually uniformly distributed in an image, which can be characterized well by global and homogeneous features [ 51 ]. However, authentic distortions often appear locally in a digital image, which can be better captured by local, non-homogeneous image features.…”

Section: Materials and Methodsmentioning

confidence: 99%

No-Reference Quality Assessment of Authentically Distorted Images Based on Local and Global Features

Varga

2022

J. Imaging

Self Cite

View full text Add to dashboard Cite

With the development of digital imaging techniques, image quality assessment methods are receiving more attention in the literature. Since distortion-free versions of camera images in many practical, everyday applications are not available, the need for effective no-reference image quality assessment algorithms is growing. Therefore, this paper introduces a novel no-reference image quality assessment algorithm for the objective evaluation of authentically distorted images. Specifically, we apply a broad spectrum of local and global feature vectors to characterize the variety of authentic distortions. Among the employed local features, the statistics of popular local feature descriptors, such as SURF, FAST, BRISK, or KAZE, are proposed for NR-IQA; other features are also introduced to boost the performances of local features. The proposed method was compared to 12 other state-of-the-art algorithms on popular and accepted benchmark datasets containing RGB images with authentic distortions (CLIVE, KonIQ-10k, and SPAQ). The introduced algorithm significantly outperforms the state-of-the-art in terms of correlation with human perceptual quality ratings.

show abstract

Section: Materials and Methodsmentioning

confidence: 99%

No-Reference Quality Assessment of Authentically Distorted Images Based on Local and Global Features

Varga

2022

J. Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…Specifically, the framework is divided into two stages: In this section, the six different aspects of feature extraction are in detailed description first: complexity, contrast, sharpness, brightness, colorfulness, and naturalness. These quality perception features that affect image quality are widely applied in NR-IQA [25][26][27] and have yielded good results. Second, the integrated SVR technology in the regression module is mainly explained.…”

Section: Objective Quality Assessment Of Display Productsmentioning

confidence: 99%

Subjective and Objective Quality Assessments of Display Products

Zhang

et al. 2021

Entropy

View full text Add to dashboard Cite

In recent years, people’s daily lives have become inseparable from a variety of electronic devices, especially mobile phones, which have undoubtedly become necessity in people’s daily lives. In this paper, we are looking for a reliable way to acquire visual quality of the display product so that we can improve the user’s experience with the display product. This paper proposes two major contributions: the first one is the establishment of a new subjective assessment database (DPQAD) of display products’ screen images. Specifically, we invited 57 inexperienced observers to rate 150 screen images showing the display product. At the same time, in order to improve the reliability of screen display quality score, we combined the single stimulation method with the stimulation comparison method to evaluate the newly created display products’ screen images database effectively. The second one is the development of a new no-reference image quality assessment (IQA) metric. For a given image of the display product, first our method extracts 27 features by analyzing the contrast, sharpness, brightness, etc., and then uses the regression module to obtain the visual quality score. Comprehensive experiments show that our method can evaluate natural scene images and screen content images at the same time. Moreover, compared with ten state-of-the-art IQA methods, our method shows obvious superiority on DPQAD.

show abstract

“…However, in most medical applications, the unavailability of the reference image highlights the importance of developing new no-reference methods. 13 In the present study, we proposed an objective descriptor of X-ray image quality called the image feature index (IFI). IFI is a no-reference image quality assessment that provides a composite measure of the amount of information, texture features, and noise in an X-ray image by obtaining quantitative information directly from the image.…”

Section: Introductionmentioning

confidence: 99%

“…The full‐reference techniques compare the evaluated image with its undistorted pristine image. However, in most medical applications, the unavailability of the reference image highlights the importance of developing new no‐reference methods 13 . In the present study, we proposed an objective descriptor of X‐ray image quality called the image feature index (IFI).…”

Section: Introductionmentioning

confidence: 99%

Image feature index: A novel metric for quantifying chest radiographic image quality

Liang

Tang

et al. 2023

Medical Physics

View full text Add to dashboard Cite

Background: Radiographic X-ray imaging is a common clinical examination. Current objective methods for quantifying image quality for radiographs struggle to capture the combined impact of factors throughout the imaging chain on the perceived image quality. Therefore, there is a need to further develop metrics that correlate with image quality as perceived by the observer. Objectives: We proposed the image feature index (IFI) to comprehensively quantify radiographic X-ray image quality. We also aimed to study the correlation between IFI and observer-perceived image quality for chest radiographs. Materials and methods:The IFI algorithm was developed, which measured the amount of information, textural features, and noise in the image. A total of 70 chest phantom radiographs were generated under 60-120 kV and 0.2-80 mAs. A vendor-proprietary exposure index (EI) and dose area product (DAP) were extracted from the DICOM header in addition to calculating IFI for each image to investigate the relationships between IFI, EI and DAP. The quality of the images was rated by three observers, and the correlation between IFI and subjective score of image quality was tested. Next, a retrospective study using a random sample of 50 clinical chest radiographs was performed, and the correlation between IFI and subjective score was tested. The correlation was determined by the Spearman test. Results: The curves of IFI versus DAP and IFI versus EI both demonstrated a similar three-stage form where IFI is above zero: in the first stage, IFI increases rapidly with increased DAP or EI, whereas in the second stage, the slope of the curves decreased towards an asymptote, that is, minimal gain in IFI with increased DAP or EI-until they hit the inflection point and then descended sharply in the third stage. For both phantom and clinical chest images, IFI demonstrated good correlation with subjective score (r = 0.9084 for phantom images, r = 0.8153 for clinical images). Conclusions: IFI is a feasible and efficient descriptor for image quality for chest radiographs. Future studies with larger sample sizes and sample types are needed to confirm the feasibility of IFI for other exam types and anatomical views, thus fulfilling and extending the potential applications of IFI in quality control and radiation dose reduction.

show abstract

No-Reference Image Quality Assessment with Global Statistical Features

Cited by 27 publications

References 66 publications

No-Reference Quality Assessment of Authentically Distorted Images Based on Local and Global Features

No-Reference Quality Assessment of Authentically Distorted Images Based on Local and Global Features

Subjective and Objective Quality Assessments of Display Products

Image feature index: A novel metric for quantifying chest radiographic image quality

Contact Info

Product

Resources

About