A Detail-Based Method for Linear Full Reference Image Quality Prediction

Claudio, Elio D. Di; Jacovitti, G.

doi:10.1109/tip.2017.2757139

Cited by 17 publications

(9 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Detail Virtual Cognitive Model (DVICOM) [80] combines two separate metrics that measure the perceptual impact of detail losses and spurious details. Using the images being compared and Least Squares decomposition, DVICOM breaks down the gradient field of the distorted image into two components, a prediction of the gradient field of the original image and an unpredictable gradient residual.…”

Section: ) Mixed Strategy Based Methodsmentioning

confidence: 99%

“…These methods include IWSSIM [87], FSIMc/FSIM [83], DSS [79], VSI [102], GMSD [84], MCSD [88], ESSIM [82], and CID_MS [78]. For these categories, the sparsity based NSS methods QASD [94] and SFF [96], and the mixed strategy based methods DVICOM [80] and MAD [6] also do well. For the multiple distortion databases category, the NSS methods VIF [100] and VIF_DWT [76], and the mixed strategy based method DVICOM/DIVICOM_F [80], do well in addition to the structural similarity based approaches.…”

Section: ) Individual Fr Methodsmentioning

confidence: 99%

“…For these categories, the sparsity based NSS methods QASD [94] and SFF [96], and the mixed strategy based methods DVICOM [80] and MAD [6] also do well. For the multiple distortion databases category, the NSS methods VIF [100] and VIF_DWT [76], and the mixed strategy based method DVICOM/DIVICOM_F [80], do well in addition to the structural similarity based approaches. It can be observed from Table 13 that error based FR methods do not offer competitive performance against other IQA design philosophies.…”

Section: ) Individual Fr Methodsmentioning

confidence: 99%

“…VIF [100], SFF [96], and QASD [94] represent the NSS based methods category. Finally, ADM [77], MAD [6], and DVI-COM_F [80], represent the mixed strategy based methods category. To help statistically compare individual FR methods with fused ones, two fused FR methods are also included in Table 16.…”

Section: F Statistical Significance Testingmentioning

confidence: 99%

See 3 more Smart Citations

A Comprehensive Performance Evaluation of Image Quality Assessment Algorithms

Athar

Zhou

2019

IEEE Access

View full text Add to dashboard Cite

Image quality assessment (IQA) algorithms aim to predict perceived image quality by human observers. Over the last two decades, a large amount of work has been carried out in the field. New algorithms are being developed at a rapid rate in different areas of IQA, but are often tested and compared with limited existing models using out-of-date test data. There is a significant gap when it comes to large-scale performance evaluation studies that include a wide variety of test data and competing algorithms. In this work we aim to fill this gap by carrying out the largest performance evaluation study so far. We test the performance of 43 full-reference (FR), seven fused FR (22 versions), and 14 no-reference (NR) methods on nine subject-rated IQA datasets, of which five contain singly distorted images and four contain multiply distorted content. We use a variety of performance evaluation and statistical significance testing criteria. Our findings not only point to the top performing FR and NR IQA methods, but also highlight the performance gap between them. In addition, we have also conducted a comparative study on FR fusion methods, and an important discovery is that rank aggregation based FR fusion is able to outperform not only other FR fusion approaches but also the top performing FR methods. It may be used to annotate IQA datasets as a possible alternative to subjective ratings, especially in situations where it is not possible to obtain human opinions, such as in the case of large-scale datasets composed of thousands or even millions of images.

show abstract

Section: ) Mixed Strategy Based Methodsmentioning

confidence: 99%

Section: ) Individual Fr Methodsmentioning

confidence: 99%

Section: ) Individual Fr Methodsmentioning

confidence: 99%

Section: F Statistical Significance Testingmentioning

confidence: 99%

See 2 more Smart Citations

A Comprehensive Performance Evaluation of Image Quality Assessment Algorithms

Athar

Zhou

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The PFI losses are calculated at the computational and representational levels, irrespective of the underlying physical mechanisms characterizing the implementation level. See (Peebles & Cooper, 2015) and the introduction of (Di Claudio & Jacovitti, 2018).…”

Section: Introductionmentioning

confidence: 99%

Predicting blur visual discomfort for natural scenes by the loss of positional information

2021

Self Cite

View full text Add to dashboard Cite

The perception of blur due to accommodation failures, insufficient optical correction or imperfect image reproduction is a common source of visual discomfort, usually attributed to an anomalous and annoying distribution of the image spectrum in the spatial frequency domain. In the present paper, this discomfort is related to a loss of the localization accuracy of the observed patterns. It is assumed, as a starting perceptual principle, that the visual system is optimally adapted to pattern localization in a natural environment. Thus, since the best possible accuracy of the image patterns localization is indicated by the positional Fisher Information, it is argued that blur discomfort is strictly related to a loss of this information. Following this concept, a receptive field functional model is adopted to predict the visual discomfort. It is a complex-valued operator, orientationselective both in the space domain and in the spatial frequency domain. Starting from the case of Gaussian blur, the analysis is extended to a generic type of blur by applying a positional Fisher Information equivalence criterion. Out-of-focus blur and astigmatic blur are presented as significant examples. The validity of the proposed model is verified by comparing its predictions with subjective ratings. The model fits linearly with the experiments reported in independent databases, based on different protocols and settings.

show abstract