Image Quality Assessment Using a Combination of Hand-Crafted and Deep Features

Ahmed, Nisar; Asif, Hafiz M.; Khalid, Hassan

doi:10.1007/978-981-15-5232-8_51

Cited by 4 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the existing learning-based color harmony models, excellent performance has been achieved using the latent Dirichlet allocation (LDA) method, which effectively imitates complex color combinations by Bayesian theory. 19,20 Nisar et al 21,22 proposed a hybrid image quality assessment method combining hand-crafted and deep features. Subsequently, they assessed the quality of digital images by computing image luminance and gradient statistics along with mean subtracted contrast normalized products in multiple scales and color spaces.…”

Section: Related Workmentioning

confidence: 99%

Dual-band color fusion image quality assessment based on color descriptors

Gao,

Song,

Zhang

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

Significant progress has been made in no-reference image quality assessment in terms of color harmony in recent years. However, most methods do not consider color contrast and lose some color information in the quantification process, so they perform poorly when evaluating the color harmony of color images. An image quality assessment model based on color descriptors is established under the inspiration of natural scene statistics. The model introduces local color contrast features of color fusion images and combines them with visual attention mechanism. The local color statistics coefficients of images in both RGB color space and CIELAB color space are calculated to reduce the loss of color information. Furthermore, a multi-scale content-aware network is used to extract multi-scale content features and establish the connection between color features and image content. Finally, the image quality score is obtained by the quality assessment network. The dataset validation and experimental results reveal that the proposed model, compared with the existing 15 methods, has good agreement with human visual perception and better performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Dual-band color fusion image quality assessment based on color descriptors

Gao,

Song,

Zhang

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…Retraining of these models makes them learn quality-aware features and these features can be used for image quality assessment. Another approach is to train the regression algorithm with natural scene statistics as well as deep-features for an enriched feature experience [2].…”

Section: Related Workmentioning

confidence: 99%

“…This quality score is a Mean Opinion Score (MOS) of human judgment. The relationship between image and its corresponding quality score is dependent on the human visual system which is a naively understood area and therefore modeling such a system is tough [2].…”

Section: Introductionmentioning

confidence: 99%

Deep ensembling for perceptual image quality assessment

et al. 2022

Self Cite

View full text Add to dashboard Cite

Blind image quality assessment is a challenging task particularly due to unavailability of reference information. Training a deep neural network requires a large amount of training data which is not readily available for image quality. Transfer learning is usually opted to overcome this limitation and different deep architectures are used for this purpose as they learn features differently. After extensive experiments, we have designed a deep architecture containing two CNN architectures as its sub-units. Moreover, a self-collected image database BIQ2021 is proposed with 12,000 images having natural distortions. The self-collected database is subjectively scored and is used for model training and validation. It is demonstrated that synthetic distortion databases cannot provide generalization beyond the distortion types used in the database and they are not ideal candidates for general-purpose image quality assessment. Moreover, a largescale database of 18.75 million images with synthetic distortions is used to pre-train the model and then retrain it on benchmark databases for evaluation. Experiments are conducted on six benchmark databases three of which are synthetic distortion databases (LIVE, CSIQ & TID2013) and three are natural distortion databases (LIVE Challenge Database, CID2013 & KonIQ-10k). The proposed approach has provided a Pearson correlation coefficient of 0.8992, 0.8472 and 0.9452 subsequently and Spearman correlation coefficient of 0.8863, 0.8408 and 0.9421. Moreover, the performance is demonstrated using Perceptually Weighted Rank Correlation (PWRC) to indicate perceptual superiority of the proposed approach. Multiple experiments are conducted to validate the generalization performance of the proposed model by training on different subsets of the databases and validating on the test subset of BIQ2021 database.

show abstract

“…It is apparent that HVS is a naïvely understood area so extraction of NSS features with ability to perfectly model the HVS is difficult [23]. A representative feature set to train a model for visual quality assessment is therefore a challenging problem [24].…”

Section: Introductionmentioning

confidence: 99%

“…Another approach to opinion un-aware IQA is learning based in which discriminative features are learned using dictionary-based [21,25] or neural network based methods [24]. These features are believed to model the HVS better than the hand-crafted features.…”

Section: Introductionmentioning

confidence: 99%

PIQI: perceptual image quality index based on ensemble of Gaussian process regression

Ahmed

Asif

Khalid

2021

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Digital images contain a lot of redundancies, therefore, compression techniques are applied to reduce the image size without the loss of reasonable image quality. Same become more prominent in the case of videos which contains image sequences and higher compression ratios are achieved in low throughput networks. Assessment of quality of images in such scenarios has become of particular interest. Subjective evaluation in most of the scenarios is infeasible so objective evaluation is preferred. Among the three objective quality measures, full-reference and reduced-reference methods require an original image in some form to calculate the image quality which is unfeasible in scenarios such as broadcasting, acquisition or enhancement. Therefore, a no-reference Perceptual Image Quality Index (PIQI) is proposed in this paper to assess the quality of digital images which calculates luminance and gradient statistics along with mean subtracted contrast normalized products in multiple scales and color spaces. These extracted features are provided to a stacked ensemble of Gaussian Process Regression (GPR) to perform the perceptual quality evaluation. The performance of the PIQI is checked on six benchmark databases and compared with twelve state-of-the-art methods and competitive results are achieved. The comparison is made based on RMSE, Pearson and Spearman's correlation coefficients between ground truth and predicted quality scores. The scores of 0.0552, 0.9802 and 0.9776 are achieved respectively for these metrics on CSIQ database. Two cross-dataset evaluation experiments are performed to check the generalization of PIQI.

show abstract

Image Quality Assessment Using a Combination of Hand-Crafted and Deep Features

Cited by 4 publications

References 23 publications

Dual-band color fusion image quality assessment based on color descriptors

Dual-band color fusion image quality assessment based on color descriptors

Deep ensembling for perceptual image quality assessment

PIQI: perceptual image quality index based on ensemble of Gaussian process regression

Contact Info

Product

Resources

About