On the use of deep learning for blind image quality assessment

Bianco, Simone; Celona, Luigi; Napoletano, Paolo; Schettini, Raimondo

doi:10.1007/s11760-017-1166-8

“…Tang et al [26] pre-trained a deep belief network with a radial basis function and fine-tuned it to predict image quality. Bianco et al [27] investigated various design choices for CNN-based BIQA. They first adopted off-the-shelf CNN features to learn a quality evaluator using support vector regression (SVR).…”

Section: Related Workmentioning

confidence: 99%

“…Alternatively, they fine-tuned the features in a multi-class classification setting followed by SVR. Their proposals are not end-to-end optimized and involve heavy manual parameter adjustments [27]. Kang et al [9] trained a CNN using a large number of spatially normalized image patches.…”

Section: Related Workmentioning

confidence: 99%

Blind Image Quality Assessment Using a Deep Bilinear Convolutional Neural Network

Zhang

¹

,

Ma

²

,

Jia

³

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

We propose a deep bilinear model for blind image quality assessment (BIQA) that handles both synthetic and authentic distortions. Our model consists of two convolutional neural networks (CNN), each of which specializes in one distortion scenario. For synthetic distortions, we pre-train a CNN to classify image distortion type and level, where we enjoy largescale training data. For authentic distortions, we adopt a pretrained CNN for image classification. The features from the two CNNs are pooled bilinearly into a unified representation for final quality prediction. We then fine-tune the entire model on target subject-rated databases using a variant of stochastic gradient descent. Extensive experiments demonstrate that the proposed model achieves superior performance on both synthetic and authentic databases. Furthermore, we verify the generalizability of our method on the Waterloo Exploration Database using the group maximum differentiation competition.

show abstract

“…Bianco et al 18 proposed DeepBIQ metrics, which estimates image quality by averaging the scores predicted on multiple sub-regions of the image. The score of a sub-region is calculated using a Support Vector Regression (SVR) machine over CNN features.…”

Section: Cnn-based Metricsmentioning

confidence: 99%

“…Many different approaches for measuring image quality have been proposed, including structural similarity, 6,7 color difference, 8 spatial extensions of color difference formulas, [9][10][11][12] simulation of detail visibility, 13,14 scene statistics, 15 low-and mid-level visual properties, 16 saliency, 17 machine learning, [18][19][20][21] and more. Image quality metrics have been used to measure general image quality, but are also applied to different applications such as printing, [22][23][24][25] displays, 26,27 spectral imaging, 28 image compression, 29 and medical imaging.…”

Section: Introductionmentioning

confidence: 99%

Image Quality Assessment by Comparing CNN Features between Images

Amirshahi¹,

Pedersen²,

Yu³

2016

jist

View full text Add to dashboard Cite

Abstract.Finding an objective image quality metric that matches the subjective quality has always been a challenging task. We propose a new full reference image quality metric based on features extracted from Convolutional Neural Networks (CNNs). Using a pre-trained AlexNet model, we extract feature maps of the test and reference images at multiple layers, and compare their feature similarity at each layer. Such similarity scores are then pooled across layers to obtain an overall quality value. Experimental results on four state-of-the-art databases show that our metric is either on par or outperforms 10 other state-of-the-art metrics, demonstrating that CNN features at multiple levels are superior to handcrafted features used in most image quality metrics in capturing aspects that matter for discriminative perception.

show abstract

“…Many different approaches for measuring image quality have been proposed, including structural similarity, 6,7 color difference, 8 spatial extensions of color difference formulas, [9][10][11][12] simulation of detail visibility, 13,14 scene statistics, 15 low-and mid-level visual properties, 16 saliency, 17 machine learning, [18][19][20][21] and more. Image quality metrics have been used to measure general image quality, but are also applied to different applications such as printing, [22][23][24][25] displays, 26,27 spectral imaging, 28 image compression, 29 and medical imaging.…”

Section: Introductionmentioning

confidence: 99%

Image Quality Assessment by Comparing CNN Features between Images

Amirshahi¹,

Pedersen²,

Yu³

2017

View full text Add to dashboard Cite

Abstract.Finding an objective image quality metric that matches the subjective quality has always been a challenging task. We propose a new full reference image quality metric based on features extracted from Convolutional Neural Networks (CNNs). Using a pre-trained AlexNet model, we extract feature maps of the test and reference images at multiple layers, and compare their feature similarity at each layer. Such similarity scores are then pooled across layers to obtain an overall quality value. Experimental results on four state-of-the-art databases show that our metric is either on par or outperforms 10 other state-of-the-art metrics, demonstrating that CNN features at multiple levels are superior to handcrafted features used in most image quality metrics in capturing aspects that matter for discriminative perception.

show abstract

On the use of deep learning for blind image quality assessment

Cited by 285 publications

References 46 publications

Blind Image Quality Assessment Using a Deep Bilinear Convolutional Neural Network

Blind Image Quality Assessment Using a Deep Bilinear Convolutional Neural Network

Image Quality Assessment by Comparing CNN Features between Images

Image Quality Assessment by Comparing CNN Features between Images

Contact Info

Product

Resources

About