Image Quality Assessment without Reference by Combining Deep Learning-Based Features and Viewing Distance

  title={Image Quality Assessment without Reference by Combining Deep Learning-Based Features and Viewing Distance},
  author={A. Chetouani and Marius Pedersen},
  journal={Applied Sciences},
An abundance of objective image quality metrics have been introduced in the literature. One important essential aspect that perceived image quality is dependent on is the viewing distance from the observer to the image. We introduce in this study a novel image quality metric able to estimate the quality of a given image without reference for different viewing distances between the image and the observer. We first select relevant patches from the image using saliency information. For each patch… 
3 Citations

Quality Assessment of 2.5D Prints Using 2D Image Quality Metrics

Current state-of-the-art 2D full-reference image quality metrics were used to predict the quality of 2.5D prints and showed that the selected metrics can detect differences between the prints as well as between a print and its 2D reference image.

Saliency-Guided Local Full-Reference Image Quality Assessment

  • D. Varga
  • Environmental Science
  • 2022
Research and development of image quality assessment (IQA) algorithms have been in the focus of the computer vision and image processing community for decades. The intent of IQA methods is to

No-Reference Image Quality Assessment with Convolutional Neural Networks and Decision Fusion

  • D. Varga
  • Computer Science
    Applied Sciences
  • 2021
A novel, deep learning-based NR-IQA architecture that relies on the decision fusion of multiple image quality scores coming from different types of convolutional neural networks to better characterize authentic image distortions than a single network.



A Blind Image Quality Metric using a Selection of Relevant Patches based on Convolutional Neural Network

  • A. Chetouani
  • Computer Science
    2018 26th European Signal Processing Conference (EUSIPCO)
  • 2018
This paper proposes an image quality framework without reference based on selection of saliency patches and Convolutional Neural Network, which was evaluated using four well-known datasets to show its efficiency.

Image Quality Assessment by Comparing CNN Features between Images

Experimental results show that the proposed full reference image quality 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.

No-reference image quality assessment using Prewitt magnitude based on convolutional neural networks

The convolutional neural network is introduced into the no-reference image quality assessment and the Prewitt magnitude of segmented images is combined to obtain the image quality score using the mean of all the products of the image patch scores and weights based on the result of segmenting images.

No-reference image quality assessment based on deep convolutional neural networks

The aim is to determine the different types of distortion that are present in an image and find the total distortion levels using a novel architecture using multiple Deep Convolutional Neural Networks (MDNN).

Blind Utility and Quality Assessment Using a Convolutional Neural Network and a Patch Selection

  • A. Chetouani
  • Computer Science
    2019 IEEE International Conference on Image Processing (ICIP)
  • 2019
A Convolutional Neural Network-based method that predicts the subjective utility and quality scores of a given image without reference is proposed that was evaluated using the CU-Nantes dataset and the results highlighted the efficiency of the method.

Image Quality Assessment Without Reference By Mixing Deep Learning-Based Features

  • A. Chetouani
  • Computer Science
    2020 IEEE International Conference on Multimedia and Expo (ICME)
  • 2020
This paper proposes an efficient blind method to estimate the quality of 2D-images based on the selection of relevant patches through the saliency information and a Convolutional Neural Network (CNN).

On the use of deep learning for blind image quality assessment

The best proposal, named DeepBIQ, estimates the image quality by average-pooling the scores predicted on multiple subregions of the original image, having a linear correlation coefficient with human subjective scores of almost 0.91.

Quality Assessment Considering Viewing Distance and Image Resolution

Experimental results show that the performance of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) can be substantially improved by applying these metrics to OSS model preprocessed images, superior to classical multi-scale-PSNR/SSIM and comparable to the state-of-the-art competitors.

No Reference Image Quality Assessment based on Multi-Expert Convolutional Neural Networks

A novel NR IQA algorithm based on multi-expert convolutional neural networks (CNNs), which consists of distortion type classification, CNN based IQA algorithms and fusion algorithm is developed.