Objective Image Quality Assessment: Facing The Real-World Challenges

@inproceedings{Wang2016ObjectiveIQ,
  title={Objective Image Quality Assessment: Facing The Real-World Challenges},
  author={Zhou Wang},
  booktitle={IQSP},
  year={2016}
}
  • Zhou Wang
  • Published in IQSP 14 February 2016
  • Computer Science
There has been a growing interest in recent years in the development of objective image quality assessment (IQA) models, whose roles are not only to monitor image quality degradations and benchmark image processing systems, but also to optimize various image and video processing algorithms and systems. While the past achievement is worth celebrating, a number of major challenges remain when we apply existing IQA models in realworld applications. These include obvious ones such as the challenges… 

Figures from this paper

A Comprehensive Performance Evaluation of Image Quality Assessment Algorithms

This work carries out the largest performance evaluation study so far 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.

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

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 is introduced.

Image Quality Assessment in the Modern Age

This tutorial provides the audience with the basic theories, methodologies, and current progresses of image quality assessment (IQA), and presents in detail the design principles of objective quality assessment models, supplemented by an in-depth analysis of their advantages and disadvantages.

Title No-Reference Quality Assessment of Deblurred ImagesBased on Natural Scene Statistics

A no-reference quality metric for defocus deblured images based on Natural Scene Statistics (NSS) is presented and experimental results demonstrate the advantages of the proposed metric over the relevant state-of-the-arts.

No-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics

A no-reference quality metric for defocus deblured images based on Natural Scene Statistics (NSS) is presented and experimental results demonstrate the advantages of the proposed metric over the relevant state-of-the-arts.

Reduced Reference Quality Assessment of Light Field Images

The relation between depth map quality and overall quality of LF image is studied and evidence that the estimated quality score by the proposed framework has a significant correlation with subjective quality rating is achieved.

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.

SIQ288: A saliency dataset for image quality research

  • Wei ZhangHantao Liu
  • Computer Science
    2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP)
  • 2016
This work proposed a new experimental methodology with dedicated control mechanisms, which allows collecting more reliable eye-tracking data, and provides a benchmark for gauging saliency models in the context of image quality.

Q-DNN: A quality-aware deep neural network for blind assessment of enhanced images

Experimental results on two challenging enhanced image databases show that the proposed data-driven blind image quality assessment (BIQA) method is significantly superior to the state-of-the-art BIQA metrics.

References

SHOWING 1-10 OF 48 REFERENCES

Modern Image Quality Assessment

This book is about objective image quality assessment to provide computational models that can automatically predict perceptual image quality and to provide new directions for future research by introducing recent models and paradigms that significantly differ from those used in the past.

Group MAD Competition? A New Methodology to Compare Objective Image Quality Models

  • Kede MaQ. Wu Lei Zhang
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
A new mechanism, namely group MAximum Differentiation (gMAD) competition, which automatically selects subsets of image pairs from the database that provide the strongest test to let the IQA models compete with each other, is proposed.

A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms

This paper presents results of an extensive subjective quality assessment study in which a total of 779 distorted images were evaluated by about two dozen human subjects and is the largest subjective image quality study in the literature in terms of number of images, distortion types, and number of human judgments per image.

Objective Quality Assessment for Color-to-Gray Image Conversion

One of the first attempts to develop an objective quality model that automatically predicts the perceived quality of C2G converted images is made, Inspired by the philosophy of the structural similarity index, which evaluates the luminance, contrast, and structure similarities between the reference color image and the C1G converted image.

Perceptual Quality Assessment for Multi-Exposure Image Fusion

This paper proposes a novel objective image quality assessment (IQA) algorithm for MEF images based on the principle of the structural similarity approach and a novel measure of patch structural consistency and shows that the proposed model well correlates with subjective judgments and significantly outperforms the existing IQA models for general image fusion.

Most apparent distortion: full-reference image quality assessment and the role of strategy

A quality assessment method [most apparent distortion (MAD)], which attempts to explicitly model these two separate strategies, local luminance and contrast masking and changes in the local statistics of spatial-frequency components are used to estimate appearance-based perceived distortion in low-quality images.

A Two-Step Framework for Constructing Blind Image Quality Indices

A new two-step framework for no-reference image quality assessment based on natural scene statistics (NSS) is proposed, which does not require any knowledge of the distorting process and the framework is modular in that it can be extended to any number of distortions.

Objective Quality Assessment of Interpolated Natural Images

An objective method to assess the quality of an interpolated natural image using the available LR image as a reference and adopts a natural scene statistics (NSS) framework, where image quality degradation is gauged by the deviation of its statistical features from the NSS models trained upon high-quality natural images.

Making a “Completely Blind” Image Quality Analyzer

This work has recently derived a blind IQA model that only makes use of measurable deviations from statistical regularities observed in natural images, without training on human-rated distorted images, and, indeed, without any exposure to distorted images.

Blind Image Quality Assessment Using Joint Statistics of Gradient Magnitude and Laplacian Features

This work proposes a novel BIQA model that utilizes the joint statistics of two types of commonly used local contrast features: 1) the gradient magnitude (GM) map and 2) the Laplacian of Gaussian response.