• Corpus ID: 10243191

Human Vision Models for Perceptually Optimized Image Processing – A Review

  title={Human Vision Models for Perceptually Optimized Image Processing – A Review},
  author={Marcus J. Nadenau and Stefan Winkler and David Alleysson and Murat Kunt},
By taking into account the properties and limitations of the human visual system (HVS), images can be more efficiently compressed, colors more accurately reproduced, prints better rendered, to mention a few major advantages. To achieve these goals it is necessary to build a computational model of the HVS. In this paper we give an introduction to the general issue of HVS-modeling and review the specific applications of visual quality assessment and HVS-based image compression, which are closely… 

Figures from this paper

A New Image Quality Metric using System Visual Human Characteristics

A new quality metric based on the dynamic characteristics and on the just-noticeable-difference threshold characteristics introduced by Weber's law is proposed: the relative weighted Peak to Signal Noise Ratio ( rwPSNR).

A HVS-inspired Attention Map to Improve CNN-based Perceptual Losses for Image Restoration

This work designs an attention map that is applied to feature maps in the perceptual loss, helping it to identify regions that are of more perceptual importance and results in a loss which delivers a better perception-distortion trade-off compared to the widely used perceptual loss in CNN based image restoration problems.

A HVS-Inspired Attention to Improve Loss Metrics for CNN-Based Perception-Oriented Super-Resolution

This work proposes a spatial attention mechanism based on the dependency human contrast sensitivity on spatial frequency that is applied to feature maps in the perceptual loss and its variants, helping them to identify regions that are of more perceptual importance.

Psychovisual Evaluation of Lossy CMYK Image Compression for Printing Applications

Results on three typical prepress test images indicate that the proposed adaptations of JPEG to CMYK images are useful and that for the investigated printing configuration, compression ratios up to 20 can be used safely.

Why Are Deep Representations Good Perceptual Quality Features?

It is demonstrated that the pre-trained CNN features which receive higher scores are better at predicting human quality judgment, and the possibility of using the method to select deep features to form a new loss function, which improves the image reconstruction quality for the well-known single-image super-resolution problem.

Visual masking model for perceptual color image compression

  • C. CharrierT. Eude
  • Engineering
    International Congress on High-Speed Imaging and Photonics
  • 2003
This scheme exploits the lowpass character of the perceptual masking for natural color images in estimating the amount of available masking in order to exploit human visual masking effect using a subband decomposition.

Image quality assessment using artificial neural networks

Experimental results show that the predicted image quality with neural networks is more consistent with perceptual image quality than existing objective measure, such as the MSSIM.

Analysis and Interpretation of Deep CNN Representations as Perceptual Quality Features

It is concluded that sensitivity to spatial frequencies that have lower contrast masking thresholds in human visual perception and a definite and strong orientation selectivity are important attributes of deep CNN channels that deliver better perceptual quality features.

Wavelet-based color image compression: exploiting the contrast sensitivity function

Two new techniques that implement the contrast sensitivity function at significantly higher precision are presented, adapting even to local variations of the spatial frequencies within a decomposition subband, and are compared to conventional CSF-schemes.



Modeling the perception of digital images: a performance study

Some well- known image discrimination models are brought together and compared their performance against one set of psychophysical data, with image fidelity as the intended task and showed that models using cross-channel masking gave the best overall results.

Visual difference metric for realistic image synthesis

A simplified version of the Lubin Visual Discrimination Metric (VDM) that was developed for insertion into an image synthesis algorithm makes use of a Haar wavelet basis for the cortical transform and a less severe spatial pooling operation.

Issues in vision modeling for perceptual video quality assessment

A Visual Model Weighted Cosine Transform for Image Compression and Quality Assessment

A new analytical solution, taking the form of a straightforward multiplicative weighting function, is developed which is readily applicable to image compression and quality assessment in conjunction with a visual model and the image cosine transform.

The Application Of Human Visual System Models To Digital Color Image Compression

  • C. Hall
  • Computer Science
    Other Conferences
  • 1986
A nonlinear mathematical model for the human visual system was selected as a pre-processing stage for monochrome and color digital image compression and leads to an image quality metric which compares to subjective evaluations of an extensive image set with a correlation of 0.92.

Image-compression-related contrast-masking measurements

This paper evaluates the effect of contrast and entropy masking based on complex images of natural scenery based on wavelet-based image compression and some models are compared in terms of prediction performance.

Picture Quality Prediction Based on a Visual Model

It is shown that the filtered error measures are better predictors of picture quality than the raw error measures and lead to further improvements but only if local rather than global averaging procedures are used.

Perceptual distortion measure for edgelike artifacts in image sequences

An objective perceptual distortion measure quantifying the visibility of edge-like blocking artifacts in coded image sequences resulting from popular transform coding techniques is presented, indicating that the perceptual distortionMeasure agrees well with human evaluation.

Comparison of two image quality models

The comparison of these two models is presented in the context of the research interests which are image quality evaluation for both computer imaging and computer graphics tasks.

Perceptual quality measure using a spatiotemporal model of the human visual system

A metric for the assessment of video coding quality is presented based on a multi- channel model of human spatio-temporal vision that has been parameterized for video coding applications by psychophysical experiments.