Unlock instant, AI-driven research and patent intelligence for your innovation.

Image quality measurement based on local amplitude and phase spectra

A quality measurement, local technology, applied in the field of image processing, can solve the problems of subjective image quality assessment, blurring and so on without reporting

Inactive Publication Date: 2015-02-11
THOMSON LICENSING SA
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Subjective image quality assessments in response to magnitude and phase errors are not reported for a general range of image distortions other than some specific distortions like blurring

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image quality measurement based on local amplitude and phase spectra
  • Image quality measurement based on local amplitude and phase spectra
  • Image quality measurement based on local amplitude and phase spectra

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In an offline fashion, the ISA bases are pre-learned independently of the image whose quality will be predicted. In an exemplary embodiment, an 8x8 ISA is performed, resulting in 14 subgroups. Each subgroup contains four bases. There are 56 bases in total. The basis defines an orthogonal (incomplete) transformation. ISA transforms linear matrix computations like 2D DCT. Thus, each 8x8 image patch produces 56 ISA transform coefficients, resulting in fourteen four-dimensional ISA transform coefficient vectors. Note that training on different datasets may result in slightly different ISA bases, however, the performance of our metric is insensitive to such variations. Each basis is vectorized as a row vector, fourteen bases yielding a 56x64 matrix W. If each 8x8 image patch is vectorized as a column vector Then the ISA transform is given by:

[0031] s → = W x →

[0...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method and system for determining a quality metric score for image processing are described including accepting a reference image, performing a pyramid transformation on the accepted reference image to produce a predetermined number of scales, applying image division to each scale to produce reference image patches, accepting a distorted image, performing a pyramid transformation on the accepted distorted image to produce the predetermined number of scales, applying image division to each scale to produce distorted image patches, performing a local distortion calculation for corresponding reference and distorted image patches, summing local distortion calculation results for image patch pairs, multiplying results of the summation operation by a positive weight for each scale, summing the results of the multiplication operation and applying a sigmoid function to results of the second summation operation to produce the quality metric score.

Description

technical field [0001] The present invention relates to image processing and, in particular, to efficient solutions to quality aware optimization problems. Background technique [0002] Measuring image quality is widely used in perceptual image processing, e.g., perceptual coding, tone mapping, restoration, watermarking, etc. Depending on the availability of reference images / videos, visual quality metrics include full-reference metrics and non-reference metrics. For full-reference quality metrics, image differences between reference and corrupted images / videos can be a key factor in visual quality. [0003] Perceptual image processing often exploits aspects of the human visual system (HVS) and seeks a compromise between good image quality and effective specific goals for processing. For example, perceptual coding looks for a trade-off between mild distortion and high bitrate efficiency, while perceptual watermarking pursues a trade-off between invisible and robust watermar...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04N17/00G06T7/00
CPCG06T2207/30168G06T7/0002G06T3/4084G06T2207/20048
Inventor 张帆陈志波江文斐
Owner THOMSON LICENSING SA