Method and system for determining a quality measure for an image using a variable number of multi-level decompositions

• US 8,660,363 B2
• Filed: 07/09/2013
• Issued: 02/25/2014
• Est. Priority Date: 02/11/2009
• Status: Active Grant

• Current Assignee: Ecole de technologie superieure
• Original Assignee: Ecole de technologie superieure
• Inventors: Rezazadeh, Soroosh, Coulombe, Stephane
• Primary Examiner(s): Bayat, Ali
• Application Number:
  US13/938,143
• Publication Number:
  US 20130294701A1
• Time in Patent Office: 231 Days
• Field of Search: 382/199, 382/232, 382/233, 382/128, 382/203, 382/240, 382/243, 382/246, 382/260, 375/240.18, 375/240.19, 375/240.8, 250/202, 250/363.06
• US Class Current: 382/199
• CPC Class Codes: G06T 2207/20016 Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
• CPC Class Codes: G06T 2207/20064 Wavelet transform [DWT]
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 7/0004 Industrial image inspection

Abstract

Method and system for determining a measure of quality for images are presented. Multi-level decomposition of images in the wavelet domain using a variable number of levels of decomposition and aggregation of selected subbands is performed to obtain an accurate measure of quality. The processing time is reduced in comparison to that required by other methods for generating measures of quality.

Claims

1. A method for determining a measure of quality for an image Y, characterizing a similarity between the image Y and a reference image X having same resolution, the method comprising:

(a) determining a number of levels of decomposition, N, to be applied to the image X and the image Y;

(b) applying an N level multiresolution decomposition, comprising levels 1, 2, . . . i, i+1, . . . N, to the image X and the image Y, producing respective approximation subbands containing main contents of the image X and image Y, and respective detail subbands containing edges of the image X and image Y;

(c) applying an image quality metric (IQM) to said respective approximation subbands of the image X and the image Y to produce an approximation quality measure, characterizing similarity between the main contents of the image X and the image Y;

(d) processing the respective detail subbands of the image X and the image Y to produce respective edge maps for the image X and the image Y, characterizing edges of the image X and the image Y respectively;

(e) applying the IQM to the respective edge maps to produce an edge quality measure, characterizing similarity between the edges of the image X and the image Y; and

(f) processing the approximation quality measure and the edge quality measure to determine the measure of quality.

2. The method of claim 1, wherein the step (a) comprises determining the number of levels of decomposition N as a function of one or more of a resolution of the image Y, a viewing distance for the image Y, and the IQM.

3. The method of claim 1, wherein the step (a) further comprises determining the number of levels of decomposition N as a function of a minimum size of an approximation subband, S, which produces a substantially peak response for human visual system.

4. The method of claim 3, wherein the step (a) further comprises determining the S as follows:

determining k, a ratio between the viewing distance and a height of a device on which the image Y is displayed; and

determining the S as a ratio between a predetermined number and the k.

5. The method of claim 1, wherein the step (b) further comprises:

for a level 1, applying the multiresolution decomposition to the Image X and the image Y producing respective intermediate subbands at the level 1 for processing at a level 2; and

for a level i, with i ranging from 2 to N, applying the multiresolution decomposition to only selected intermediate subbands produced by the multiresolution decomposition performed at the level i−

1.

6. The method of claim 5, further comprising determining the selected intermediate subbands based on a number of the intermediate subbands required for achieving a required accuracy in determining the measure of quality.

7. The method of claim 5, further comprising aggregating one or more of the selected intermediate subbands of the image X and the image Y produced by the multiresolution decomposition performed at a level j, with j ranging from 1 to N.

8. The method of claim 7, further comprising aggregating one or more of selected detail subbands of the image X and the image Y respectively, produced at level N, with said one or more of the selected intermediate subbands produced at said each level j for the image X and the image Y respectively.

9. The method of claim 1, wherein the approximation quality measure is an approximation quality map, and the edge quality measure is an edge quality map, and the step (f) further comprises:

generating a contrast map, including assigning corresponding values to pixels of the approximation subband and the edge map of the image X and the image Y according to their respective importance to human visual system;

performing weighted pooling of the approximation quality map using the contrast map to produce an approximation quality score;

performing weighted pooling of the edge quality map using the contrast map to produce an edge quality score; and

combining the approximation quality score with the edge quality score to determine the measure of quality.

10. The method of claim 1, wherein the steps (c) and (e) comprise applying the IQM, which is one of the following:

a structural similarity (SSIM) IQM;

an Absolute Difference (AD) IQM;

a peak-signal-to-noise ratio (PSNR) IQM;

or

a Visual Information Fidelity (VIF) IQM.

11. The method of claim 1, wherein the step (b) comprises applying an N level discrete wavelet transform (DWT).

12. A system for determining a measure of quality for an image Y, characterizing a similarity between the image Y and a reference image X having same resolution, the system comprising:

a processor; and

a non-transitory computer readable storage medium having computer readable instructions stored thereon for execution by the processor, causing the processor to;

(a) determine a number of levels of decomposition, N, to be applied to the image X and the image Y;

(b) apply an N level multiresolution decomposition, comprising levels 1, 2, . . . i, i+1, . . . N, to the image X and the image Y, producing respective approximation subbands containing main contents of the image X and image Y, and respective detail subbands containing edges of the image X and image Y;

(c) apply an image quality metric (IQM) to said respective approximation subbands of the image X and the image Y to produce an approximation quality measure, characterizing similarity between the main contents of the image X and the image Y;

(d) process the respective detail subbands of the image X and the image Y to produce respective edge maps for the image X and the image Y, characterizing edges of the image X and the image Y respectively;

(e) apply the IQM to the respective edge maps to produce an edge quality measure, characterizing similarity between the edges of the image X and the image Y; and

(f) process the approximation quality measure and the edge quality measure to determine the measure of quality.

13. The system of claim 12, wherein the computer readable instructions further cause the processor to determine the number of levels of decomposition N as a function of one or more of a resolution of the image Y, a viewing distance for the image Y, and the IQM.

14. The system of claim 12, wherein the computer readable instructions further cause the processor to determine the number of levels of decomposition N as a function of a minimum size of an approximation subband, S, which produces a substantially peak response for human visual system.

15. The system of claim 14, wherein the computer readable instructions further cause the processor to determine the S as follows:

to determine k, a ratio between the viewing distance and a height of a device on which the image Y is displayed; and

to determine the S as a ratio between a predetermined number and the k.

16. The system of claim 12, wherein the computer readable instructions further cause the processor to:

apply, for a level 1, the multiresolution decomposition to the Image X and the image Y to produce respective intermediate subbands at the level 1 for processing at a level 2; and

apply, for a level i, with i ranging from 2 to N, the multiresolution decomposition to only selected intermediate subbands produced by the multiresolution decomposition performed at the level i−

1.

17. The system of claim 16, wherein the computer readable instructions further cause the processor to determine the selected intermediate subbands based on a number of the intermediate subbands required for achieving a required accuracy in determining the measure of quality.

18. The system of claim 16, wherein the computer readable instructions further cause the processor to aggregate one or more of the selected intermediate subbands of the image X and the image Y produced by the multiresolution decomposition performed at a level j, with j ranging from 1 to N.

19. The system of claim 18, wherein the computer readable instructions further cause the processor to aggregate one or more of selected detail subbands of the image X and the image Y respectively, produced at level N, with said one or more of the selected intermediate subbands produced at said each level j for the image X and the image Y respectively.

20. The system of claim 12, wherein the approximation quality measure is an approximation quality map, and the edge quality measure is an edge quality map, and wherein the computer readable instructions further cause the processor to:

generate a contrast map, including assigning corresponding values to the pixels of the approximation subband and the edge map of the image X and the image Y according to their respective importance to human visual system;

perform weighted pooling of the approximation quality map using the contrast map to produce an approximation quality score;

perform weighted pooling of the edge quality map using the contrast map to produce an edge quality score; and

combine the approximation quality score with the edge quality score to determine the measure of quality.

21. The system of claim 12, wherein the computer readable instructions further cause the processor to apply the IQM, which is one of the following:

a structural similarity (SSIM) IQM;

an Absolute Difference (AD) IQM;

a peak-signal-to-noise ratio (PSNR) IQM;

or

a Visual Information Fidelity (VIF) IQM.

22. The system of claim 12, wherein the N level multiresolution decomposition is an N level discrete wavelet transform (DWT).