Quality evaluation

Patent metadata

Field	Value
Publication number	US-10424059-B2
Application number	US-201715700259-A
Country	US
Kind code	B2
Filing date	Sep 11, 2017
Priority date	Sep 11, 2017
Publication date	Sep 24, 2019
Grant date	Sep 24, 2019

Abstract

Implementations of the present disclosure relate to methods, systems, and computer program products for quality evaluation. In one implementation, a computer-implemented method is disclosed. In the method, a pattern period may be extracted from an image of a target object, the pattern period indicating a period of a pattern that is repeated in the image. A reference image may be generated by repeating the pattern based on the extracted pattern period. Quality of the target object may be evaluated by comparing the generated reference image and the image of the target object. In other implementations, a computer-implemented system and a computer program product for quality evaluation are disclosed.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
extracting a pattern period from an image of a target object, the pattern period indicating a period of a pattern that is repeated in the image, wherein extracting a pattern period comprises:
obtaining an initial period by a symmetric analysis to the image; and
obtaining the pattern period by refining an initial period based on a correlation analysis associated with the initial period, wherein obtaining the pattern period comprises:
selecting a current period from a range associated with the initial period;
obtaining a first sub-image and a second sub-image from the image by dividing the image with the current period; and
identifying the current period as the pattern period in response to a correlation occurring between the first sub-image and the second sub-image;

generating a reference image by repeating the pattern based on the pattern period; and
evaluating quality of the target object by comparing the reference image and the image of the target object.

2. The computer-implemented method of claim 1 , wherein the evaluating quality of the target object comprises:
aligning the reference image and the image;
detecting a defect area including a difference by comparing the aligned reference image and the image; and
evaluating the quality of the target object as qualified, in response to not detecting the defect area.

3. The computer-implemented method of claim 2 , wherein the quality comprises repairability of the target object, and evaluating the quality of the target object further comprises:
determining repairability of the target object based on a location of the defect area in the reference image, in response to detecting the defect area.

4. The computer-implemented method of claim 3 , wherein determining the repairability of the target object comprises:
detecting an intersection relationship between the location of the defect area and at least one boundary line of a reference pattern in the reference image; and
determining repairability of the target object based on the intersection relationship.

5. The computer-implemented method of claim 4 , wherein detecting the intersection relationship, further comprises:
obtaining, from the reference image, a block corresponding to the defect area along a direction with respect to a vertical direction and a horizontal direction of the image;
determining a projection of the block at one or more pixels along the direction, a value at the one or more pixels in the projection indicating accumulated values of the one or more pixels in a line crossing the one or more pixels along another direction of the vertical direction and the horizontal direction of the image; and
determining the intersection relationship based on whether a peak occurs in the projection.

6. The computer-implemented method of claim 5 , wherein determining repairability of the target object based on the intersection relationship further comprises:
evaluating the quality of the target object as repairable in response to no peak occurring in the projection along the vertical direction and the horizontal direction of the image; or
evaluating the quality of the target object as non-repairable in response to the peak occurring in the projection along one of the vertical direction and the horizontal direction of the image.

7. The computer-implemented method of claim 1 , further comprising:
evaluating the quality of a second image of a second target object by comparing the reference image and the second image of the second target object, wherein models of the target object and the second target object are the same.

8. A computer-implemented system, comprising a computer processor coupled to a computer-readable memory unit, the memory unit comprising instructions that when executed by the computer processor implements a method comprising:
extracting a pattern period from an image of a target object, the pattern period indicating a period of a pattern that is repeated in the image, wherein extracting a pattern period comprises:
obtaining an initial period by a symmetric analysis to the image; and
obtaining the pattern period by refining an initial period based on a correlation analysis associated with the initial period, wherein obtaining the pattern period comprises:
selecting a current period from a range associated with the initial period;
obtaining a first sub-image and a second sub-image from the image by dividing the image with the current period; and
identifying the current period as the pattern period in response to a correlation occurring between the first sub-image and the second sub-image;

generating a reference image by repeating the pattern based on the pattern period; and
evaluating quality of the target object by comparing the reference image and the image of the target object.

9. The computer-implemented system of claim 8 , wherein the evaluating quality of the target object comprises:
aligning the reference image and the image;
detecting a defect area including a difference by comparing the aligned reference image and the image; and
evaluating the quality of the target object as qualified, in response to not detecting the defect area.

10. The computer-implemented system of claim 9 , wherein the quality comprises repairability of the target object, and evaluating the quality of the target object further comprises:
determining repairability of the target object based on a location of the defect area in the reference image, in response to detecting the defect area.

11. The computer-implemented system of claim 10 , wherein determining the repairability of the target object comprises:
detecting an intersection relationship between the location of the defect area and at least one boundary line of a reference pattern in the reference image; and
determining repairability of the target object based on the intersection relationship.

12. The computer-implemented system of claim 11 , wherein detecting the intersection relationship, further comprises:
obtaining, from the reference image, a block corresponding to the defect area along a direction with respect to a vertical direction and a horizontal direction of the image;
determining a projection of the block at one or more pixels along the direction, a value at the one or more pixels in the projection indicating accumulated values of the one or more pixels in a line crossing the one or more pixels along another direction of the vertical direction and the horizontal direction of the image; and
determining the intersection relationship based on whether a peak occurs in the projection.

13. The computer-implemented system of claim 8 , wherein the method further comprises:
evaluating the quality of a second image of a second target object by comparing the reference image and the second image of the second target object, wherein models of the target object and the second target object are the same.

14. A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by an electronic device to cause the electronic device to perform actions of:
extracting a pattern period from an image of a target object, the pattern period indicating a period of a pattern that is repeated in the image, wherein extracting a pattern period comprises:
obtaining an initial period by a symmetric analysis to the image; and
obtaining the pattern period by refining an initial period based on a correlation analysis associated with the initial period, wherein obtaining

Assignees

• IBM

Inventors

• Huang Jing Chang
• Zhu Jun
• Yan jun chi
• Hu Guo Qiang

Classifications

• G06V10/54 Primary

  relating to texture · CPC title

• G06T7/001 Primary

  using an image reference approach · CPC title

• G06V10/42

  Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation · CPC title

• G06V10/993

  Evaluation of the quality of the acquired pattern · CPC title

• G06T2207/30121

  CRT, LCD or plasma display · CPC title