Index image quality metric

Patent metadata

Field	Value
Publication number	US-9754237-B2
Application number	US-201514975655-A
Country	US
Kind code	B2
Filing date	Dec 18, 2015
Priority date	Dec 18, 2015
Publication date	Sep 5, 2017
Grant date	Sep 5, 2017

Abstract

A system and method that computes a quality score for an index image is disclosed. The method includes receiving an index image, computing a blurriness score of the index image based on variance associated with the index image, computing an image resolution score of the index image based on an area of the index image and a threshold area, computing a feature spread score for the index image using a first plurality of features associated with the index image, computing a feature uniqueness score for the index image using a description associated with each of a second plurality of features and determining a quality score for the index image using the blurriness score, the image resolution score, the feature spread score, and the feature uniqueness score.

First claim

What is claimed is:

1. A method comprising:
receiving, by one or more processors, an input image;
computing, by the one or more processors, a blurriness score for the input image based on a variance associated with the input image;
computing, by the one or more processors, an image resolution score for the input image based on an area of the input image;
computing, by the one or more processors, a feature spread score for the input image using a first plurality of features associated with the input image;
computing, by the one or more processors, a feature uniqueness score for the input image using a description associated with each of a second plurality of features;
determining, by the one or more processors, a quality score for the input image using the blurriness score, the image resolution score, the feature spread score, and the feature uniqueness score; and
generating a graphical user interface for presentation to a user, wherein the graphical user interface includes the input image and an indication of the quality score.

2. The method of claim 1 , wherein computing a blurriness score for the input image comprises:
convolving the input image using a Laplacian kernel;
calculating the variance associated with the input image using the convolved image; and
calculating the blurriness score for the input image using the variance.

3. The method of claim 1 , wherein computing an image resolution score for the input image comprises:
calculating an area of the input image; and
calculating the image resolution score for the input image using a ratio between the area and a threshold area.

4. The method of claim 1 , wherein computing a feature spread score for the input image comprises:
dividing the input image based on a grid;
determining a number of features in each cell of the grid; and
calculating the feature spread score for the input image using the number of features in each cell of the grid.

5. The method of claim 1 , wherein computing a feature uniqueness score for the input image comprises:
determining a descriptor associated with each of the second plurality of features;
generating clusters based on the descriptor associated with each of the second plurality of features; and
calculating the feature uniqueness score for the input image based on the clusters.

6. The method of claim 5 , wherein each of the second plurality of features is associated with a locator and the descriptor, the locator describing a location of the feature in the input image and the descriptor including a number.

7. The method of claim 1 ,
wherein the quality score indicates recognizability of the input image.

8. A system comprising:
one or more processors; and
a memory storing instructions comprising, which when executed by the one or more processors, cause the one or more processors to implement:
an image recognition application to receive an input image;
a blur estimation engine to compute a blurriness score for the input image based on a variance associated with the input image;
an image resolution engine to compute an image resolution score for the input image based on an area of the input image;
a feature spread engine to compute a feature spread score for the input image using a first plurality of features associated with the input image;
a feature uniqueness engine to compute a feature uniqueness score for the input image using a description associated with each of a second plurality of features;
a quality score generation engine to:
determine a quality score for the input image using the blurriness score, the image resolution score, the feature spread score, and the feature uniqueness score; and
generate a graphical user interface for presentation to a user, wherein the graphical user interface includes the input image and an indication of the quality score.

9. The system of claim 8 , wherein the blur estimation engine is configured to:
convolve the input image using a Laplacian kernel;
calculate the variance associated with the input image using the convolved image; and
calculate the blurriness score for the input image using the variance.

10. The system of claim 8 , wherein the image resolution engine is configured to:
calculate an area of the input image; and
calculate the image resolution score for the input image using a ratio between the area and a threshold area.

11. The system of claim 8 , wherein the feature spread engine is configured to:
divide the input image based on a grid;
determine a number of features in each cell of the grid; and
calculate the feature spread score for the input image using the number of features in each cell of the grid.

12. The system of claim 8 , wherein the feature uniqueness engine is configured to:
determine a descriptor associated with each of the second plurality of features;
generate clusters based on the descriptor associated with each of the second plurality of features; and
calculate the feature uniqueness score for the input image based on the clusters.

13. The system of claim 12 , wherein each of the second plurality of features is associated with a locator and the descriptor, the locator describing a location of the feature in the input image and the descriptor including a number.

14. The system of claim 8 ,
wherein the quality score indicates recognizability of the input image.

15. A non-transitory computer-readable medium storing instructions which, when executed by one or more processors, causes the one or more processors to:
receive an input image;
compute a blurriness score for the input image based on a variance associated with the input image;
compute an image resolution score for the input image based on an area of the input image;
compute a feature spread score for the input image using a first plurality of features associated with the input image;
compute a feature uniqueness score for the input image using a description associated with each of a second plurality of features;
determine a quality score for the input image using the blurriness score, the image resolution score, the feature spread score, and the feature uniqueness score; and
generate a graphical user interface for presentation to a user, wherein the graphical user interface includes the input image and an indication of the quality score.

16. The non-transitory computer-readable medium of claim 15 , wherein to compute a blurriness score for the input image the instructions cause the one or more processors to:
convolve the input image using a Laplacian kernel;
calculate the variance associated with the input image using the convolved image; and
calculate the blurriness score for the input image using the variance.

17. The non-transitory computer-readable medium of claim 15 , wherein to compute an image resolution score for the input image the instructions cause the one or more processors to:
calculate an area of the input image; and
calculate the image resolution score for the input image using a ratio between the area and a threshold area.

18. The non-transitory computer-readable medium of claim 15 , wherein to compute a feature spread score for the input image the instructions cause the one or more processors to:
divide the input image based on a grid;
determine a number of features in each cell of the grid; and
calculate the feature spread score for the input image using the number of features in each cell of the grid.

19. The non-transitory computer-readable medium of claim 15 , wherein to compute a feature uniqueness score for t

Assignees

• Bhat Srikrishna
• Pavani Sri Kaushik
• Garg Anshul
• Ricoh Co Ltd

Inventors

• Bhat Srikrishna
• Pavani Sri Kaushik
• Garg Anshul

Classifications

• G06T2207/30168

  Image quality inspection · CPC title

• G06T7/20

  Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51) · CPC title

• G06Q10/087 Primary

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title

• G06T7/0002 Primary

  Inspection of images, e.g. flaw detection · CPC title

• G06Q10/08724

  by shelf level inventory management, e.g. planograms · CPC title