Image enhancement and repair using sample data from other images

Patent metadata

Field	Value
Publication number	US-9626747-B2
Application number	US-201213454782-A
Country	US
Kind code	B2
Filing date	Apr 24, 2012
Priority date	Apr 24, 2012
Publication date	Apr 18, 2017
Grant date	Apr 18, 2017

Abstract

A image manipulation technique allows a user to correct an image using samples obtained from other images. These samples may be obtained from one or more other images in a library of images. Matching techniques may identify an image that best matches the image to be corrected, or may aggregate or average multiple images that are identified as containing an area corresponding to the area to be corrected. Identification of the image or images to use as the source of the samples may be automatic or manual. The images may be from a library of images under the control of the user or from a library of images maintained by another person or service provider. Application of the samples to correct the image may be manually or automatically directed.

First claim

What is claimed is:

1. A computer-implemented method for image modification, comprising:
selecting, by one or more processors, a first region of a first image;
identifying, automatically, from a database of images, one or more second images that have a region corresponding to the first region, wherein the one or more processors are communicatively coupled to the database via a communications network and wherein identifying the one or more second images comprises:
ascertaining geodata information associated the first image;
ascertaining an image capture condition associated with the first image; and
identifying each of the one or more second images based, at least in part, on the geodata information and the image capture condition; and

modifying, automatically, the first region by replacing data in the first region with data from the corresponding region of at least one of the one or more second images.

2. The method of claim 1 , wherein the image capture condition comprises one or more of lighting information associated with the first image and a resolution associated with the first image.

3. The method of claim 1 , wherein selecting a first region of a first image further comprises analyzing, automatically, the first region to identify an object.

4. The method of claim 3 , wherein identifying, automatically, one or more second images comprises selecting one or more second images having represented therein the object.

5. The method of claim 1 , wherein identifying, automatically, from a database of images, one or more second images comprises:
searching the database of images for images having a region corresponding the first region, wherein searching the database is constrained by one or more predetermined criteria.

6. The method of claim 5 , wherein the predetermined criteria comprises one or more of the geodata information associated with the first image and the image capture condition associated with the first image.

7. The method of claim 6 , wherein the image capture condition comprises lighting information associated with the first image.

8. The method of claim 5 , wherein searching the database is constrained by a temporal window, wherein the first image was captured during the temporal window.

9. The method of claim 5 , wherein searching the database is constrained by label information associated with the first region.

10. The method of claim 1 , wherein modifying, automatically, the first region comprises:
combining, automatically, each of the corresponding regions from the one or more second images to generate a combined region; and
modifying, automatically, the first region based, at least in part, on the combined region.

11. The method of claim 10 , wherein combining, automatically, each of the corresponding regions from the one or more second images to generate a combined region comprises:
averaging the corresponding regions from the one or more second images to generate the combined region.

12. The method of claim 1 , wherein selecting a first region comprises:
detecting and selecting a facial region of the first image.

13. A non-transitory program storage device, readable by a programmable control device and comprising instructions stored thereon to cause the programmable control device to:
receive an indication that identifies a first region of a first image;
identify, from a database of images, one or more second images that have a region corresponding to the first region, wherein the one or more processors are communicatively coupled to the database via a communications network and wherein the instructions to cause the programmable control device to identify the one or more second images comprise instructions to cause the programmable control device to:
ascertain geodata information associated the first image;
ascertain an image capture condition associated with the first image; and
identify each of the one or more second images based, at least in part, on the geodata information and the image capture condition; and

modify the first region by replacing data in the first region with data from the corresponding region of at least one of the one or more second images.

14. The non-transitory program storage device of claim 13 , wherein the image capture condition comprises one or more of lighting information associated with the first image and a resolution associated with the first image.

15. The non-transitory program storage device of claim 13 , wherein the instructions to cause the programmable control device to receive an indication that identifies a first region of a first image further comprise instructions to cause the programmable control device to analyze the first region to identify an object.

16. The non-transitory program storage device of claim 15 , wherein the instructions to cause the programmable control device to identify one or more second images comprise instructions to cause the programmable control device to select one or more second images having represented therein the object.

17. The non-transitory program storage device of claim 16 , wherein the instructions to cause the programmable control device to modify the first region comprise instructions to cause the programmable control device to:
combine each of the corresponding regions from the one or more second images to generate a combined region; and
modify the first region based, at least in part, on the combined region.

18. A programmable device, comprising:
a programmable control device;
a memory coupled to the programmable control device; and
software stored in the memory, the software comprising instructions that cause the programmable control device to:
receive an indication that identifies a first region of a first image;
identify, automatically, one or more second images from a collection of images that have a region corresponding to the first region, wherein the one or more processors are communicatively coupled to the database via a communications network and wherein the instructions that cause the programmable control device to identify the one or more second images from a collection of images comprise instructions that cause the programmable control device to:
ascertain geodata information associated the first image;
ascertain an image capture condition associated with the first image; and
identify each of the one or more second images based, at least in part, on the geodata information and the image capture condition; and

modify the first region automatically by replacing data in the first region with data from the corresponding region of at least one of the one or more second images.

19. The programmable device of claim 18 , wherein the image capture condition comprises one or more of lighting information associated with the first image and a resolution associated with the first image.

20. The programmable device of claim 18 , wherein the instructions that cause the programmable control device to receive an indication that identifies a first region of a first image comprise instructions that cause the programmable control device to:
identify a first object represented in the first image; and
automatically select the first region as a region of the first image including a representation of the first object.

21. The programmable device of claim 20 , wherein the instructions that cause the programmable control device to identify, automatically, one or more images from a collection of images comprise instructions that cause the programmable control device

Assignees

• Dellinger Richard R
• Sabatelli Alessandro F
• Apple Inc

Inventors

• Dellinger Richard R
• Sabatelli Alessandro F

Classifications

• G06T2207/30216

  Redeye defect · CPC title

• G06F16/51

  Indexing; Data structures therefor; Storage structures · CPC title

• G06F16/5854

  using shape and object relationship · CPC title

• G06F16/5866

  using information manually generated, e.g. tags, keywords, comments, manually generated location and time information · CPC title

• G06T2207/30201

  Face · CPC title