Intelligent auto cropping of digital images

Patent metadata

Field	Value
Publication number	US-10713469-B2
Application number	US-201916391578-A
Country	US
Kind code	B2
Filing date	Apr 23, 2019
Priority date	Apr 28, 2017
Publication date	Jul 14, 2020
Grant date	Jul 14, 2020

Abstract

Disclosed in some examples are methods, systems, computing devices, and machine readable mediums that provide for cropping systems that automatically crop digital images using one or more smart cropping techniques. Smart cropping techniques may include: cropping an image based upon emotion detection, cropping based upon facial recognition and matching, and cropping based upon landmark matching. In some examples, a single smart cropping technique may be utilized. In other examples, a combination of the smart cropping techniques may be utilized.

First claim

What is claimed is:

1. A machine-readable storage device, storing instructions, which when executed by a machine, cause the machine to perform operations for automatically cropping an image, the operations comprising:
receiving a first digital image;
detecting a face in the first digital image;
determining that the detected face in the first digital image matches a face from a second digital image previously stored in a data store;
determining that a landscape landmark displayed in the first digital image matches a landscape landmark displayed in a plurality of images of landscape landmarks stored in the data store; and
responsive to determining that the detected face in the first digital image matches the face from the second digital image previously stored in the data store and that the landscape landmark displayed in the first digital image matches the landscape landmark displayed in the plurality of images of landscape landmarks stored in the data store, cropping the first digital image based upon the detected face such that the detected face and the landscape landmark remains part of the cropped first digital image.

2. The machine-readable storage device of claim 1 , wherein the second digital image is a photo posted to a social networking service.

3. The machine-readable storage device of claim 2 , wherein the second digital image was posted to a social networking service account of a connection on the social networking service of a user that captured the first digital image.

4. The machine-readable storage device of claim 1 , wherein the operations further comprise:
detecting a second face in the first digital image;
determining that the detected second face in the first digital image matches a second face from the second digital image or a third digital image in the data store; and
cropping the first digital image based upon the detected face, the landscape landmark, and the detected second face such that the detected face, the landscape landmark, and the detected second face remain part of the cropped first digital image.

5. The machine-readable storage device of claim 1 , wherein the operations further comprise:
detecting a second face in the first digital image;
determining that the detected second face in the first digital image does not match any of a plurality of faces from a plurality of images previously stored in the data store; and
cropping the first digital image based upon the detected face, the landscape landmark, and the detected second face such that the detected face, and the landscape landmark remains part of the cropped first digital image, but the detected second face is cropped out.

6. The machine-readable storage device of claim 1 , wherein the operations of determining that the detected face in the first digital image matches the face from the second digital image comprises utilizing one of: eigen-faces, linear discriminant analysis, elastic bunch graph matching, or hidden Markov models to match the faces.

7. The machine-readable storage device of claim 1 , wherein the operations of cropping the first digital image based upon the detected face such that the detected face remains part of the cropped first digital image comprises cropping the first digital image such that the detected face and a body of a person associated with the detected face remain part of the cropped first digital image.

8. A computing device comprising:
a processor;
a memory, the memory storing instructions, which when executed by the processor, cause the computing device to perform operations comprising:
receiving a first digital image;
detecting a face in the first digital image;
determining that the detected face in the first digital image matches a face from a second digital image previously stored in a data store;
determining that a landscape landmark displayed in the first digital image matches a landscape landmark displayed in a plurality of images of landscape landmarks stored in the data store; and
responsive to determining that the detected face in the first digital image matches the face from the second digital image previously stored in the data store and that the landscape landmark displayed in the first digital image matches the landscape landmark displayed in the plurality of images of landscape landmarks stored in the data store, cropping the first digital image based upon the detected face such that the detected face and the landscape landmark remains part of the cropped first digital image.

9. The computing device of claim 8 , wherein the second digital image is a photo posted to a social networking service.

10. The computing device of claim 9 , wherein the second digital image was posted to a social networking service account of a connection on the social networking service of a user that captured the first digital image.

11. The computing device of claim 8 , wherein the operations further comprise:
detecting a second face in the first digital image;
determining that the detected second face in the first digital image matches a second face from the second digital image or a third digital image in the data store; and
cropping the first digital image based upon the detected face, the landscape landmark, and the detected second face such that the detected face, the landscape landmark, and the detected second face remain part of the cropped first digital image.

12. The computing device of claim 8 , wherein the operations further comprise:
detecting a second face in the first digital image;
determining that the detected second face in the first digital image does not match any of a plurality of faces from a plurality of images previously stored in the data store; and
cropping the first digital image based upon the detected face, the landscape landmark, and the detected second face such that the detected face, and the landscape landmark remains part of the cropped first digital image, but the detected second face is cropped out.

13. The computing device of claim 8 , wherein the operations of determining that the detected face in the first digital image matches the face from the second digital image comprises utilizing one of: eigen-faces, linear discriminant analysis, elastic bunch graph matching, or hidden Markov models to match the faces.

14. The computing device of claim 8 , wherein the operations of cropping the first digital image based upon the detected face such that the detected face remains part of the cropped first digital image comprises cropping the first digital image such that the detected face and a body of a person associated with the detected face remain part of the cropped first digital image.

15. A computer-implemented method for automatically cropping an image, the method comprising:
receiving a first digital image;
detecting a face in the first digital image;
determining that the detected face in the first digital image matches a face from a second digital image previously stored in a data store;
determining that a landscape landmark displayed in the first digital image matches a landscape landmark displayed in a plurality of images of landscape landmarks stored in the data store; and
responsive to determining that the detected face in the first digital image matches the face from the second digital image previously stored in the data store and that the landscape landmark displayed in the first digital image matches the landscape landmark displayed in the plurality of images of landscape landmarks stored in the data store, cropping the first digital image based upon the detected face such that the detected face and the landscape landmark remains part o

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Lee David Benjamin
• Kikin Gil Erez

Classifications

• G06V40/175 Primary

  Static expression · CPC title

• G06V40/161

  Detection; Localisation; Normalisation · CPC title

• G06V10/255

  Detecting or recognising potential candidate objects based on visual cues, e.g. shapes · CPC title

• G06T2210/22

  Cropping · CPC title

• G06T11/60

  Creating or editing images; Combining images with text · CPC title