Optimal cropping of digital image based on professionalism score of subject

• US 10,043,240 B2
• Filed: 04/14/2016
• Issued: 08/07/2018
• Est. Priority Date: 04/14/2016
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Merhav, Uri, Shacham, Dan
• Primary Examiner(s): BEKELE, MEKONEN T
• Application Number:
  US15/098,931
• Publication Number:
  US 20170301063A1
• Time in Patent Office: 845 Days
• Field of Search: 382159, 382173, 382174
• CPC Class Codes: G06F 17/11 for solving equations , e.g. nonlinear equations, general mathematical optimization problems optimization specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06F 18/2148 characterised by the process organisation or structure, e.g. boosting cascade
• CPC Class Codes: G06F 18/2413 based on distances to training or reference patterns
• CPC Class Codes: G06F 18/2414 Smoothing the distance, e.g. radial basis function networks [RBFN]
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 2210/22 Cropping
• CPC Class Codes: G06T 3/4046 using neural networks
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/82 using neural networks
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]

Abstract

In an example embodiment, an optimal cropping of a digital image is determined. A machine learning algorithm is used to generate a professionalism score for the digital image, the utilizing a machine learning algorithm comprising a training mode where a plurality of sample images with labeled professionalism scores are used to train a classification function in a model that produces as professionalism score as output; and an analysis mode where the model is used to generate a professionalism score for the digital image. Then, the professionalism score is used as an input to a discrete variable optimization algorithm to determine an optimum cropped version of the digital image from a plurality of possible cropped versions of the digital image using the classification function.

Claims

1. A computerized method for automatically cropping a digital image to improve perceived professionalism of a subject of the image, the method comprising:

utilizing a machine learning algorithm to generate a professionalism score for the digital image, wherein the professionalism score indicates a perceived professionalism of a human depicted in the digital image, the utilizing a machine learning algorithm comprising;

a training mode where a plurality of sample images with labeled professionalism scores are used to train a classification function in a model that produces as professionalism score as output,

an analysis mode where the model is used to generate a professionalism score for the digital image; and

using the professionalism score for the digital image as an input to a discrete variable optimization algorithm to determine an optimum cropped version of the digital image from a plurality of possible cropped versions of the digital image using the classification function.

2. The method of claim 1, wherein the classification function contains one or more weights, and wherein the training of the classification function includes modifying the one or more weights.

3. The method of claim 1, wherein the discrete variable optimization algorithm is a deterministic optimization algorithm.

4. The method of claim 3, wherein the discrete variable optimization algorithm is a Gauss-Newton optimization algorithm.

5. The method of claim 3, wherein the discrete variable optimization algorithm is a Levenberg-Marquardt optimization algorithm.

6. The method of claim 1, wherein the discrete variable optimization algorithm is a stochastic algorithm.

7. The method of claim 6, wherein the stochastic algorithm is stochastic gradient descent.

8. A system comprising:

a computer readable medium having instructions stored there on, which, when executed by a processor, cause the system to;

utilize a machine learning algorithm to generate a professionalism score for a digital image, wherein the professionalism score indicates a perceived professionalism of a human depicted in the digital image, the utilizing a machine learning algorithm comprising;

a training mode where a plurality of sample images with labeled professionalism scores are used to train a classification function in a model that produces as professionalism score as output;

an analysis mode where the model is used to generate a professionalism score for the digital image; and

using the professionalism score for the digital image as an input to a discrete variable optimization algorithm to determine an optimum cropped version of the digital image from a plurality of possible cropped versions of the digital image using the classification function.

9. The system of claim 8, wherein the classification function contains one or more weights, and wherein the training of the classification function includes modifying the one or more weights.

10. The system of claim 8, wherein the discrete variable optimization algorithm is a deterministic optimization algorithm.

11. The system of claim 10, wherein the discrete variable optimization algorithm is a Gauss-Newton optimization algorithm.

12. The system of claim 10, wherein the discrete variable optimization algorithm is a Levenberg-Marquardt optimization algorithm.

13. The system of claim 8, wherein the discrete variable optimization algorithm is a stochastic algorithm.

14. The system of claim 13, wherein the stochastic algorithm is stochastic gradient descent.

15. A non-transitory machine-readable storage medium comprising instructions, which when implemented by one or more machines, cause the one or more machines to perform operations for automatically performing optimal cropping on a digital image to improve perceived professionalism of a subject of the image, the operations comprising:

utilizing a machine learning algorithm to generate a professionalism score for the digital image, wherein the professionalism score indicates a perceived professionalism of a human depicted in the digital image, the utilizing a machine learning algorithm comprising;

a training mode where a plurality of sample images with labeled professionalism scores are used to train a classification function in a model that produces as professionalism score as output;

an analysis mode where the model is used to generate a professionalism score for the digital image; and

using the professionalism score for the digital image as an input to a discrete variable optimization algorithm to determine an optimum cropped version of the digital image from a plurality of possible cropped versions of the digital image using the classification function.

16. The non-transitory machine-readable storage medium of claim 15, wherein the classification function contains one or more weights, and wherein the training of the classification function includes modifying the one or more weights.

17. The non-transitory machine-readable storage medium of claim 15, wherein the discrete variable optimization algorithm is a deterministic optimization algorithm.

18. The non-transitory machine-readable storage medium of claim 17, wherein the discrete variable optimization algorithm is a Gauss-Newton optimization algorithm.

19. The non-transitory machine-readable storage medium of claim 17, wherein the discrete variable optimization algorithm is a Levenberg-Marquardt optimization algorithm.

20. The non-transitory machine-readable storage medium of claim 15, wherein the discrete variable optimization algorithm is a stochastic algorithm.