Recommending location and content aware filters for digital photographs

1. A computer-implemented method for recommending camera settings comprising:

receiving a plurality of images and metadata associated with each of the plurality of images;

receiving human interaction scores for each of the plurality of images;

generating training data by classifying the plurality of images using the associated metadata and human interaction scores;

using the training data to derive an image classification model for predicting a human interaction score for an image having an unknown human interaction score;

in response to determining that a user is preparing to capture an image with a device, determining at least one recommended image capture setting using the image classification model; and

displaying the recommended image capture setting on a display of the device.

2. The method of claim 1 , wherein the generating training data by classifying the plurality of images using the associated metadata and human interaction scores further comprises:

determining a location for each of the plurality of images.

3. The method of claim 2 , wherein the generating training data by classifying the plurality of images using the associated metadata and human interaction scores further comprises:

determining a type of scene for each of the plurality of images; and

associating the determined type of scene with each of the plurality of images.

4. The method of claim 1 , wherein the image classification model for predicting a human interaction score for an image having an unknown human interaction score is a regression model having multiple vectors and multiple targets.

5. The method of claim 1 , wherein the using the training data to derive an image classification model for predicting a human interaction score for an image having an unknown human interaction score further comprises:

deriving a revised image classification model for predicting a human interaction score for an image having an unknown human interaction score by:

generating supplemental training data by:

selecting a first image, the first image being of a first scene type;

generating two or more test images from the selected first image, wherein each test image is generated using one of two or more different image capture settings;

receiving a human interaction score for each the test images from a set of human users;

associating the received human interaction scores with the each of the respective test images; and

updating the image classification model using the supplemental training data.

6. The method of claim 1 , wherein determining at least one recommended image capture setting using the image classification model further comprises:

capturing a first image in a field of view of the camera; and

determining an image capture setting for the first image using the image classification model.

7. The method of claim 1 , wherein the using the training data to derive an image classification model for predicting a human interaction score for an image having an unknown human interaction score further comprises:

deriving a revised image classification model for predicting a human interaction score for an image having an unknown human interaction score by:

receiving an input from a user, wherein the user accepts the recommended image capture setting;

capturing an image using the recommended image capture setting;

generating supplemental training data by:

obtaining a human interaction score for the captured image from one or more human users,

associating the human interaction score with the captured image; and

updating the image classification model using the supplemental training data.

8. A computer program product for recommending camera settings, the computer program product comprising:

a computer readable storage device storing computer readable program code embodied therewith, the computer readable program code comprising program code executable by a computer to perform a method comprising:

receiving a plurality of images and metadata associated with each of the plurality of images;

receiving human interaction scores for each of the plurality of images;

generating training data by classifying the plurality of images using the associated metadata and human interaction scores;

using the training data to derive an image classification model for predicting a human interaction score for an image having an unknown human interaction score;

in response to determining that a user is preparing to capture an image with a device, determining at least one recommended image capture setting using the image classification model; and

displaying the recommended image capture setting on a display of the device.

9. The computer program product of claim 8 , wherein the generating training data by classifying the plurality of images using the associated metadata and human interaction scores further comprises:

determining a location for each of the plurality of images.

10. The computer program product of claim 9 , wherein the generating training data by classifying the plurality of images using the associated metadata and human interaction scores further comprises:

determining a type of scene for each of the plurality of images; and

associating the determined type of scene with each of the plurality of images.

11. The computer program product of claim 8 , wherein the image classification model for predicting a human interaction score for an image having an unknown human interaction score is a regression model having multiple vectors and multiple targets.

12. The computer program product of claim 8 , wherein the using the training data to derive an image classification model for predicting a human interaction score for an image having an unknown human interaction score further comprises:

deriving a revised image classification model for predicting a human interaction score for an image having an unknown human interaction score by:

generating supplemental training data by:

selecting a first image, the first image being of a first scene type;

generating two or more test images from the selected first image, wherein each test image is generated using one of two or more different image capture settings;

receiving a human interaction score for each the test images from a set of human users;

associating the received human interaction scores with the each of the respective test images; and

updating the image classification model using the supplemental training data.

13. The computer program product of claim 8 , wherein determining at least one recommended image capture setting using the image classification model further comprises:

capturing a first image in a field of view of the camera; and

determining an image capture setting for the first image using the image classification model.

14. The computer program product of claim 8 , wherein the using the training data to derive an image classification model for predicting a human interaction score for an image having an unknown human interaction score further comprises:

deriving a revised image classification model for predicting a human interaction score for an image having an unknown human interaction score by:

receiving an input from a user, wherein the user accepts the recommended image capture setting;

capturing an image using the recommended image capture setting;

generating supplemental training data by:

obtaining a human interaction score for the captured image from one or more human users,

associating the human interaction score with the captured image; and

updating the image classification model using the supplemental training data.

15. A computer system for recommending camera settings, the computer system comprising: one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more tangible storage media for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:

receiving a plurality of images and metadata associated with each of the plurality of images;

receiving human interaction scores for each of the plurality of images;

generating training data by classifying the plurality of images using the associated metadata and human interaction scores;

using the training data to derive an image classification model for predicting a human interaction score for an image having an unknown human interaction score;

in response to determining that a user is preparing to capture an image with a device, determining at least one recommended image capture setting using the image classification model; and

displaying the recommended image capture setting on a display of the device.

16. The computer system of claim 15 , wherein the generating training data by classifying the plurality of images using the associated metadata and human interaction scores further comprises:

determining a location for each of the plurality of images.

17. The computer system of claim 16 , wherein the generating training data by classifying the plurality of images using the associated metadata and human interaction scores further comprises:

determining a type of scene for each of the plurality of images; and

associating the determined type of scene with each of the plurality of images.

18. The computer system of claim 15 , wherein the image classification model for predicting a human interaction score for an image having an unknown human interaction score is a regression model having multiple vectors and multiple targets.

19. The computer system of claim 15 , wherein the using the training data to derive an image classification model for predicting a human interaction score for an image having an unknown human interaction score further comprises:

deriving a revised image classification model for predicting a human interaction score for an image having an unknown human interaction score by:

generating supplemental training data by:

selecting a first image, the first image being of a first scene type;

generating two or more test images from the selected first image, wherein each test image is generated using one of two or more different image capture settings;

receiving a human interaction score for each the test images from a set of human users;

associating the received human interaction scores with the each of the respective test images; and

updating the image classification model using the supplemental training data.

20. The computer system of claim 15 , wherein determining at least one recommended image capture setting using the image classification model further comprises:

capturing a first image in a field of view of the camera; and

determining an image capture setting for the first image using the image classification model.