Enhanced image capture
Disclosed are techniques that provide a “best” picture taken within a few seconds of the moment when a capture command is received (e.g., when the “shutter” button is pressed). In some situations, several still images are automatically (that is, without the user's input) captured. These images are compared to find a “best” image that is presented to the photographer for consideration. Video is also captured automatically and analyzed to see if there is an action scene or other motion content around the time of the capture command. If the analysis reveals anything interesting, then the video clip is presented to the photographer. The video clip may be cropped to match the still-capture scene and to remove transitory parts. Higher-precision horizon detection may be provided based on motion analysis and on pixel-data analysis.
1. A method performed by an image-capture device, the method comprising:
storing a plurality of still images captured by the image-capture device in temporal proximity to an image-capture command received by the image-capture device;
determining, in response to receiving the image-capture command, a first still image from the plurality of still images;
determining, for the first still image, a first score for a quality characteristic, the quality characteristic based on motion data and a face score;
determining, for a second still image from the plurality of still images, a second score for the quality characteristic;
determining that the second score for the quality characteristic is better than the first score for the quality characteristic; and
outputting, for display, the second still image in response to determining that the second score for the quality characteristic is better than the first score for the quality characteristic.
2. The method of claim 1 wherein a rate of capturing the plurality of still images is based, at least in part, on a level of resources available to the image-capture device.
3. The method of claim 2 wherein the level of resources available to the image-capture device corresponds to a battery level of the image-capture device.
4. The method of claim 1 wherein the face score is based on a weighted sum of two or more of a detected-smile score, an open-eyes score, or a face orientation score.
5. The method of claim 1 wherein the quality characteristic is further determined based on a privacy setting that corresponds to a list of contacts.
6. The method of claim 1 wherein the quality characteristic is further determined based on past behavior of a user of the image-capture device.
7. The method of claim 1 wherein determining that the second score for the quality characteristic is better than the first score for the quality characteristic is based on a recommendation received from a server remote from the image-capture device, the recommendation based on data provided by a general population of image-capture devices.
8. The method of claim 7 wherein the data of the general population of image-capture devices includes:
other image data from other captured images;
metadata associated with the capturing of the other image data; or
selection and interest scores.
9. The method of claim 1 , wherein the motion data indicates:
a motion of the image-capture device; and
an inter-frame motion, the inter-frame motion amongst frames corresponding to the plurality of still images.
10. An image-capture device comprising:
a display;
a buffer; and
a processing system configured to:
store a plurality of still images captured by the image-capture device in temporal proximity to an image-capture command received by the image-capture device;
capture, in response to receiving the image-capture command, a first still image;
determine, for the first still image, a first score for a quality characteristic, the quality characteristic based on motion data and a face score;
determine, for a second still image, from the plurality of still images, a second score for the quality characteristic;
determine that the second score for the quality characteristic is better than the first score for the quality characteristic; and
output, on the display, the second still image in response to determining that the second score for the quality characteristic is better than the first score for the quality characteristic.
11. The image-capture device of claim 10 wherein the image-capture device is a camera, a cellphone, or a tablet computer.
12. The image-capture device of claim 10 wherein a rate of capturing the plurality of still images is based, at least in part, on a level of resources available to the image-capture device.
13. The image-capture device of claim 10 wherein the first score for the quality characteristic and the second score for the quality characteristic are determined based on a stated preference of a user of the image-capture device or a past behavior of the user of the image-capture device.
14. The image-capture device of claim 10 further comprising:
a communications interface operatively connected to the processing system and configured for receiving a recommendation from a server remote from the image-capture device, the recommendation based on data provided by a general population of image-capture devices, and wherein determining that the second score for the quality characteristic is greater than the first score for the quality characteristic is based on a received recommendation.
15. The image-capture device of claim 14 wherein the communications interface is further configured for sending metadata associated with the capturing to the server remote from the image-capture device.
16. A method performed by an image-capture device comprising:
receiving, from a user, an explicit first command to enter a first mode to capture a plurality of still images before receiving an explicit second command to identify a first still image from the plurality of still images;
capturing and storing, in response to receiving the explicit first command, the plurality of still images;
receiving, from the user, the explicit second command;
identifying, in response to receiving of the explicit second command, a subset of the plurality of still images, the identified subset of the plurality still images captured in temporal proximity to the receiving of the explicit second command;
receiving, from the user, an explicit third command to enter a second mode to display the identified subset of the plurality of still images;
determining, in response to receiving the explicit third command, a first image quality characteristic of the first still image captured in response to receiving the explicit second command and a second image quality characteristic of a second still image, the first still image and the second still image included in the identified subset of the plurality of still images;
determining that the second image quality characteristic is better than the first image quality characteristic; and
displaying the identified subset of the plurality of still images, including the first still image and the second still image, the second still image highlighted to indicate that the second still image quality characteristic is better than the first still image quality characteristic.
17. The method of claim 16 , wherein the first image quality characteristic and the second quality characteristic are based on motion data and a face score.
18. The method of claim 17 , wherein the face score consists of a weighted-sum of two or more of a detected-smile score, an open-eyes score, or a face-orientation score.
19. The method of claim 17 , wherein the first image quality characteristic and the second quality characteristic are further based on a sharpness score.
20. The method of claim 17 , wherein the motion data indicates a motion of the image-capture device or an inter-frame motion amongst frames corresponding to the plurality of still images.
21. The method of claim 16 , wherein entering the first mode includes the image-capture device presenting a scene in a display of the image-capture device.
22. The method of claim 21 , further including presenting, in response to receiving the explicit second command, the first still image in the display.