Personalizing image capture

Abstract

In some implementations, image data in a live image feed of a camera of an electronic device is received. The electronic device detects a face in the image data. Then, the electronic device determines that the detected face is important based on occurrence of the detected face in the previously captured images. The electronic device determines that an image of the detected face in the image data has at least a minimum level of quality. The electronic device then initiates capture of images using the camera at a time determined by the electronic device and ends the capture of images from the camera at a time determined by the electronic device.

1 . (canceled) 
     
     
         2 . A method performed by an electronic device, the method comprising:
 receiving, by the electronic device, image data in a live image feed of a camera of the electronic device;   detecting, by the electronic device, a face in the image data;   determining, by the electronic device, that the detected face is important based on occurrence of the detected face in previously captured images;   in response to determining that the detected face is classified as important, determining, by the electronic device, that an image of the detected face in the image data has at least a minimum level of quality;   in response to determining that the detected face image has at least a minimum level of quality, initiating, by the electronic device, capture of images using the camera at a time determined by the electronic device; and   ending, by the electronic device, the capture of images from the camera at a time determined by the electronic device.   
     
     
         3 . The method of  claim 2 , wherein the electronic device selects the time to initiate capture of images and the time to end capture of images without user interaction with the electronic device. 
     
     
         4 . The method of  claim 2 , wherein initiating capture of images comprises:
 determining that an image having at least the minimum level of quality has not been recorded for a particular identified face;   waiting until the quality score for the particular identified face in the live image feed of the camera satisfies a threshold prior to recording an additional image of the particular identified face; and   recording an additional image for the particular identified face in response to determining that the quality score for the particular identified face in the live image feed of the camera satisfies the threshold.   
     
     
         5 . The method of  claim 2 , wherein at least one of the images is captured in response to determining that the detected face has a level of quality that satisfies a threshold. 
     
     
         6 . The method of  claim 2 , wherein ending the capture of images comprises:
 ending the capture of images before capturing an image that includes a face image having at least the minimum quality score for all people in view of the camera.   
     
     
         7 . The method of  claim 2 , wherein determining that the detected face in the image data has at least a minimum level of quality comprises:
 determining a measure of similarity between a detected face of a person and a known image of the person.   
     
     
         8 . The method of  claim 2 , wherein determining that the detected face in the image data has at least a minimum level of quality comprises:
 determining whether a sharpness measure associated with the detected face satisfies a sharpness threshold;   determining whether the detected face is smiling; and   determining a level of quality for the detected face based on whether the sharpness measure and the smiling determination.   
     
     
         9 . The method of  claim 2 , wherein determining that the detected face is important based on occurrence of the detected face in previously-captured images comprises:
 obtaining data indicating facial features of people, in a set of people who are classified as being important to the user; and   determining that the facial features of the one or more people in the set of people match facial features of the detected face.   
     
     
         10 . The method of  claim 2 , wherein ending the capture of images comprises ending the capture of images a predetermined amount of time after initiating the capture of images.