Method and system for smart group portrait
AssigneeQUALCOMM Incorporated
InventorPia Zobel
Life of this patent
Estimating the term…
Abstract
Various systems and methods are provided for capturing an image of a group of individuals in a scene. Facial detection may be performed to identify one or more individuals of the group. One or more features of each identified individual are monitored to determine an image quality score for the individual, indicative of how the individual will appear in a captured image of the group. A determination is made as to whether the image quality score for the individual satisfies one or more image quality threshold values. If the image quality score for the individual satisfies the one or more threshold values, a sub-image may be captured of the individuals. Sub-images for each individual may be combined to form a single composite image of the group.
Claims20
A method for capturing an image of a group of individuals in a scene, the method comprising:
- performing facial detection to detect one or more individuals of the group;
- monitoring, for each detected individual, one or more features of the individual;
- determining an image quality score for each individual based upon the one or more features of the individual, the image quality score indicative of how the individual will appear in a captured image of the group;
- determining whether the image quality score for each individual is within a first threshold range, the first threshold range indicative of a range of smiles;
- capturing a sub-image of each individual when the image quality score for that individual is within the first threshold range, including capturing a first sub-image of a first individual when the image quality score for the first individual is within the first threshold range;
- continuing to monitor the one or more features of the first individual after the sub-image of the first individual is captured;
- capturing a second sub-image of the first individual if the image quality score for the first individual is greater than the image quality score for the first individual when the first sub-image was captured, the second sub-image replacing the first sub-image;
- and
- combining the captured sub-images to form a single composite image of the group.
An image capture system for capturing an image of a group of individuals in a scene, comprising:
- an image sensor configured to capture image data of the scene;
- a memory configured to store image data;
- at least one processor, configured to:
- receive image data of the scene from the image sensor;
- perform facial detection on the received image data to detect one or more individuals of the group in the scene;
- monitor, for each detected individual, one or more features of the individual;
- determine an image quality score for each individual based upon the one or more features of the individual, the image quality score indicative of how the individual will appear in a captured image of the group;
- determine whether the image quality score for each individual is within a first threshold range, the first threshold range indicative of a range of smiles;
- capture a sub-image of each individual when the image quality score for that individual is within the first threshold range, including capturing a first sub-image of a first individual when the image quality score for the first individual is within the first threshold range;
- continue to monitor the one or more features of the first individual after the sub-image of the first individual is captured;
- capture a second sub-image of the first individual if the image quality score for the first individual is greater than the image quality score for the first individual when the first sub-image was captured, the second sub-image replacing the first sub-image;
- and
- combine the captured sub-images to form a single composite image of the group.
Dependencies are inferred from the claim text.