Image optimization during facial recognition
AssigneeGoogle Inc.
InventorUriel Gerardo Rodriguez
Life of this patent
Estimating the term…
Abstract
Described is a technique for optimizing an image for facial detection. More specifically, described is a process of predicting the location of a face within an image and adjusting image settings based on at least a portion of the predicted location of the face. An image may be adjusted based on the characteristics of a metering region, which may be selected prior to performing facial detection. For example, the metering region may be a specified shape with dimensions equal to a certain percentage of the input image and placed at a specified location. The result of using such a metering region is that the image adjustments may be based on a portion of the face, and therefore, may be optimized for facial detection.
Claims20
A method for a device to perform facial detection, comprising:
- capturing an image;
- executing a facial detection algorithm on the image a first time;
- determining that a face is not detected within the image based upon the execution the first time;
- selecting a metering region within a portion of the image;
- adjusting the image based on the metering region;
- and
- detecting a face by executing the facial detection algorithm on the adjusted image a second time;
- and the method further comprising selecting a first metering region and wherein the execution the first time is based on the first metering region and a size of the first metering region is larger than a size of the metering region within the portion of the image.
A device performing facial detection, comprising:
- a camera for capturing an image;
- a display previewing the captured image;
- and
- a processor configured to:
- execute a facial detection algorithm on the image a first time;
- determine that a face is not detected within the image based upon the execution the first time;
- select a metering region within a portion of the image;
- adjust the image based on the metering region;
- detect a face by executing the facial detection algorithm on the adjusted image a second time;
- and
- select a first metering region and wherein the execution the first time is based on the first metering region and a size of the first metering region is larger than a size of the metering region within the portion of the image.
A system comprising:
- one or more computers and one or more storage devices storing instructions which, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
- capturing an image;
- executing a facial detection algorithm on the image a first time;
- determining that a face is not detected within the image based upon the execution the first time;
- selecting a metering region within a portion of the image;
- adjusting the image based on the metering region;
- detecting a face by executing the facial detection algorithm on the adjusted image a second time;
- and
- selecting a first metering region and wherein the execution the first time is based on the first metering region and a size of the first metering region is larger than a size of the metering region within the portion of the image.
Dependencies are inferred from the claim text.