Automatic white-balance (AWB) for a camera system
This document describes techniques and apparatuses for automatic white-balance for a camera system. The techniques and apparatuses utilize a precursor image to detect one or more detected faces and determine a tone. The camera system retrieves tonal data based on a group of images determined to contain a same face as the detected face. Based on this tonal data, a difference in white balance is determined based on the difference in tone of the detected face within the precursor image and the associated tonal data. Camera settings are adjusted based on the difference in white balance to enable capture of an image having an improved tone.
1 . A method for automatic white-balance (AWB) in a camera system of an electronic device, the method comprising:
detecting a first human face within a precursor image;
determining a first tone of the first detected human face within the precursor image;
retrieving first tonal data associated with the detected first human face, the first tonal data determined from a group of previous images captured in previous ambient conditions, the previous images determined to contain a same human face as the first detected human face;
determining, based on the first tonal data, a first difference in white-balance (WB) between the first tone of the first detected human face within the precursor image and the first tonal data; and
adjusting camera settings based on the first difference in WB, the adjusting enabling capture of an image having an improved tone, the improved tone more-closely matching the first tonal data than the first tone.
2 . A method as in claim 1 , further comprising:
detecting an additional human face within the precursor image;
determining an additional tone of the additional detected human face within the precursor image;
retrieving additional tonal data associated with the additional detected human face, the additional tonal data associated with the additional detected human face determined from another group of previous images captured in previous ambient conditions, the other group of previous images determined to contain a same human face as the additional detected human face;
determining, based on the additional tonal data associated with the additional detected human face, an additional difference in AWB between the additional tone of the additional detected human face within the precursor image and the additional tonal data associated with the additional detected human face; and
wherein adjusting camera settings is based on the first difference in WB and the additional difference in WB.
3 . A method as in claim 2 , further comprising:
determining a first priority value of the first detected human face within the precursor image; and
determining an additional priority value of the additional detected human face within the precursor image,
wherein adjusting camera settings is further based on a weighted sum of the first difference in WB weighted by the first priority value and the additional difference in WB weighted by the additional priority value.
4 . A method as in claim 3 , wherein:
determining the first priority value is based on a first size of the first detected human face within the precursor image; and
determining the additional priority value is based on a size of the additional detected human face within the precursor image.
5 . A method as in claim 3 , wherein:
determining the first priority value is based on a first determined face-frequency value, the first determined face-frequency value based on a quantity of previous images in the group of previous images that are determined to contain a same human face as the first detected human face; and
determining the additional priority value is based on an additional determined face-frequency value of the additional detected human face, the additional determined face-frequency value of the additional detected human face based on a quantity of previous images in the other group of previous images that are determined to contain a same human face as the additional detected human face.
6 . A method as in claim 2 , wherein:
detecting an additional human face includes detecting up to 19 human faces; and
determining an additional priority value includes determining up to 19 priority values.
7 . A method as in claim 1 , wherein adjusting camera settings causes the electronic device to capture a first image having the first detected human face with an improved tone, and further comprising:
detecting an additional human face within the precursor image;
determining an additional tone of the additional detected human face within the precursor image;
retrieving additional tonal data associated with the additional detected human face, the additional tonal data associated with the additional detected human face determined from another group of previous images captured in previous ambient conditions, the other previous images determined to contain a same human face as the additional detected human face;
determining, based on the additional tonal data associated with the additional detected human face, an additional difference in AWB between the additional tone of the additional detected human face within the precursor image and the additional tonal data associated with the additional detected human face;
adjusting camera settings based on the additional difference in WB causing the electronic device to capture an additional image having the additional detected human face with another improved tone; and
providing the first and additional images to an image-merging module to produce a single image incorporating the first image for the first detected human face and the additional image for the additional detected human face.
8 . A method as in claim 1 , wherein the first tonal data includes a confidence value, the confidence value based on:
a face size of the same human face as the first detected human face within the previous images determined to contain a same human face as the first detected human face; or
ambient light conditions within the previous images determined to contain a same human face as the first detected human face.
9 . A method as in claim 8 , wherein determining the first difference in WB is based on filtered first tonal data, the filtered first tonal data being a subset of the first tonal data having been filtered by the confidence value.
10 . A method as in claim 8 , wherein determining the first difference in WB is based on a weighted sum of the first tonal data weighted by the confidence value.
11 . A method as in claim 1 , wherein detecting the first human face within the precursor image is initiated by an actuator.
12 . A method as in claim 1 , wherein adjusting camera settings causes the electronic device to capture an image having the improved tone.
13 . A method as in claim 12 , further comprising providing the image having the improved tone to a display.
14 . A method as in claim 1 , wherein adjusting camera settings includes adjusting:
a red sensor gain;
a green sensor gain; or
a blue sensor gain.
15 . A method as in claim 1 , wherein detecting a first human face includes using a low-resolution sensor.
16 . A device comprising:
a processor; and
a non-transitory computer-readable media comprising instructions which, when executed by the processor, cause the processor to carry out operations comprising:
detecting a first human face within a precursor image;
determining a first tone of the first detected human face within the precursor image;
retrieving first tonal data associated with the detected first human face, the first tonal data determined from a group of previous images captured in previous ambient conditions, the previous images determined to contain a same human face as the first detected human face;
determining, based on the first tonal data, a first difference in white-balance (WB) between the first tone of the first detected human face within the precursor image and the first tonal data; and
adjusting camera settings based on the first difference in WB, the adjusting enabling capture of an image having an improved tone, the improved tone more-closely matching the first tonal data than the first tone.
17 . The device of claim 16 , the operations further comprising:
detecting an additional human face within the precursor image;
determining an additional tone of the additional detected human face within the precursor image;
retrieving additional tonal data associated with the additional detected human face, the additional tonal data associated with the additional detected human face determined from another group of previous images captured in previous ambient conditions, the other group of previous images determined to contain a same human face as the additional detected human face;
determining, based on the additional tonal data associated with the additional detected human face, an additional difference in AWB between the additional tone of the additional detected human face within the precursor image and the additional tonal data associated with the additional detected human face; and
wherein adjusting the camera settings is based on the first difference in WB and the additional difference in WB.
18 . The device of claim 17 , the operations further comprising determining a first priority value of the first detected human face within the precursor image and an additional priority value of the additional detected human face within the precursor image, wherein adjusting the camera settings is based on the first priority value and the additional priority value.
19 . The device of claim 18 , wherein adjusting the camera settings is based on a combination of the first difference in WB and the additional difference in WB, the combination being determined using the first priority value and the additional priority value.
20 . A non-transitory computer-readable storage medium comprising instructions which, when executed by one or more processors, cause the one or more processors to carry out functions comprising:
detecting a first human face within a precursor image;
determining a first tone of the first detected human face within the precursor image;
retrieving first tonal data associated with the detected first human face, the first tonal data determined from a group of previous images captured in previous ambient conditions, the previous images determined to contain a same human face as the first detected human face;
determining, based on the first tonal data, a first difference in white-balance (WB) between the first tone of the first detected human face within the precursor image and the first tonal data; and
adjusting camera settings based on the first difference in WB, the adjusting enabling capture of an image having an improved tone, the improved tone more-closely matching the first tonal data than the first tone.