Image capture techniques personalized to individual subjects being imaged
Methods and apparatuses are disclosed to personalize image capture operations of imaging equipment according to models that correspond uniquely to subjects being imaged. According to these techniques, a subject's face may be detected from a first image supplied by an image source and a first model of the subject may be developed from the detected face. The first model of the subject may be compared to another model of the subject developed from other images. Image adjustment parameters may be generated from a comparison of these models, which may control image adjustment techniques that are applied to the newly captured image of the subject. In this manner, aspects of the present disclosure may generate image capture operations that are tailored to characteristics of the subjects being imaged and avoid artifacts that otherwise could cause image degradation.
1. A method, comprising:
detecting a subject's face from a first image supplied by an image source,
developing a first model of the subject from the detected face,
comparing a first skin tone in the developed model to a second skin tone in a second model of the subject developed from other images;
generating, from the comparison of skin tones, image adjustment parameters and capture control parameters including control parameter(s) of high dynamic range (HDR) capture modes;
capturing a second image from the image source according to the capture control parameters for control of HDR capture modes; and
altering the second image supplied by the image source according to the image adjustment parameters.
2. The method of claim 1 , wherein the second subject model represents skin tone of the subject over a range of image brightnesses.
3. The method of claim 1 , wherein the second subject model represents geometry of the subject's face over a range of expressions.
4. The method of claim 1 , wherein the altering adjusts brightness of the first image according to image adjustment parameters generated from a comparison of skin tone information of the two subject models.
5. The method of claim 1 , wherein, when altering applies a color transform to the first image according to image adjustment parameters generated from a comparison of skin tone information of the first subject model and the second subject model.
6. The method of claim 1 , wherein the altering applies denoising filtering to the first image according to image adjustment parameters generated from a comparison of geometry of subject facial features of the two models.
7. The method of claim 1 , wherein the altering alters an expression of the subject in the first image according to a comparison of geometry of subject facial features of the two models.
8. The method of claim 1 , wherein the altering alters a physical characteristic of the subject as represented in the first image according to a comparison of geometry of subject facial features of the two models.
9. The method of claim 1 , wherein the altering increases resolution of the detected face within the first image according to the second model representing the subject.
10. The method of claim 1 , further comprising altering capture parameters of the image source based on a comparison of the two subject models.
11. The method of claim 1 , further comprising altering a plurality of images from the image source according to the image adjustment parameters and displaying the altered images in real-time with capture of the image by the image source.
12. The method of claim 1 , further comprising outputting the altered image to an image library.
13. The method of claim 1 , further comprising outputting the altered image to a videoconferencing application.
14. The method of claim 1 , wherein the first image is an infrared image, the other images include visible light images, and the image adjustment parameters include one or more color transforms to transform the infrared first image into a visible light image.
15. The method of claim 14 , wherein the image adjustment parameters include image shading effects from depth information derived from geometrical models representing the subject's face.
16. An apparatus, comprising:
an image source,
a face extractor having an input for a first image output by the image source,
a modeling unit having an input for cropped face data output by the face extractor,
a source of modeling data developed from other images
a model evaluation unit having for comparing a first skin tone in a model output by the modeling unit and a second skin tone in modeling data from the source to produce capture control parameters and image adjustment parameters including control parameter(s) of high dynamic range (HDR) capture modes, and
an image adjustment unit, having an input for a second frame of the image source captured according to the capture control parameters for control of HDR capture modes and the image adjustment parameters output by the model evaluation unit, and an output for an adjusted second image based on adjustments described by the image adjustment parameters.
17. The apparatus of claim 16 , wherein the source of modeling data comprises:
storage for an image library, and
a second face extractor having an input for second images stored in the image library, and
a second modeling unit having an input for cropped face data output by the second face extractor.
18. The apparatus of claim 16 , wherein the source of modeling data comprises a storage unit for storing the modeling data developed from other images.
19. A non-transitory computer readable medium storing program instructions that, when executed by a processing device, cause the device to perform a method, comprising:
detecting a subject's face from a first image supplied by an image source,
developing a first model of the subject from the detected face,
comparing a first skin tone in the developed model to a second skin tone in a second model of the subject developed from other images;
generating, from the comparison of skin tones, image adjustment parameters and capture control parameters including control parameter(s) of high dynamic range (HDR) capture modes;
capturing a second image from the image source according to the capture control parameters for control of HDR capture modes; and
altering the second image supplied by the image source according to the image adjustment parameters.
20. The medium of claim 19 , wherein the altering adjusts brightness of the first image according to image adjustment parameters generated from a comparison of skin tone information of the two subject models.
21. The medium of claim 19 , wherein, when altering applies a color transform to the first image according to image adjustment parameters generated from a comparison of skin tone information of the two models.
22. The medium of claim 19 , wherein the altering applies denoising filtering to the first image according to image adjustment parameters generated from a comparison of geometry of subject facial features of the two models.
23. The medium of claim 19 , wherein the altering alters an expression of the subject in the first image according to a comparison of geometry of subject facial features of the two models.
24. The medium of claim 19 , wherein the altering alters a physical characteristic of the subject as represented in the first image according to a comparison of geometry of subject facial features of the two models.
25. The medium of claim 19 , wherein the altering increases resolution of the detected face within the first image according to the second model representing the subject.
26. A method, comprising:
detecting a subject's face from a first image supplied by an image source,
developing a first model of the subject from the detected face,
comparing skin tone in the developed model to a second model of the subject developed from other images;
generating, from the comparison of skin tone, capture control parameters including control parameter(s) of high dynamic range (HDR) capture modes and image adjustment parameters, wherein the image adjustment parameters include image shading effects from depth information derived from geometrical models representing the subject's face; and
capturing a second image from the image source according to the capture control parameters for control of HDR capture modes;
altering the second image supplied by the image source according to the image adjustment parameters.
27. The method of claim 26 , wherein the second subject model represents a skin tone of the subject in a predetermined brightness condition, and the capture control parameters represent a difference between a skin tone represented in the first model and the second model.
28. The method of claim 26 , wherein the second subject model represents a geometry of the subject's face in a predetermined expression condition, and the capture control parameters represent a difference between an expression represented in the first model and the second model.