Monocular camera defocus face measuring
A device that measures a size of a user's face, referred to as face scaling, using a monocular camera. Depth is calculated from sparse feature points. A face mesh is used to improve the estimation accuracy. A processing pipeline detects face features by applying a face landmark detection algorithm to find the important face feature points such as the eyes, nose, and mouth. The processing pipeline estimates feature points depth using depth obtained through image defocus. The processing pipeline further scales the face using an estimated depth of the face features.
1 . A device, comprising:
a monocular camera configured to capture images of a face, the captured images comprising a plurality of face features;
a processor configured to determine a distance between the monocular camera and the face, the processor configured to:
determine the plurality of face features in the captured images;
determine a scale of the face as a function of the determined plurality of face features by using a manual focus feature of the device to process a focal stack of the captured images based on the captured images, wherein each said captured image of the focal stack has a focal plane and the processor is configured to process the focal planes to determine the scale of the face;
apply a two-dimensional (2D) facial landmark detection algorithm to an in-focus one of said captured images to detect 2D facial landmarks and determine a focus distance between the camera and the face; and
estimate a three-dimensional (3D) mesh of the face of a unit size corresponding to the detected 2D facial landmarks.
2 . The device of claim 1 , wherein the processor is configured to use an auto-focus feature of the device to determine the scale of the face, wherein the auto-focus feature is configured to apply the two-dimensional (2D) facial landmark detection algorithm to an in-focus one of said captured images to detect 2D facial landmarks and determine an auto-focus distance between the camera and the face.
3 . The device of claim 1 , wherein the processor is configured to determine a distance between two of the plurality of face features to determine the scale of the face by combining the estimated 3D face mesh and the focus distance.
4 . The device of claim 1 , wherein the device further comprises a display and wherein the device is configured to produce and display a product image in association with the face on the display in accordance with the determined scale of the face.
5 . The device of claim 4 , wherein the processor is configured to present different sizes of the product on the display that is in accordance with the determined scale of the face.
6 . A method of scaling a face, comprising:
capturing images using a monocular camera;
determining a plurality of face features in the captured images;
determining a distance between the monocular camera and the face; and
determining a scale of the face as a function of the determined plurality of face features by processing a focal stack of the captured images using a manual focus feature and based on the captured images, wherein each said captured image of the focal stack has a focal plane, wherein the determining the scale of the face comprises processing the focal planes;
applying a 2D facial landmark detection algorithm to an in-focus one of said captured images to detect 2D facial landmarks and determine a focus distance between the camera and the face; and
estimating a 3D mesh of the face of a unit size corresponding to the detected 2D facial landmarks and determining a distance between two of the plurality of face features to determine the scale of the face by combining the estimated 3D face mesh and the focus distance.
7 . The method of claim 6 , wherein the determining the scale of the face comprises:
determining an auto-focus distance between the camera and the face.
8 . The method of claim 7 , wherein the determining the scale of the face comprises:
combining the estimated 3D face mesh and the auto-focus distance.
9 . A non-transitory computer-readable storage medium that stores instructions that when executed by a processor of a device comprising a monocular camera configured to capture images of a face, the captured images including a plurality of face features to determine a distance between the camera and the face, the instructions operable to determine the plurality of face features in the captured images and determine a scale of the face as a function of the determined plurality of face features by:
processing a focal stack of the captured images using a manual focus feature and based on the captured images, wherein each said captured images of the focal stack has a focal plane, wherein the determining the scale of the face comprises processing the focal planes;
applying a 2D facial landmark detection algorithm to an in-focus one of said captured images to detect 2D facial landmarks and determine a focus distance between the camera and the face; and
estimating a 3D mesh of the face of a unit size corresponding to the detected 2D facial landmarks and determining a distance between two of the plurality of face features to determine the scale of the face by combining the estimated 3D face mesh and the focus distance.