Biometric aware object detection and tracking
The technology disclosed can provide methods and systems for identifying users while capturing motion and/or determining the path of a portion of the user with one or more optical, acoustic or vibrational sensors. Implementations can enable use of security aware devices, e.g., automated teller machines (ATMs), cash registers and banking machines, other secure vending or service machines, security screening apparatus, secure terminals, airplanes, automobiles and so forth that comprise sensors and processors employing optical, audio or vibrational detection mechanisms suitable for providing gesture detection, personal identification, user recognition, authorization of control inputs, and other machine control and/or machine communications applications. A virtual experience can be provided to the user in some implementations by the addition of haptic, audio and/or other sensory information projectors.
1 . A method of authorizing a user to issue a command indicated by a gesture of a hand moving freely in 3D sensory space, the method including:
receiving a plurality of images of a hand captured in a three-dimensional (3D) sensory space;
obtaining at least one of: one or more scars of the hand; a vein pattern of the hand; and a palm print of the hand extracted from the images of the hand;
authenticating a user based on the at least one of: one or more scars of the hand; a vein pattern of the hand; and a palm print of the hand extracted from the images of the hand;
obtaining for the hand, a command determined from at least a subset of the plurality of images;
determining whether the user as authenticated based on the at least one of: one or more scars of the hand; a vein pattern of the hand; and a palm print of the hand extracted from the images is authorized to issue the command as determined from the at least a subset of the plurality of images; and
issuing the command when authorized to a security aware device, wherein the command indicates a financial transaction involving an account associated with the user as authenticated.
2 . The method of claim 1 , further including rejecting the command whenever the user as authenticated is determined unauthorized to issue the command.
3 . The method of claim 1 , further including triggering a response to gestures performed by an authenticated hand authorized to issue a command without triggering a response to gestures performed by non-authenticated hands.
4 . The method of claim 1 , further including authenticating a second hand captured in the plurality of images when the second hand belongs to a user authorized to issue commands.
5 . The method of claim 1 , further including extracting at least one of:
shape of the hand;
size of the hand;
measurements across a palm of the hand;
finger width at a first knuckle of the hand; and
complexion of the hand.
6 . The method of claim 1 , further including:
registering multiple images of different poses of the hand during a hand gesture.
7 . The method of claim 6 , wherein the multiple images of different poses of the hand include at least one of:
palm view of the hand;
backhand view of the hand; and
closed fist view of the hand.
8 . The method of claim 1 , further including:
responsive to the authenticating of the hand based on the at least one of: one or more scars of the hand; a vein pattern of the hand; and a palm print of the hand extracted from the images of the hand, interpreting one or more hand gestures based on specific interpretation criteria.
9 . The method of claim 1 , wherein the at least one of: one or more scars of the hand; a vein pattern of the hand; and a palm print of the hand are extracted from the images of the hand by processing that includes:
using at least one image characteristic of the images, determining an image property that specifies changes to the image characteristic across various image points;
determining variations to the image property across the various image points; and
based on the variations determined, identifying points of interest in the images that represent biometric features.
10 . The method of claim 9 , further including:
using a Hessian Matrix for determining changes to the image property across the various image points.
11 . The method of claim 9 , further including:
using eigenvalues and eigenvectors for identifying the points of interest.
12 . The method of claim 9 , wherein the image characteristic is pixel intensity.
13 . The method of claim 9 , wherein the image property is gradient of pixel intensity.
14 . The method of claim 9 , further including:
determining normalized biometric features by at least one of rotating, translating, and scaling biometric features.
15 . The method of claim 9 , wherein the determining of whether the hand is authorized to issue the command further includes:
comparing the biometric features to a stored biometric profile.
16 . The method of claim 15 , further including:
constructing a biometric profile based on the biometric features, including:
prompting a user to perform hand gestures in the 3D sensory space and capturing a plurality of images of the hand during the hand gestures;
processing one or more of the images to extract biometric features of the hand;
determining normalized biometric features by at least one of rotating, translating, and scaling biometric features;
registering multiple images of different poses of the hand during the hand gestures; and
storing the normalized biometric features and corresponding poses for recognizing gestures.
17 . The method of claim 1 , wherein the determining of whether the hand is authorized to issue the command further includes:
determining whether a user who performs a hand gesture has a role authorized to issue the command.
18 . The method of claim 1 , wherein a biometric profile is constructed at a first device and an authorized command is issued to a second device.
19 . A non-transitory, computer-readable medium having computer executable instructions for authorizing a user to issue a command indicated by a gesture of a hand moving freely in 3D sensory space, which instructions, when executed by one or more hardware processors, perform actions comprising:
receiving a plurality of images of a hand captured in a three-dimensional (3D) sensory space;
obtaining at least one of: one or more scars of the hand; a vein pattern of the hand; and a palm print of the hand extracted from the images of the hand;
authenticating a user based on the at least one of: one or more scars of the hand; a vein pattern of the hand; and a palm print of the hand extracted from the images of the hand;
obtaining for the hand, a command determined from at least a subset of the plurality of images;
determining whether the user as authenticated based on the at least one of: one or more scars of the hand; a vein pattern of the hand; and a palm print of the hand extracted from the images is authorized to issue the command as determined from the at least a subset of the plurality of images; and
issuing the command when authorized to a security aware device, wherein the command indicates a financial transaction involving an account associated with the user as authenticated.
20 . A computer system with one or more processors adapted to perform a method comprising:
receiving a plurality of images of a hand captured in a three-dimensional (3D) sensory space;
processing images of the hand to extract one or more biometric features of the hand including at least one of: one or more scars of the hand; a vein pattern of the hand; and a palm print of the hand;
authenticating a user based on the one or more biometric features of the hand as extracted;
processing a sequence of images of the plurality of images to interpret a hand gesture;
determining for the hand, a command indicated by the hand gesture;
determining whether the user as authenticated based on the one or more biometric features of the hand is authorized to issue the command; and
issuing the command when authorized to a security aware device, wherein the command indicates a financial transaction involving an account associated with the user as authenticated.