US 12,283,127 B2
Method for obtaining data from an image of an object of a user that has a biometric characteristic of the user
Hardik Gupta, Jabalpur (IN); Satheesh Murugan, Ramapurum (IN); and Saneesh Bhaskaran, Bengaluru (IN)
Assigned to Identy Inc., Dover, DE (US)
Appl. No. 17/642,123
Filed by Identy Inc., Dover, DE (US)
PCT Filed Sep. 10, 2020, PCT No. PCT/IB2020/058405
§ 371(c)(1), (2) Date Mar. 10, 2022,
PCT Pub. No. WO2021/048777, PCT Pub. Date Mar. 18, 2021.
Claims priority of application No. 201941036800 (IN), filed on Sep. 12, 2019.
Prior Publication US 2022/0383663 A1, Dec. 1, 2022
Int. Cl. G06V 40/13 (2022.01); G06V 10/25 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 40/12 (2022.01); G06V 40/40 (2022.01)
CPC G06V 40/1312 (2022.01) [G06V 10/25 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 40/1365 (2022.01); G06V 40/1388 (2022.01); G06V 40/45 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A method for obtaining data from a single image of an object of a user that has a biometric characteristic of the user, wherein the object of the user comprises one or more of a fingerprint, a set of fingerprints, a palm, a face, an eye, or a bottom of a foot, the method comprising:
on a mobile device, performing the following operations:
obtaining, by an optical sensor of the mobile device, the single image of the object, wherein the single image contains either a spoof or a real object;
processing, in an identification operation, the single image to identify one or more of the object in the single image or a position of the object in the single image;
wherein processing the single image further comprises a liveliness-detection operation, comprising calculating at least one of:
a distance map representative of a distance of a first plurality of pixels to the optical sensor, the first plurality of pixels comprising at least a first portion of the object within the single image; or
a reflection pattern representative of light reflection associated with a second plurality of pixels comprising at least a second portion of the object within the single image;
and wherein processing the single image further comprises a comparison operation comprising comparing at least one of the calculated distance map or the calculated reflection pattern with a known distance map or a known reflection pattern to determine, based on an outcome of the comparing, that the single image contains either the spoof or the real object;
obtaining, from the single image, after the processing, data comprising at least the biometric characteristic, by performing a cropping operation comprising:
processing the single image or a part of the single image by a neural network, comprising processing the single image by an encoder to obtain an encoded image and processing the encoded image by a decoder to obtain a decoded output image, wherein the single image or the part of the single image provided to the neural network for processing comprises N×M pixels and the encoded image comprises n×m pixels, where n<N, m<M and the decoded output image comprises N×M pixels;
distinguishing a first portion of the single image or the part of the single image comprising a region of interest (ROI) from a second portion of the single image;
extracting, from the single image or the part of the single image, the ROI; and
storing the first portion comprising the ROI in a storage device on the mobile device; and
sending, to a third party computing device, the data comprising at least the biometric characteristic.