US 12,087,078 B2
Method for identifying an object within an image and mobile device for executing the method
Jesus Aragon, Dover, DE (US)
Assigned to Identy Inc., Dover, DE (US)
Filed by Identy Inc., Dover, DE (US)
Filed on Jun. 28, 2022, as Appl. No. 17/851,381.
Application 17/851,381 is a continuation of application No. 16/981,262, granted, now 11,508,184, previously published as PCT/IB2019/052126, filed on Mar. 15, 2019.
Claims priority of application No. 18382174 (EP), filed on Mar. 16, 2018.
Prior Publication US 2022/0335748 A1, Oct. 20, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 40/13 (2022.01); G06F 18/21 (2023.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06V 10/10 (2022.01); G06V 10/20 (2022.01); G06V 10/44 (2022.01); G06V 10/75 (2022.01); G06V 10/82 (2022.01); G06V 20/64 (2022.01); G06V 30/142 (2022.01); G06V 40/10 (2022.01); G06V 40/12 (2022.01); G06V 40/40 (2022.01); H04N 23/56 (2023.01)
CPC G06V 40/1312 (2022.01) [G06F 18/21 (2023.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06V 10/17 (2022.01); G06V 10/255 (2022.01); G06V 10/454 (2022.01); G06V 10/751 (2022.01); G06V 10/82 (2022.01); G06V 20/64 (2022.01); G06V 30/142 (2022.01); G06V 40/107 (2022.01); G06V 40/1318 (2022.01); G06V 40/1347 (2022.01); G06V 40/1365 (2022.01); G06V 40/1388 (2022.01); G06V 40/40 (2022.01); H04N 23/56 (2023.01); G06T 2207/20021 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30196 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for identifying a user using an image of an object of the user, the method comprising:
obtaining, by an optical sensor of a mobile device, the image of the object, wherein the mobile device is a smartphone or a tablet computer, wherein the object comprises a biometric characteristic of the user;
providing, by the mobile device, the image to a neural network;
processing, by the mobile device, the image by the neural network to identify a position of the object and the object in the image, wherein the identified object comprises at least one fingertip, wherein the neural network comprises a plurality of layers, a layer of the plurality of layers being a depthwise separable convolution comprising at least one of: a depthwise convolution layer, a first batch normalizer, a first rectified linear unit, a pointwise convolution layer, a second batch normalizer, or a second rectified linear unit;
extracting, by the mobile device, from the identified object, the biometric characteristic comprising a fingerprint of the at least one fingertip;
storing, by the mobile device, the biometric characteristic in a storage device; and
providing, by the mobile device, at least the biometric characteristic as input to an identification means to determine whether the biometric characteristic identifies the user.