公开(公告)号：US11216681B2

公开(公告)日：2022-01-04

申请号：US16911136

申请日：2020-06-24

Applicant: InvenSense, Inc.

Inventor： Sina Akhbari ,  Romain Fayolle ,  Daniela Hall

IPC: G06K9/00

Abstract: In a method for determining whether a finger is a real finger at an ultrasonic fingerprint sensor, a sequence of images of a fingerprint of a finger are captured at an ultrasonic fingerprint sensor, wherein the sequence of images includes images captured during a change in contact state between the finger and the ultrasonic fingerprint sensor. A plurality of transient features of the finger is extracted from the sequence of images. A classifier is applied to the plurality of transient features to classify the finger as one of a real finger and a fake finger. It is determined whether the finger is a real finger based on an output of the classifier.

公开(公告)号：US11188735B2

公开(公告)日：2021-11-30

申请号：US16909917

申请日：2020-06-23

Applicant: InvenSense, Inc.

Inventor： Sina Akhbari ,  Lingtao Wang ,  Mei-Lin Chan ,  Nikhil Apte

IPC: G06K9/00

Abstract: In a method for determining whether a finger is a real finger at an ultrasonic fingerprint sensor, a first image of a fingerprint pattern is captured at an ultrasonic fingerprint sensor, wherein the first image is based on ultrasonic signals corresponding to a first time of flight range. A second image of the fingerprint pattern is captured at the ultrasonic fingerprint sensor, wherein the second image is based on ultrasonic signals corresponding to a second time of flight range, the second time of flight range being delayed compared to the first time of flight range. A difference in a width of ridges of the fingerprint pattern in the first image compared to the width of ridges of the fingerprint pattern in the second image is quantified. Based on the quantification of the difference, a probability whether the finger is a real finger is determined.

公开(公告)号：US10984209B2

公开(公告)日：2021-04-20

申请号：US16270395

申请日：2019-02-07

Applicant: InvenSense, Inc.

Inventor： Sina Akhbari ,  Bruno Flament ,  Daniela Hall ,  Romain Fayolle ,  Etienne DeForas ,  Harihar Narasimha-Iyer

IPC: G06K9/00 ,  G01N21/88 ,  B06B1/06 ,  G06T5/50 ,  G06K9/22

Abstract: In a method for modeling a darkfield candidate image at a sensor, a plurality of darkfield images of the sensor is captured, wherein each darkfield image of the plurality of darkfield images is associated with a different operational condition of the sensor. An operational condition of the sensor is determined. A darkfield candidate image comprising a combination of the plurality of darkfield images is modeled based at least in part on the operational condition of the sensor, wherein a contribution of each darkfield image of the plurality of darkfield images is dependent on the operational condition.