Qualcomm Incorporated

Gesturetek, Inc.

Jin Gu

Kwokleung Chan

Eliza Yingzi Du

Ming Yu Chen

Esra Vural

John Keith Schneider

David William Burns

Suryaprakash Ganti

Kostadin Dimitrov Djordjev

Jessica Liu Strohmann

Stephen Michael Gojevic

Jack Conway Kitchens, Ii

Ashish Hinger

Nai-Kuei Kuo

Nao Sugawara Chuei

Ranjith Ranganathan

Wei-En Hsu

Chuenwen Chung

Some methods may involve receiving fingerprint image data. Some methods may involve determining whether the fingerprint image data was captured by a first fingerprint sensor of a device or a second fingerprint sensor of the device. Some methods may involve obtaining an enhanced version of the fingerprint image data based on a determination that the fingerprint image data was captured by the second fingerprint sensor of the device. Some methods may involve providing the enhanced version of the fingerprint image data for authentication. In some examples, obtaining the enhanced version of the fingerprint image data may involve an image enhancement machine learning model. In some examples, prior to obtaining the enhanced version of the fingerprint image data, a determination is made that the fingerprint image data captured by the second fingerprint sensor fails to satisfy a quality threshold.

Image enhancement for fingerprint sensor deployed in a flexible device

Systems and methods for multi-spectral ultrasonic imaging are disclosed. In one embodiment, a finger is scanned at a plurality of ultrasonic scan frequencies. Each scan frequency provides an image information set describing a plurality of pixels of the finger including a signal-strength indicating an amount of energy reflected from a surface of a platen on which a finger is provided. For each of the pixels, the pixel output value corresponding to each of the scan frequencies is combined to produce a combined pixel out put value for each pixel. Systems and methods for improving the data capture of multi-spectral ultrasonic imaging are also disclosed.

Multi-spectral ultrasonic imaging

A method of determining whether a biometric object is part of a live individual is described. In one such method, image information is acquired from the biometric object by using a sensor, such as an ultrasonic sensor. The image information may be analyzed in at least two analysis stages. One of the analysis stages may be a temporal analysis stage that analyzes changes in the image information obtained during a time period throughout which the biometric object was continuously available to the sensor. For example, a dead/alive stage may analyze differences between image information taken at two different times in order to identify changes from one time to the next. Other stages may focus on aspects of a particular image information set, rather than seeking to assess changes over time. These other stages seek to determine whether an image information set exhibits characteristics similar to those of a live biometric object.

Multi-stage liveness determination

A liveness-detection method and/or system is disclosed. A method of detecting liveness can comprise obtaining a single ultrasonic image of a biometric object. The single ultrasonic image can be subdivided into a plurality of overlapping sample blocks. Feature vectors can be extracted in a spatial domain and a frequency domain from each of the plurality of sample blocks. The feature vectors can be compared from each of the plurality of sample blocks to a classification model.

Image-based liveness detection for ultrasonic fingerprints

Processing images includes projecting an infra-red pattern onto a three-dimensional object and producing a first image, a second image, and a third image of the three-dimensional object while the pattern is projected on the three-dimensional object. The first image and the second image include the three-dimensional object and the pattern. The first image and the second image are produced by capturing at a first camera and a second camera, respectively, light filtered through an infra-red filter. The third image includes the three-dimensional object but not the pattern. Processing the images also includes establishing a first-pair correspondence between a portion of pixels in the first image and a portion of pixels in the second image. Processing the images further includes constructing, based on the first-pair correspondence and the third image, a two-dimensional image that depicts a three-dimensional construction of the three-dimensional object.

Enhanced object reconstruction

Various arrangements for identifying a location of a hand of a person are presented. A group of pixels may be identified in an image of a scene as including the person. A reference point may be set for the group of pixels identified as the person. The hand may be identified as using a local distance maximum from the reference point. An indication, such as coordinates, of the location of the hand may be output based on the local distance.

Hand detection, location, and/or tracking

Various arrangements for modeling a scene are presented. A plurality of images of the scene captured over a period of time may be received, each image comprising a plurality of pixels. A plurality of background models may be created using the plurality of images. At least one background model may be created for each pixel of the plurality of pixels. A plurality of foreground models may be created using the plurality of images. A foreground model may be created for each pixel of at least a first subset of pixels of the plurality of pixels. The background models and the foreground models may be indicative of the scene over the period of time.

Object tracking using background and foreground models

According to a general aspect, processing images includes projecting an infra-red pattern onto a three-dimensional object and producing a first image, a second image, and a third image of the three-dimensional object while the pattern is projected on the three-dimensional object. The first image and the second image include the three-dimensional object and the pattern. The first image and the second image are produced by capturing at a first camera and a second camera, respectively, light filtered through an infra-red filter. The third image includes the three-dimensional object but not the pattern. Processing the images also includes establishing a first-pair correspondence between a portion of pixels in the first image and a portion of pixels in the second image. Processing the images further includes constructing, based on the first-pair correspondence and the third image, a two-dimensional image that depicts a three-dimensional construction of the three-dimensional object.

Growing community of inventors

Nepean, Canada

Jin Gu