Smartphone Fingerprint Authentication via Optical Imaging and Liveness Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional fingerprint recognition systems on smartphones are limited by the size and cost of dedicated fingerprint sensors, which reduce accuracy and are prone to false rejections and spoof attacks, especially when used for newborns or in applications requiring higher security, and are not universally available across devices.

Innovation Solution

A method for capturing and processing high-resolution images of multiple fingers using a smartphone's camera, employing algorithms for finger detection, segmentation, and feature extraction to generate a biometric identifier, which enhances security and usability by incorporating liveness detection and anti-spoofing techniques.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If dedicated fingerprint sensors are used in smartphones, then fingerprint authentication can be performed, but the device size, weight, and cost increase

Engineering Contradiction:
Improvefingerprint authentication capabilityVSAvoiddevice weight
Core Design Contradiction:
ReliabilityVSWeight of moving object

Solution Approach 1:

The patent replaces the mechanical contact-based fingerprint sensor with an optical imaging system using the smartphone's existing camera. The camera captures images of the finger, and software algorithms process these images to perform fingerprint authentication, eliminating the need for dedicated fingerprint sensor hardware.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent makes the smartphone's camera serve multiple functions: it is used both for standard photography and for fingerprint authentication. By utilizing the existing camera hardware for biometric verification, the system eliminates the need for separate fingerprint sensor components.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Reliability

If dedicated fingerprint sensors are used in smartphones, then fingerprint authentication can be performed, but the device cost increases

Engineering Contradiction:
Improvefingerprint authentication capabilityVSAvoiddevice cost
Core Design Contradiction:
ReliabilityVSEase of manufacture

Solution Approach 1:

The patent replaces the mechanical contact-based fingerprint sensor with an optical imaging system using the smartphone's existing camera. The camera captures images of the finger, and software algorithms process these images to perform fingerprint authentication, eliminating the need for dedicated fingerprint sensor hardware.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a digital copy of the fingerprint pattern by capturing it through the camera and processing it into a biometric template. This digital representation is then stored and used for authentication, replacing the need for physical sensor hardware.

Inventive Principle:
Principle #26Copying

3Volume of moving object

If small fingerprint sensors are used to minimize device size, then device compactness is improved, but authentication accuracy decreases and false rejections increase

Engineering Contradiction:
Improvesensor sizeVSAvoidfingerprint capture accuracy
Core Design Contradiction:
Volume of moving objectVSMeasurement precision

Solution Approach 1:

The patent segments the finger image into multiple regions of interest, focusing on capturing the entire finger surface area rather than just a small portion. The image processing algorithm divides and conquers the fingerprint analysis by identifying key features across the complete finger surface.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from capturing only the fingerprint ridge pattern (2D surface pattern) to capturing the entire finger including its 3D shape and surface topology. This additional dimensional information provides more data points for accurate authentication.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

4Reliability

If traditional fingerprint sensors are used, then fingerprint data can be captured, but the system is vulnerable to spoof attacks

Engineering Contradiction:
Improvefingerprint data captureVSAvoidspoof attack vulnerability
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent transitions from capturing only the fingerprint ridge pattern (2D surface pattern) to capturing the entire finger including its 3D shape and surface topology. This additional dimensional information provides more data points for accurate authentication and makes spoofing more difficult.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent uses the smartphone's existing camera, which is designed for temporary, disposable use in photography, and repurposes it for fingerprint authentication. This approach avoids using expensive specialized sensors that are vulnerable to spoofing.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

5Adaptability or versatility

If conventional smartphones with limited camera resolution are used, then device accessibility is improved, but biometric identification accuracy decreases

Engineering Contradiction:
Improvedevice accessibilityVSAvoidbiometric identification accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent segments the finger image into multiple regions of interest, focusing on capturing the entire finger surface area rather than just a small portion. The image processing algorithm divides and conquers the fingerprint analysis by identifying key features across the complete finger surface.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary image processing and enhancement steps before fingerprint analysis. The system captures multiple images, pre-processes them to enhance quality, and selects the best image for analysis, thereby compensating for the limited camera resolution.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9361507B1Systems and methods for performing fingerprint based user authentication using imagery captured using mobile devices
Publication Date: 2016.06.07 VERIDIUM IP LTD

AI summary

Technologies are presented herein in support of a system and method for performing fingerprint recognition. Embodiments of the present invention concern a system and method for capturing a user's biometric features and generating an identifier characterizing the user's biometric features using a mobile device such as a smartphone. The biometric identifier is generated using imagery captured of a plurality of fingers of a user for the purposes of authenticating/identifying the user according to the captured biometrics and determining the user's liveness. The present disclosure also describes additional techniques for preventing erroneous authentication caused by spoofing. In some examples, the anti-spoofing techniques may include capturing one or more images of a user's fingers and analyzing the captured images for indications of liveness.