Liveness Detection Using Random Target Position Tracking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional biological identification technologies, such as face recognition, are vulnerable to security risks due to the possibility of unauthorized users mimicking authorized users, as they do not effectively distinguish between live and non-live entities.

Innovation Solution

A liveness detection method that maps biological characteristic information, such as facial gestures, to a display position on a screen, and uses a target position generated randomly to verify whether the user is a living being by tracking the movement of this information, thereby enhancing security during identity authentication.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional biological identification technology is used for identity authentication, then the authentication process is simple and fast, but security is compromised due to vulnerability to spoofing attacks

Engineering Contradiction:
ImprovesecurityVSAvoiddetection complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by performing liveness detection before identity authentication. The system first determines whether the user is a living being through active liveness detection (requiring user interaction such as following gaze or moving face), and only after successful liveness verification does it proceed to authenticate the biological characteristic information. This preliminary security check prevents spoofing attacks while maintaining a clear separation between liveness detection and authentication processes.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If active liveness detection is implemented to verify user interaction, then security against spoofing is improved, but the authentication time and user operation complexity increase

Engineering Contradiction:
Improveanti-spoofing capabilityVSAvoidauthentication time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent implements periodic action by dividing the liveness detection into discrete, time-limited interaction tasks. The system presents a series of simple challenges (e.g., follow gaze to specific points, move face to indicated positions) that the user completes sequentially. Each challenge has a predefined time limit, and the system transitions between challenges in a periodic manner. This approach verifies liveness through multiple small interactions rather than a single prolonged task, reducing overall authentication time while maintaining security.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The patent applies dynamics by making the liveness detection process adaptive and flexible. The system dynamically adjusts the difficulty and type of interaction challenges based on initial detection results and user response. If simple challenges are successfully completed, the system may proceed to authentication; if not, it may present alternative challenges or terminate the process. This dynamic approach optimizes authentication time by avoiding unnecessarily complex interactions while ensuring adequate security verification.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3308325B1Liveness detection method and device, and identity authentication method and device
Publication Date: 2023.10.25 ADVANCED NEW TECHNOLOGIES CO LTD
  • EP3308325B1 patent drawingFigure 1
  • EP3308325B1 patent drawingFigure 2
  • EP3308325B1 patent drawingFigure 3

AI summary

Liveness detection and an identity authentication is included in the disclosure. A user's biological characteristic information is collected and displayed at an initial position on a screen of a computing device. A target position is determined using the initial position, and the target position is displayed on the screen. The user is prompted to move the user's biological characteristic information to cause the displayed biological characteristic to move from the initial position on the screen to the target position on the screen. The user's movement is detected and the display position of the displayed biological characteristic information is determined using the detected user's movement; a judgment is made whether the user is a living being using a relationship between the determined display position and the target position. The biological characteristic information of a living being can be verified, e.g., when the user logs in, thereby improving security.