Live Facial Recognition via Structured Light Projection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional facial recognition systems using 2D cameras struggle to distinguish between real persons and images, leading to security vulnerabilities and inefficiencies in recognition processes.
Innovation Solution
A live facial recognition method and system that projects a pattern onto the subject, captures the reflected pattern, and determines whether the subject is a living being by analyzing the pattern's distortion, distinguishing between flat and curved surfaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional 2D facial recognition is used, then the recognition process is simple and fast, but the system cannot distinguish between real persons and pictures
Solution Approach 1:
The patent transitions from 2D facial recognition to 3D depth information acquisition by projecting structured light patterns and capturing their reflections. This dimensional change enables the system to detect surface curvature and distinguish real faces from flat images, directly resolving the reliability issue while maintaining practical system complexity through integrated hardware design.
Solution Approach 2:
The patent introduces structured light patterns as an intermediary medium between the camera and the subject. By projecting known patterns and analyzing their reflection, the system obtains depth information without requiring complex direct measurement, thus improving reliability while keeping the device complexity manageable.
2Reliability
If depth information is obtained through user actions such as head swinging or mouth opening, then the reliability of security measure is enhanced, but the recognition process becomes time-consuming and inconvenient
Solution Approach 1:
The patent performs depth verification through structured light projection simultaneously with facial image capture, rather than requiring sequential user actions. The depth information is obtained as part of the initial recognition process, eliminating additional time requirements while maintaining enhanced security reliability.
Solution Approach 2:
The system automatically captures depth information during the normal facial recognition process without requiring the user to perform specific actions. The structured light pattern reflection occurs naturally when light hits the face, and the camera automatically captures this information, making the process convenient and time-efficient.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the reliability and speed of facial recognition by accurately differentiating between real individuals and images, providing a more secure and convenient security measure.
Implementation Method 1
a reflected pattern of the subject under recognition is captured
Data Source
AI summary
A live facial recognition method includes projecting a given pattern to a subject under recognition; capturing a reflected pattern of the subject under recognition; and detecting whether the subject under recognition is a flat surface according to the reflected pattern. The subject under recognition is determined to be a living subject when the subject under recognition is not a flat surface.