Dual Sensor 3D Biometric Model Generation via Sliding Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current biometric identification systems using 2D models are susceptible to spoofing attacks and lack robustness due to their reliance on illumination compatibility, while 3D models are more secure but require bulky and expensive equipment.
Innovation Solution
An electronic device with dual imaging sensors captures overlapping images of a body part to generate a 3D biometric model, using a sliding motion to ensure accurate alignment and reduce equipment complexity, thereby creating a spoof-free, live biometric authentication method.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If 2D imaging is used for biometric identification, then the system is simple and inexpensive, but it is susceptible to spoofing attacks and lacks robustness
Solution Approach 1:
The patent transitions from 2D imaging to 3D imaging by capturing images from multiple viewpoints (front and side angles) and synthesizing depth information. This dimensional change enables the system to capture the three-dimensional structure of body parts, making spoofing attacks much more difficult while maintaining system simplicity through the use of standard imaging sensors.
2Reliability
If traditional 3D imaging equipment is used, then spoofing resistance is improved, but the equipment becomes bulky and expensive
Solution Approach 1:
The patent divides the imaging task into multiple sequential captures from different angles rather than using a single complex 3D scanner. By segmenting the imaging process into front-view and side-view captures using simple 2D sensors, the system achieves 3D reconstruction capability without requiring bulky or expensive dedicated 3D imaging equipment.
Solution Approach 2:
The patent uses standard 2D imaging sensors to perform multiple functions: capturing front views, capturing side views, and synthesizing 3D information. This multi-functional approach allows ordinary imaging devices to achieve 3D biometric capabilities, eliminating the need for specialized expensive equipment.
3Measurement precision
If multiple images from different angles are captured, then 3D model accuracy is improved, but the time required for image capture increases
Solution Approach 1:
The patent employs rapid sequential imaging where the sensor quickly captures images from different angles in succession. This periodic capture approach minimizes the total time required while still gathering sufficient multi-angle data for accurate 3D reconstruction, balancing speed and precision.
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
The solution provides a robust, spoof-free 3D biometric model that is difficult to replicate, offering enhanced security and reduced equipment costs compared to traditional methods, with improved feature extraction capabilities and resistance to illumination variations.
Implementation Method 1
A two-dimensional (2D) finger vein pattern is obtained by illuminating a finger with a light at a specific wavelength (e.g., near infrared) such that the light is absorbed by blood in the finger veins
Data Source
Figure 1A~1C
Figure 1D~2
Figure 3A~3C
AI summary
A method for generating a three-dimensional (3D) biometric model of a user's body part is provided. The method includes detecting, by at least one imaging sensor of the electronic device, the body part, capturing by the at least two imaging sensors a first image of a first portion of the body part and a second image of a second portion of the body part, generating the 3D biometric model of the body part using the first image and the second image of the body part, and storing the 3D biometric model of the body part.