Integrated Image Sensor for Liveness Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current face and iris verification systems face challenges in accurately distinguishing between genuine and fake biometric inputs, particularly when using images or videos, leading to potential false acceptances and security breaches.
Innovation Solution
A processor-implemented liveness test method using an integrated image sensor that captures both color and infrared images, employing neural network-based models to determine the authenticity of the input by analyzing color and infrared features, thereby enhancing the accuracy of liveness detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single image sensor is used to capture both color and infrared images, then device complexity is reduced, but measurement precision may be compromised
Solution Approach 1:
The patent combines color and infrared image capture capabilities into a single integrated image sensor. The sensor includes a pixel array where each pixel can detect both visible light (for color images) and infrared light (for infrared images), eliminating the need for separate sensors and reducing overall device complexity while maintaining the ability to perform multi-spectral liveness detection
Solution Approach 2:
The integrated image sensor is designed with multi-functionality, allowing it to perform both color image capture and infrared image capture using the same physical sensor structure. This universal sensor can detect different wavelengths of light through the same pixel array, enabling dual-mode operation without requiring separate specialized sensors for each function
2Measurement precision
If dual liveness tests are performed using both color and infrared images, then liveness detection accuracy is improved, but processing time increases
Solution Approach 1:
The system performs preliminary action by capturing both color and infrared images simultaneously using the integrated sensor, rather than sequentially. The neural network models are pre-trained to process both image types, enabling parallel evaluation of liveness features from both spectral domains, which reduces the overall processing time compared to sequential analysis
Solution Approach 2:
The verification system dynamically adapts its processing based on the captured images. The neural network models can dynamically adjust their analysis focus based on the quality and characteristics of the input images, optimizing processing efficiency while maintaining detection accuracy. The system can dynamically switch between different verification pathways based on initial assessment results
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
The present application concers an apparatus and method with liveness verification. A processor-implemented liveness test method includes: obtaining a color image including an object and an infrared (IR) image including the object; performing a first liveness test using the color image; performing a second liveness test using the IR image; and determining a liveness of the object based on a result of the first liveness test and a result of the second liveness test.