Single Sensor Biometric Recognition with Dynamic Illumination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric recognition systems face limitations in accurately identifying individuals, particularly when multiple biometric types are acquired from a single sensor or when poor-quality data is obtained, due to issues like registration errors, pose variations, inadequate camera sensitivity, and varying illumination, leading to false positives and negatives.
Innovation Solution
A method and system that capture high-quality images of both iris and face using a single sensor by adjusting camera and illumination settings between acquisitions, allowing for optimal parameter settings for each biometric recognition step, such as varying illumination power, camera integration time, and frame grabber settings, within a short time frame to ensure accurate feature comparison.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single sensor is used to acquire multiple biometric types (face and iris), then device complexity is reduced, but measurement precision deteriorates due to conflicting dynamic range requirements
Solution Approach 1:
The patent applies dynamics by making the sensor parameters adjustable and time-varying. The system dynamically changes illumination intensity and camera exposure time between capturing face and iris images, allowing optimization for each biometric type separately while using a single sensor.
Solution Approach 2:
The patent changes sensor parameters (illumination power, integration time) between different biometric acquisitions. By adjusting these parameters, the system captures face images with one set of parameters and iris images with optimized different parameters, resolving the dynamic range conflict.
2Measurement precision
If different illumination settings are used for face and iris acquisition, then measurement precision improves, but loss of time increases due to multiple acquisitions
Solution Approach 1:
The patent maintains continuity by acquiring face and iris images in rapid succession with minimal interruption. The system switches between different illumination and exposure settings between the two acquisitions, keeping the overall process continuous and minimizing time loss.
Solution Approach 2:
The patent uses periodic action by alternating between different acquisition modes (face mode with one set of parameters, iris mode with another set) in a repeated sequence. This periodic switching allows optimization for each biometric type while maintaining an efficient overall acquisition rhythm.
3Measurement precision
If registration is performed to align corresponding features, then measurement precision improves, but device complexity increases due to additional processing requirements
Solution Approach 1:
The patent applies preliminary action by performing registration and alignment operations before the actual biometric comparison. The system pre-aligns the face and iris images to a common coordinate system and corrects pose variations in advance, so that subsequent matching operations can proceed with high precision without requiring complex real-time processing.
Data Source
AI summary
High quality, high contrast images of an iris and the face of a person are acquired in rapid succession in either sequence by a single sensor and one or more illuminators, preferably within less than one second of each other, by changing the data acquisition settings or illumination settings between each acquisition.