Iris Authentication Accuracy via Pupil Distribution Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing iris authentication techniques face challenges in maintaining accurate authentication performance due to variations in pupil diameter and lighting conditions, leading to increased false rejection rates and database capacity issues.
Innovation Solution
The method involves acquiring a uniform distribution of iris images by duplicating or deleting images, controlling illumination intensity, and selecting a predetermined number of registration features based on authentication performance evaluation, ensuring stable authentication regardless of pupil opening size at the time of authentication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple iris images with different pupil diameters are taken at registration, then authentication accuracy under various lighting conditions is improved, but database capacity requirements increase
Solution Approach 1:
The patent applies parameter changes by varying illumination intensity during image acquisition to create multiple iris images with different pupil diameters. This allows the system to capture iris patterns under various lighting conditions, improving authentication reliability while managing database requirements through selective feature extraction.
Solution Approach 2:
The patent implements preliminary action by acquiring and processing multiple iris images with different pupil diameters during the registration phase. This preparatory step ensures that when authentication occurs under any lighting condition, the system already has pre-processed features available, reducing computational burden during actual authentication.
2Reliability
If more registration features are stored, then authentication performance is improved, but authentication time and database capacity increase
Solution Approach 1:
The patent applies extraction by selecting and storing only the most discriminative iris features from multiple images with different pupil diameters. Instead of storing all possible features, the system extracts key features that provide the highest authentication performance, reducing both database capacity requirements and authentication processing time.
Solution Approach 2:
The patent implements partial action by using a selective subset of features from the multiple acquired images rather than processing all features. This approach achieves sufficient authentication performance without the computational overhead of processing every available feature, balancing accuracy with speed.
3Measurement precision
If pupil diameter is controlled to a predetermined size, then authentication accuracy is improved, but authentication time increases due to waiting for pupil adjustment
Solution Approach 1:
The patent applies preliminary action by acquiring iris images with multiple different pupil diameters during registration, eliminating the need to control pupil size during authentication. This preparatory multi-image acquisition allows the system to handle any pupil size during actual authentication without waiting for adjustment.
Solution Approach 2:
The patent implements dynamics by making the system adaptable to varying pupil diameters rather than requiring a fixed pupil size. The authentication algorithm dynamically selects and compares features from images with different pupil sizes, allowing accurate authentication regardless of the current pupil state.
4Quantity of substance
If illumination intensity is changed to vary pupil diameter, then multiple iris patterns are captured, but lighting control complexity increases
Solution Approach 1:
The patent applies parameter changes by systematically varying illumination intensity to achieve different pupil diameters. This controlled parameter change allows the system to capture diverse iris patterns while maintaining manageable lighting control through automated intensity adjustment.
Data Source
AI summary
A plurality of iris images are acquired (SA0), and aggregation of iris images of which distribution of pupil openings is uniform is acquired from the plurality of iris images by duplication and/or deletion (SA1). Features are generated from the respective iris images that belong to the aggregation (SA2), and a predetermined number of registration features are selected from the features, using authentication performance as an evaluation index.