Eye Image Quality Metrics for Biometric Authentication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric authentication systems using eye images face challenges in efficiently distinguishing high-quality images from low-quality ones, leading to potential false rejections and unnecessary processing, especially due to factors like poor lighting, focus issues, and occlusions.
Innovation Solution
A method and system that determine quality metrics for eye images, including the extent of visible vasculature, color component comparison, and clarity measures, to assess image quality and predict a match score, thereby rejecting low-quality images and providing feedback for improved capture.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If biometric authentication systems process all eye images without quality assessment, then all images are evaluated for authentication, but processing resources are wasted on low-quality images and false rejections increase
Solution Approach 1:
The patent applies preliminary action by implementing a quality assessment step before full authentication processing. The system evaluates multiple quality metrics (vasculature extent, color component consistency, clarity measures) on captured eye images and only proceeds with authentication processing for images meeting quality thresholds. This preliminary filtering prevents wasteful processing of low-quality images that would inevitably lead to false rejections, thereby conserving computational resources while maintaining authentication reliability.
2Productivity
If quality metrics are used to reject low-quality images, then false rejections are reduced and processing resources are conserved, but additional processing steps are required to calculate quality scores
Solution Approach 1:
The patent applies segmentation by dividing the image analysis process into distinct quality metric components: vasculature extent metric, color component metric, and clarity metric. Each metric is calculated independently using specific algorithms tailored to that aspect, allowing the system to assess multiple quality dimensions without requiring a single complex monolithic evaluation system. This segmented approach improves processing efficiency by enabling selective computation and parallel evaluation while managing system complexity through modular design.
3Measurement precision
If multiple quality metrics are calculated for each image, then image quality assessment becomes more accurate, but computational complexity and processing time increase
Solution Approach 1:
The patent applies local quality by calculating different quality metrics for specific regions and aspects of the eye image rather than applying a single global quality measure to the entire image. The vasculature extent metric focuses on specific vascular structures, the color component metric analyzes particular color channels, and the clarity metric evaluates local sharpness and focus. This localized approach enables accurate quality assessment of critical authentication features while reducing unnecessary computational overhead on irrelevant image portions, thereby balancing measurement precision with processing time efficiency.
Data Source
AI summary
This specification describes technologies relating to biometric authentication based on images of the eye. In general, one aspect of the subject matter described in this specification can be embodied in methods that include obtaining a first image of an eye including a view of the white of the eye. The method may further include determining metrics for the first image, including a first metric for reflecting an extent of one or more connected structures in the first image that represents a morphology of eye vasculature and a second metric for comparing the extent of eye vasculature detected across different color components in the first image. A quality score may be determined based on the metrics for the first image. The first image may be rejected or accepted based on the quality score.