Iris Authentication Device Using Segmented Imaging and Weighted Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Iris authentication systems face challenges in accurately identifying and authenticating left and right eyes due to issues like dark shadows, strong light, facial expressions, hair, and glasses, which can obstruct the inner corner of the eye, requiring high-cost telephotographic cameras and image analyzing apparatuses for accurate capture and analysis.
Innovation Solution
An iris authentication device that captures images of moving targets, determines whether the images are of the left or right eye using information from a first image, detects overlaps between image regions, calculates weighted verification scores by comparing iris characteristic information, and authenticates users based on these scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a telephotographic camera with high magnification is used to capture the inner corner of the eye, then the measurement precision of eye identification is improved, but the device cost increases
Solution Approach 1:
The patent divides the authentication process into two stages: first capturing a wide-angle overview image to identify eye position and orientation, then capturing a detailed iris image. This segmentation allows using a standard camera for the overview shot rather than requiring expensive telephotographic equipment for the entire process.
Solution Approach 2:
The system performs preliminary identification of eye position and orientation using a wide-angle image before capturing the detailed iris image. This preliminary action using simpler equipment enables subsequent accurate authentication without requiring high-magnification equipment for the initial detection phase.
2Measurement precision
If the inner corner of the eye is used for left/right identification, then the authentication accuracy is improved, but the reliability of identification deteriorates under certain conditions
Solution Approach 1:
The patent utilizes the asymmetric spatial relationship between the inner corner of the eye and the iris to determine left/right orientation. By analyzing the relative positions of these features in a wide-angle image, the system can reliably identify which eye is being viewed even when the inner corner itself is obscured.
Solution Approach 2:
The wide-angle overview image serves as an intermediary that provides contextual information about eye position and orientation. This intermediary image enables the system to identify left/right eyes even when direct viewing of the inner corner is blocked by shadows, light, expressions, hair, or glasses.
3Measurement precision
If detailed capture of the inner corner of the eye is attempted, then the measurement precision is improved, but the device complexity increases
Solution Approach 1:
The imaging system is segmented into two functional components: a wide-angle camera for capturing overview images that include the inner corner position, and a separate iris capture mechanism for detailed iris imaging. This segmentation avoids the need for a single complex telephotographic system while achieving the same identification accuracy.
Solution Approach 2:
The system captures more information than strictly necessary for iris authentication by including the inner corner and surrounding facial features in the wide-angle overview image. This partial action of capturing contextual information simplifies the overall system by using standard cameras rather than specialized high-magnification equipment.
Data Source
AI summary
The disclosure is inputting a first image captured an image of an authentication target; inputting a second image captured an image of a right eye or a left eye of the target; determining whether the second image is of a left eye or a right eye of the target based on information including the first image, and outputting a determination result as left/right information in association with the second image; detecting an overlap between a region including the second image and a predetermined region in the first image; calculating a verification score by comparing characteristic information that are related to the left/right information with iris characteristic information calculated from the second image, and calculating a first weighted verification score obtained by weighting the verification score with a detection result; and authenticating a target in the second image based on the first weighted verification score, and outputting an authentication result.