Iris Recognition Using Geometric Parameters for Occlusion Handling

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional iris recognition methods struggle with accurately authenticating users when the iris is partially occluded, as they rely solely on binary iris representation and do not effectively utilize geometric parameters, leading to reduced recognition accuracy and increased failed attempts.

Innovation Solution

A method and device that acquire images of both eyes, extract pupil and iris features, and calculate a similarity score using both iris texture and geometric parameters, such as iris and pupil circle radii and positions, to improve recognition accuracy and handle occlusions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional iris recognition methods are used that rely solely on binary iris representation, then the system is simple to implement, but recognition accuracy deteriorates when the iris is partially occluded

Engineering Contradiction:
Improverecognition accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines multiple feature types (binary iris representation, iris texture, and geometric parameters including pupil-iris distance and radius ratios) into a unified authentication system. This merging of diverse features enables accurate recognition even when the iris is partially occluded, while the system maintains manageable complexity through integrated processing.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces additional parameters beyond traditional binary iris representation, specifically geometric parameters such as pupil-iris distance and radius ratios. By changing the parameter set to include these geometric measurements, the system achieves improved recognition accuracy under occlusion conditions without excessive complexity increase.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If additional information such as eye color and region around the eye is used to improve recognition accuracy, then recognition accuracy improves, but computational resource requirements increase

Engineering Contradiction:
Improverecognition accuracyVSAvoidcomputational resource consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent segments the authentication process into distinct feature extraction components: binary iris representation extraction, iris texture extraction, and geometric parameter extraction. By segmenting the processing into these modular components, the system achieves high recognition accuracy through multiple features while managing computational resources efficiently through targeted processing of each segment.

Inventive Principle:
Principle #1Segmentation

3Adaptability or versatility

If a sufficient area of the iris (more than 40%) is required for registration, then reliable recognition is achieved, but the system becomes insensitive to users with partially occluded irises due to eyelids, eyelashes, or external conditions

Engineering Contradiction:
Improveadaptability to occluded irisesVSAvoidauthentication reliability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent applies local quality analysis by examining specific local features including iris texture patterns and geometric relationships (pupil-iris distance, radius ratios) rather than requiring a uniform sufficient area. This local quality approach allows the system to adapt to partially occluded irises by utilizing available local features while maintaining authentication reliability through the combined feature set.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3680794B1Device and method for user authentication on basis of iris recognition
Publication Date: 2024.07.17 SAMSUNG ELECTRONICS CO LTD
  • EP3680794B1 patent drawingFigure 1
  • EP3680794B1 patent drawingFigure 2
  • EP3680794B1 patent drawingFigure 3

AI summary

Provided are a user authentication device and method based on iris recognition. The user authentication method includes: acquiring an image of a user's left and right eyes; extracting a pupil image and an iris image from the image; obtaining a first iris feature by analyzing the iris image; obtaining a second iris feature by analyzing the iris image and the pupil image; obtaining a similarity score based on the first iris feature, the second iris feature, and prestored reference iris data; and determining whether to approve user authentication based on the similarity score.