Iris Recognition Illuminator and Sensor Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Iris recognition systems face challenges in varying lighting conditions, leading to false acceptance and rejection rates, especially when users with glasses or contact lenses attempt to access electronic devices, as existing methods struggle to accurately detect corneal specular reflections and adapt to different ambient lighting.

Innovation Solution

A device and method that employ a successive on/off dual illuminator scheme to detect genuine corneal specular reflections, estimate size, shape, and brightness using eye, camera, and illuminator models, and verify the eye region using AdaBoost, while prompting users to enroll iris samples in multiple lighting conditions to create robust iris templates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If iris recognition is performed in varying lighting conditions, then the system must adapt to different ambient light, but detection accuracy deteriorates leading to false acceptance and rejection rates

Engineering Contradiction:
Improveadaptation to lighting conditionsVSAvoiddetection accuracy
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary actions by capturing multiple iris samples under different lighting conditions during enrollment and creating condition-specific templates. When authentication is attempted, the system first detects the current lighting condition and then selects the appropriate pre-prepared template for comparison, avoiding the need to adapt in real-time during authentication.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system changes parameters by creating multiple iris templates under different lighting conditions (varying illumination intensity, color temperature, and ambient light levels). Each template is optimized for specific lighting parameters, allowing the system to select the most appropriate template based on current environmental conditions, thereby maintaining high detection accuracy across varying lighting scenarios.

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If users with glasses or contact lenses are accommodated, then inclusivity improves, but detection accuracy deteriorates due to difficulty in detecting genuine corneal specular reflections

Engineering Contradiction:
Improveaccommodation of users with glassesVSAvoidcorneal specular reflection detection
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system segments the authentication process into distinct phases: first detecting corneal specular reflections to locate the eye region, then capturing iris samples, and finally performing recognition. By separating these steps and using the specular reflection detection only for localization rather than authentication, the system can accommodate users with glasses while maintaining accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system uses an intermediary approach by detecting corneal specular reflections as a preliminary step to identify the eye region and guide subsequent iris capture, but does not rely on these reflections for the actual authentication decision. This intermediary use of specular reflection detection allows users with glasses to be accommodated while maintaining measurement precision through the primary iris pattern matching.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If multiple iris samples are collected under different lighting conditions, then template robustness improves, but enrollment time increases

Engineering Contradiction:
Improvetemplate robustnessVSAvoidenrollment time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system applies partial action by collecting a limited but sufficient number of iris samples under representative lighting conditions during enrollment, rather than attempting to capture all possible lighting scenarios. This selective sampling approach creates robust templates while keeping enrollment time acceptable for users.

Inventive Principle:
Principle #16Partial or excessive action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution achieves a high correct iris detection rate of 99.5% for images without glasses and 98.9% with glasses or contact lenses, with an improved equal error rate of 0.05%, enhancing the reliability of iris authentication across various lighting conditions.

Implementation Method 1

an ambient light sensor is configured to measure a lighting condition in the surroundings

Methodology Applied
Scientific EffectAmbient light detection: Photoelectric Effect

Implementation Method 2

iris samples (images) of the user are shot by specialized infrared cameras that use light emitting diode (LED) to illuminate the irises of the user

Methodology Applied
Scientific EffectLight emitting diode illumination: Light Emitting Diode

Implementation Method 3

a new iris recognition method for mobile phones based on corneal specular reflections (SRs)

Methodology Applied
Scientific EffectSpecular reflection: Reflection

Data Source

PatentEP3362942B1Electronic devices with improved iris recognition and methods thereof
Publication Date: 2021.03.17 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3362942B1 patent drawingFigure 1
  • EP3362942B1 patent drawingFigure 2
  • EP3362942B1 patent drawingFigure 3A~3B

AI summary

An electronic device and a method for improving iris recognition for providing access to the electronic device. The electronic device includes an iris scanner, an ambient light sensor, a memory and a processor. The memory includes computer program code for providing access control to the electronic device to a user by iris recognition of the user's iris. The processor causes the electronic device to prompt the user to provide iris samples of the user's iris to the iris scanner in a particular lighting condition measured by the ambient light sensor in occurrence of at least one of first event and second event. The first event occurs if the processor determines a missing information associated with an iris sample in the particular lighting condition in the electronic device. The second event occurs if the processor detects an unsuccessful iris recognition attempt for accessing the electronic device in the particular lighting condition.