Head-Tilt Invariant Real-Eye Detection With Polarized Corneal Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Iris recognition systems are susceptible to spoofing attacks using fake iris prints, and head tilts can blur or deform birefringent cornea features, making real-eye detection challenging.
Innovation Solution
Utilize a polarization-sensitive camera to capture images of the eye with polarized light, producing an iso-chrome pattern that highlights birefringent cornea features, and compensate for head tilts by aligning detected features with expected patterns to determine if the eye is real.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If polarized light is used to capture birefringent cornea features, then spoof detection capability is improved, but head tilts cause blurring and deformation of these features
Solution Approach 1:
The patent changes the polarization configuration parameter to produce an iso-chrome pattern that is invariant to head tilts. By selecting specific polarization angles (e.g., 45 degrees) and using circular polarization, the system maintains consistent birefringent feature appearance regardless of eye orientation, resolving the contradiction between spoof detection reliability and feature clarity under head tilts
Solution Approach 2:
The patent creates an equipotential situation where the iso-chrome pattern appears identical regardless of head tilt angle. The polarization configuration is designed so that the corneal birefringent features maintain constant visual characteristics across different head positions, making the detection system robust to tilt variations while maintaining spoof detection capability
2Productivity
If conventional iris recognition is used, then processing speed is maintained, but susceptibility to spoofing attacks increases
Solution Approach 1:
The patent introduces polarized light as an intermediary medium between the camera and the eye. This intermediary enables the capture of additional birefringent corneal features that are not visible in conventional images, providing an extra verification layer that maintains processing speed while significantly improving anti-spoofing capability
Solution Approach 2:
The patent combines multiple imaging modalities - conventional reflected light imaging with polarized light birefringent imaging - to create a composite detection system. This composite approach integrates the speed of conventional processing with the enhanced security of polarized light analysis, achieving both productivity and improved reliability
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
Enhances the reliability of iris recognition by reducing false rejections and ensuring the detection of authentic eyes, even with head tilts, through the use of birefringent cornea features.
Implementation Method 1
capturing at least one image comprising a representation of an eye of the individual, which image is captured utilizing polarized light reflected at the eye and received at a polarization-sensitive camera
Implementation Method 2
detecting, from the representation, birefringent features of a cornea of the individual
Data Source
AI summary
A method of a biometric recognition system of performing real-eye detection and associated biometric recognition system are disclosed. The method comprises capturing at least one image comprising a representation of an eye of the individual, which image is captured utilizing polarized light reflected at the eye and received at a polarization-sensitive camera capturing said image, wherein a polarization configuration is selected which produces an iso-chrome pattern of the representation of the eye in the captured image, detecting, from the representation, birefringent features of a cornea of the individual, aligning the detected birefringent cornea features with birefringent cornea features of an expected eye representation, determining, by matching the detected birefringent cornea features with the expected birefringent cornea features, whether the birefringent features are correctly rendered in the captured image, and if so determining that the eye is a real eye.