Textured Contact Lens Detection via Photometric Stereo
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Iris recognition systems are susceptible to presentation attacks, particularly from textured contact lenses that can simulate or obscure the true iris, leading to incorrect identity verification.
Innovation Solution
The method employs a single camera lens and multiple illuminants positioned at different angles to capture images and utilize photometric stereo to estimate surface normal vectors, distinguishing between the flat authentic iris and irregular textured contact lens by analyzing the variance in shadow patterns generated under varying illumination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a conventional iris recognition sensor is used, then the system is simple and cost-effective, but it is vulnerable to presentation attacks using textured contact lenses
Solution Approach 1:
The patent transitions from 2D iris image capture to 3D surface analysis by introducing multiple illuminants at different angles. This dimensional change enables the system to capture depth information and surface normal vectors, allowing differentiation between flat authentic irises and curved textured contact lenses without requiring complex additional hardware beyond standard camera and light source arrangements
Solution Approach 2:
The patent introduces photometric stereo processing as an intermediary computational step between image capture and iris recognition. This intermediary process analyzes shadow patterns and surface normal vectors from multiple illuminated images to detect the presence of textured contact lenses, effectively mediating between the physical sensor and the recognition algorithm to enhance security
2Measurement precision
If multiple illuminants at different angles are used, then detection accuracy of textured contact lenses is improved, but the use of energy and system complexity increases
Solution Approach 1:
The patent employs periodic illumination sequences where multiple illuminants are activated in alternating or sequential patterns rather than simultaneously. This periodic action allows the system to capture multiple images with different lighting conditions while minimizing total energy consumption, as each illuminant operates only during its designated time slot in the sequence
Solution Approach 2:
The patent uses a minimal set of illuminants (typically 2-3) positioned at specific angles rather than comprehensive multi-directional lighting. This partial action approach provides sufficient surface normal vector information for detection while avoiding the excessive energy consumption that would result from using numerous illuminants covering all possible angles
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
This approach effectively differentiates between authentic irises and those covered by textured contact lenses, enhancing the security of iris recognition systems by accurately detecting presentation attacks without requiring significant hardware modifications.
Implementation Method 1
utilize photometric stereo to estimate surface normal vectors
Implementation Method 2
analyze the variance in shadow patterns generated under varying illumination
Data Source
AI summary
Systems and methods for detecting textured contact lenses in an iris image are disclosed. Initially, âKâ images are taken of an eye in near-infrared light, each for a different positioning of the illuminant. Three-dimensional properties of the hypothetical iris are estimated based on image processing methods. The variability of the estimated three-dimensional properties is calculated, and a classification into two classes is made based on the variability. A low variability denotes that an authentic iris pattern was presented to the sensor, whereas a high variability denotes that the sensor observes an eye wearing a textured contact lens. The systems and methods disclosed allow for detecting presentation attacks to iris recognition systems/sensors based on presentation of an eye wearing a textured contact lens in an automatic and accurate way.