Iris Recognition Using Multi-Angle Illumination for Spoof Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Iris recognition systems face challenges in reliability due to variations in illumination and sensing component properties, which can lead to false identification of real eyes versus images of eyes.
Innovation Solution
A method involving the capture of digital image frames of an eye from different directions to generate comparison data based on similarities, determining the presence of verification features indicating a real eye, and detecting characteristic features of the iris using image data from multiple frames.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If single-direction illumination is used for iris capture, then the system complexity is reduced, but the reliability of iris recognition deteriorates due to inability to distinguish real eyes from images
Solution Approach 1:
The system uses multiple illumination sources positioned at different angles relative to the eye, dynamically capturing image frames from different directions. This dynamic multi-angle illumination approach enables differentiation between real eyes and images without requiring complex additional hardware, as the existing camera can capture frames from various illumination angles
Solution Approach 2:
The patent introduces a new dimension of analysis by capturing and comparing image frames illuminated from different directions. This multi-dimensional approach (adding the illumination angle dimension) allows the system to verify eye authenticity by detecting verification features that only appear under specific illumination conditions, thereby improving reliability without fundamentally changing the core imaging hardware
2Reliability
If multiple image frames from different directions are captured and compared, then the reliability of distinguishing real eyes from images is improved, but the processing time and computational complexity increase
Solution Approach 1:
The system performs preliminary actions by capturing multiple image frames with different illumination directions in rapid succession before the verification process begins. These pre-captured frames are then analyzed to detect verification features, allowing the actual verification to be performed quickly without real-time computational delays during the authentication moment
Solution Approach 2:
The patent extracts only the essential verification features from the multiple captured image frames rather than processing all frame data. By identifying and isolating the specific features that indicate a real eye (such as reflection patterns unique to biological tissue), the system reduces computational complexity and processing time while maintaining high verification accuracy
Data Source
AI summary
A method may comprise obtaining image data of a plurality of digital image frames captured of an assumed eye having an iris and a pupil while illuminating the assumed eye from different directions; obtaining comparison data dependent on similarities in parts of image data of at least two of the plurality of digital image frames corresponding to an area of interest of the assumed eye; and automatically determining, on the basis of the comparison data, presence of a verification feature in the assumed eye indicating a real eye.