Iris Image Normalization Using Polygonal Pupil Boundaries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing iris analysis methods struggle to normalize images for individuals with non-circular or elliptic pupils, limiting the reliability of iris code creation and identification, as they often focus on specific regions rather than the entire iris image.
Innovation Solution
A method that determines the pupil region using more than five independent parameters and transforms the iris image into a coordinate system where each point is described by its position along the pupil boundary and distance from it, allowing for normalization across the entire iris region, including irregular shapes, and correcting for rotation and dilation effects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional normalization methods are used for circular pupils, then the method is simple and efficient, but it fails to handle non-circular or elliptic pupils correctly
Solution Approach 1:
The patent changes the parameter description from fixed circular/elliptic models to a flexible polygonal model with variable numbers of vertices. The pupil boundary is represented by a polygon whose vertices can be dynamically determined from image data, allowing the normalization method to adapt to any pupil shape while maintaining mathematical tractability through coordinate transformation.
Solution Approach 2:
The patent introduces dynamic adaptability by allowing the number and positions of polygon vertices to vary based on the actual pupil shape detected in the image. Rather than using a fixed geometric model, the system dynamically adjusts the polygonal representation to match the observed pupil boundary, enabling handling of irregular shapes without manual intervention.
2Reliability
If only specific regions of interest are processed, then the processing is faster and simpler, but the iris code contains less information and reduces identification reliability
Solution Approach 1:
The patent applies universality by extending the normalization and processing procedure to cover the entire iris region rather than limiting it to specific areas of interest. The same coordinate transformation and feature extraction methods are applied uniformly across the complete iris boundary defined by the polygon, ensuring that no informative regions are excluded while maintaining a consistent processing approach throughout.
3Measurement precision
If the entire iris image is normalized, then more iris detail is included and identification accuracy improves, but the normalization becomes more complex
Solution Approach 1:
The patent segments the iris region into a polygonal representation with multiple vertices that define the boundary. This segmentation allows the complex task of normalizing the entire iris to be broken down into manageable coordinate transformations along each polygon edge, making the process computationally feasible while maintaining comprehensive coverage of the entire iris area for high precision coding.
Data Source
AI summary
A method of normalizing a digital image of an iris of an eye for the purpose of creating an iris code for identification of vertebrates, including humans, the method comprising the steps of:determining a pupil region in the image as a convex region having a boundary that can only be described by more than five independent parameters;determining, in the image, an outer boundary of the iris; andtransforming an image of a ring shaped iris region that surrounds the pupil region into a coordinate system in which each point of the iris region is described by a first coordinate that indicates the position of the point along the boundary of the pupil and a second coordinate that indicates the distance of the point from said boundary, said second coordinate having a constant value when the point is located on the outer boundary of the iris.