Iris Segmentation Using Nonparametric Thresholding and Hough Transform

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional iris segmentation methods for biometric identification are prone to errors due to weak edge detection between the iris and sclera, sensitivity to noise and reflections, and require iterative parameter adjustments, making them computationally costly and less robust.

Innovation Solution

A nonparametric thresholding method using a grey scale histogram to segment iris images, eliminating the need for edge classification and iterative parameter searches, and allowing for dynamic adjustment to varying lighting conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional edge detection methods are used to identify iris boundaries, then the method can be implemented with simple edge strength thresholds, but the edge detection becomes unreliable due to weak edges between iris and sclera

Engineering Contradiction:

Improveiris boundary detection reliabilityVSAvoidedge detection difficulty

Core Design Contradiction:

ReliabilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent introduces an intermediary approach by using the Hough transform to detect circular patterns in the image. Instead of directly detecting edges between iris and sclera, the system transforms the image into Hough space where circular structures become easier to identify and segment, thereby resolving the weak edge detection problem

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces conventional mechanical edge detection algorithms with a mathematical transformation approach (Hough transform). This substitution allows the system to detect iris boundaries by identifying circular patterns in transformed space rather than relying on direct edge strength measurements, improving reliability while reducing detection difficulty

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If iterative parameter searches are performed to find optimal boundary parameters, then the segmentation accuracy can be improved, but the computational cost increases significantly

Engineering Contradiction:

Improveiris segmentation precisionVSAvoidcomputational time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by performing the Hough transform and initial circular pattern detection before the actual iris segmentation. This preliminary processing identifies potential circular structures and their parameters in advance, allowing the subsequent segmentation process to use these pre-computed values rather than performing iterative searches, thereby reducing computational time while maintaining precision

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent changes the parameter space from direct image coordinates to Hough space (rho, theta parameters for circles). This parameter transformation allows for efficient non-iterative detection of circular patterns, replacing time-consuming iterative optimization with straightforward parameter extraction from the transformed image data

Inventive Principle:

Principle #35Parameter changes

3Ease of manufacture

If edge strength thresholds are used to identify iris boundaries, then the method is simple to implement, but it becomes sensitive to noise and reflections

Engineering Contradiction:

Improvemethod implementation simplicityVSAvoidnoise and reflection sensitivity

Core Design Contradiction:

Ease of manufactureVSObject-affected harmful factors

Solution Approach 1:

The patent introduces the Hough transform as an intermediary that separates the iris detection process from direct edge strength analysis. By transforming the image into Hough space, the system can identify circular patterns without being directly affected by noise and reflections that plague conventional edge detection methods, while maintaining implementation simplicity

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent substitutes conventional edge strength thresholding with a mathematical transformation approach (Hough transform). This substitution replaces the simple but noise-sensitive edge detection mechanism with a robust circular pattern recognition system that is inherently less sensitive to noise and reflections, while keeping the overall method simple to implement

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS9235762B2Iris data extraction

Publication Date: 2016.01.12 IDEMIA IDENTITY & SECURITY USA LLC

AI summary

A process for extracting iris data for biometric identification includes a thresholding method where the thresholds are selected according to a nonparametric approach that considers the grey scale and does not require classifying pixels as edge or non-edge pixels. An eye image is first acquired, where the eye image has component images including an iris image with an inner boundary and an outer boundary. The eye image has a distribution of grey levels. Component images, such as an iris image or a pupil image, from the eye image are segmented according to the distribution of grey levels. The inner boundary and outer boundary of the iris image are determined from the component images. The iris image within the inner boundary and outer boundary is processed for biometric identification. The component images may be segmented by creating an eye histogram of pixel intensities from the distribution of grey levels.