Iris Location Algorithm Using Fourier Transform and Integrodifferential Operator

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Iris recognition systems face challenges in accurately locating the iris due to poor image quality, caused by factors like specular reflections, blurring, and a small depth of field, which affects the performance of identification algorithms.

Innovation Solution

A method and device for locating the iris in an image that involves detecting the pupil, calculating the energy of high-frequency components using a Fourier transform, and determining the radius of the iris by analyzing transitions between the iris and the cornea, while refining the center and radius using an integrodifferential operator, and preprocessing to filter out eyelashes and reflections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If images are taken at a relatively short distance to obtain sufficient iris resolution, then the iris resolution is improved, but the depth of field becomes small causing differences in sharpness between zones

Engineering Contradiction:

Improveiris resolutionVSAvoidsharpness consistency

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent divides the image processing into multiple stages: preprocessing to detect and remove eyelashes, main processing to locate the iris and pupil, and post-processing to refine the location. This segmentation allows each stage to address specific quality issues independently, improving overall reliability without sacrificing resolution.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies preprocessing steps before main iris location to eliminate eyelashes and reflections that would interfere with detection. By performing these actions in advance, the system ensures that the main processing operates on cleaned data, improving sharpness consistency across different image zones.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If traditional iris identification methods are used on poor quality images, then the processing speed is maintained, but errors in locating the iris increase

Engineering Contradiction:

Improveprocessing speedVSAvoidiris location accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent replaces traditional mechanical focus adjustment with a software-based approach that processes images at fixed focus distances. By using image processing algorithms to compensate for optical limitations, the system maintains processing speed while improving location accuracy through digital rather than mechanical means.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the processing parameters dynamically based on image quality characteristics. The method adapts its detection thresholds and processing intensity based on the detected image conditions, allowing it to maintain high accuracy across varying image qualities without sacrificing processing speed through exhaustive analysis.

Inventive Principle:

Principle #35Parameter changes

3Device complexity

If non-autofocus cameras are used to reduce cost, then the device complexity is reduced, but the image quality deteriorates due to small depth of field

Engineering Contradiction:

Improvecamera system complexityVSAvoidimage quality

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent introduces image processing algorithms as an intermediary between the simple camera hardware and the iris recognition system. This intermediary layer compensates for the optical limitations of non-autofocus cameras by digitally enhancing image quality and correcting focus issues, allowing low-cost hardware to achieve reliable results.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent accepts that individual images may have quality variations and uses a multi-image processing approach where poor quality images are compensated by processing multiple frames. This allows the use of simple, low-cost cameras while maintaining overall system reliability through redundancy rather than investing in expensive autofocus hardware.

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

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 enhances the robustness of iris location algorithms, reducing sensitivity to image quality and improving accuracy even with low-cost, non-autofocus cameras, achieving high success rates in iris recognition.

Implementation Method 1

calculating the energy of high-frequency components of a Fourier spectrum obtained by a fast Fourier transform on a gate-type mobile window

Methodology Applied

Scientific EffectFourier transform:

Data Source

PatentUS8325996B2Method and device for locating a human iris in an eye image

Publication Date: 2012.12.04 STMICROELECTRONICS (ROUSSET) SAS

AI summary

The present disclosure relates to a method for locating the iris in an image of an eye, comprising steps of locating the pupil in the image, of detecting positions of intensity steps of pixels located on a line passing through the pupil and transition zones between the iris and the cornea, on either side of the pupil, and of determining the center and the radius of a circle passing through the detected positions of the transitions.