Pupil Boundary Detection Using Reflection-Removed Circle Scoring

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional pupil detection methods, including statistical and non-statistical approaches, fail to provide accurate and reliable biometric authentication due to issues such as ocular reflections, diseases, pupil dilation, and contact lenses, leading to poor iris segmentation.

Innovation Solution

A method and system for pupil detection using a circle formation based scoring approach, involving reflection removal, core point identification, generation of points based on gradient changes, plotting of circles using permutation combinations, and selecting an optimum circle using a score-based method to identify the pupil accurately.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If statistical methods or conventional thresholding are used for pupil segmentation, then the process is simple, but the segmentation accuracy is poor

Engineering Contradiction:

Improvesimplicity of segmentation processVSAvoidpupil segmentation accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The method segments the pupil detection process into multiple distinct phases: reflection removal using inpainting, core point identification through gradient analysis, circle generation using permutation combinations, and optimal circle selection via scoring. This multi-stage segmentation allows each phase to be optimized independently, achieving high accuracy without excessive complexity

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The method performs preliminary actions by first removing ocular reflections using inpainting algorithms before attempting pupil detection. It also pre-identifies the core point and generates multiple candidate circles before selecting the optimal one. These preliminary steps prepare the data and reduce complexity for the final detection phase

Inventive Principle:

Principle #10Preliminary action

2Adaptability or versatility

If non-statistical methods relying on iris boundary are used, then the approach is alternative, but the pupil segmentation remains inaccurate

Engineering Contradiction:

Improvealternative detection approachVSAvoidpupil segmentation accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The method introduces an intermediary scoring mechanism that evaluates multiple candidate circles against established criteria before selecting the optimal pupil boundary. This intermediary selection process mediates between the generated candidate circles and the final pupil segmentation, ensuring accurate results regardless of the initial detection approach

Inventive Principle:

Principle #24Intermediary (Mediator)

3Device complexity

If pupil identification is based only on Euclidean distance between concentric circles, then the method is simple, but the segmentation is inaccurate

Engineering Contradiction:

Improvesimplicity of detection methodVSAvoidpupil segmentation accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The method changes the evaluation parameter from simple Euclidean distance to a comprehensive scoring system that considers multiple parameters including gradient magnitude, reflection intensity, and boundary regularity. This parameter transformation allows accurate pupil segmentation while maintaining reasonable computational complexity

Inventive Principle:

Principle #35Parameter changes

4Reliability

If ocular reflections are present in the input image, then the image captures real eye conditions, but the pupil detection accuracy deteriorates

Engineering Contradiction:

Improverepresentation of real eye conditionsVSAvoidpupil detection accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The method converts the harmful effect of ocular reflections into a beneficial process by using the reflection patterns themselves as indicators. The inpainting algorithm identifies reflection regions and uses the surrounding gradient information to reconstruct the underlying pupil structure, effectively using the reflection presence to guide the removal process and improve detection accuracy

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Data Source

PatentUS12511936B2Pupil detection using circle formation based scoring method

Publication Date: 2025.12.30 TATA CONSULTANCY SERVICES LTD

AI summary

The present disclosure detects a pupil of an eye using circle formation based scoring method. The conventional approaches fail to provide an accurate and reliable biometric authentication due to the usage of simple thresholding based statistical methods and iris dependent segmentation methods. The present disclosure utilizes a circle plotting approach and selects the optimum circle using several parameters. The present disclosure can generate a pupil boundary that fits the pupil region inside an iris perfectly. Initially, the system receives an input image of an eye. After removing reflections, a core point of the reflection free image is identified. Further, a plurality of points are obtained based on a sudden gradient change. and a plurality of circles are plotted. Further, an optimum circle is identified using a score based optimum circle selection method. Finally, the pupil associated with the input image is identified based on the optimum circle.