Eye Rotation Angle Detection Using Direct Image Comparison

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for determining the rotation angle of an eye, particularly cyclotorsion, during ophthalmological treatments require specific lighting conditions, manual intervention, or iterative computations, making them cumbersome and less effective.

Innovation Solution

An ophthalmological treatment device using a processor and camera to determine the rotation angle by comparing a reference image taken in an upright position with a current image in a reclined position, employing a direct solver and neural networks to identify non-local features and calculate the rotation angle efficiently.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual marking methods are used to determine eye rotation angle, then the measurement can be performed, but the process becomes time-consuming and requires manual intervention

Engineering Contradiction:
Improverotation angle measurementVSAvoidtreatment time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical marking methods with an automated image processing system. The processor automatically captures images of the eye, detects features (blood vessels, iris patterns), and calculates the rotation angle through computational algorithms, eliminating the need for manual marking and significantly reducing treatment time while maintaining measurement precision.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service measurement by automatically performing all steps of rotation angle determination without operator intervention. The image capture, feature detection, and angle calculation are all executed autonomously by the device's processor, allowing the measurement process to serve itself and eliminating time-consuming manual operations.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If iterative optimization computations are used to determine cyclotorsion angle, then accurate measurement can be achieved, but the computation time increases

Engineering Contradiction:
Improvecyclotorsion angle accuracyVSAvoidcomputation speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent extracts and utilizes naturally occurring anatomical features (blood vessels in the sclera, iris patterns) as reference markers for measurement. By leveraging these pre-existing structural features rather than requiring iterative optimization against artificial markers, the system achieves accurate cyclotorsion angle measurement through direct geometric calculation, significantly improving computation speed while maintaining precision.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs preliminary capture of eye images before treatment begins, allowing the rotation angle to be determined in advance. The processor analyzes the captured images to establish the treatment model with proper orientation, so that during actual treatment, the pre-determined angle can be applied directly without requiring real-time iterative computation, thus enhancing both accuracy and productivity.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If diagnostic images and treatment images are taken under different conditions, then comprehensive data can be collected, but alignment and comparison become difficult

Engineering Contradiction:
Improvedata collection flexibilityVSAvoidimage alignment accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent employs universal anatomical features (blood vessels, iris patterns) that remain consistent across different imaging conditions and positions. These features serve as reliable reference points whether the eye is imaged in upright or supine position, allowing accurate alignment and comparison of diagnostic and treatment images despite varying capture conditions, thus maintaining measurement precision while preserving data collection flexibility.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system accounts for parameter changes between diagnostic and treatment phases by detecting and measuring the rotation angle that occurs when the patient changes position. The processor calculates the transformation parameters (rotation angle, translation) needed to align images taken under different conditions, enabling accurate comparison and superposition of diagnostic and treatment images while maintaining measurement precision.

Inventive Principle:
Principle #35Parameter changes

4Measurement precision

If multiple diagnostic images and artificial markers are used to determine eye rotation, then measurement accuracy can be improved, but the device complexity and manual intervention increase

Engineering Contradiction:
Improverotation angle accuracyVSAvoidmeasurement system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system utilizes the eye's own anatomical structures (blood vessels, iris patterns) as natural reference markers, eliminating the need for artificial markers. The processor automatically detects and tracks these self-service features across images, achieving accurate rotation angle measurement without adding device complexity or requiring manual marker application, thus simplifying the overall measurement system.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4197428B1Opthalmological treatment device for determining a rotation angle of an eye
Publication Date: 2026.05.20 ZIEMER OPHTHALMIC SYST
  • EP4197428B1 patent drawingFigure 1~2
  • EP4197428B1 patent drawingFigure 3a~3b
  • EP4197428B1 patent drawingFigure 4~5

AI summary

An ophthalmological treatment device (1) comprising a processor (11) and a camera (12) for determining a rotation of an eye (21) of a person, the processor (11) configured to: receive a reference image of the eye (21), the reference image having been recorded with the person in an upright position by a separate diagnostic device; record, using the camera, a current image of the eye (21), the current image being recorded with the person in a reclined position; and determine a rotation angle of the eye (21) by comparing the reference image to the current image using a direct solver.