Eye Tracker Hardware Filtering for Fast Pupil Detection

Solution Overview

Problem

Existing ophthalmic surgical systems face challenges in accurately tracking eye movement during procedures like LASIK, as laser beams need precise targeting to specific eye points, which current systems struggle to achieve due to inefficiencies in identifying and tracking the pupil.

Innovation Solution

An ophthalmic surgical system incorporates hardware filtering and software sorting to quickly identify candidate pupil images using criteria such as bounding box shape, area, symmetry, and density, followed by software sorting based on object area, central location, symmetry, and historical tracking to accurately track eye movement, enabling precise laser beam direction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional eye tracking methods are used to monitor eye movement during laser surgery, then the system can track eye position, but the tracking speed and accuracy are insufficient for precise laser targeting

Engineering Contradiction:

Improvetracking accuracyVSAvoidtracking speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent segments the eye tracking process into two distinct stages: hardware filtering (pre-processing) and software sorting (post-processing). The hardware filter divides candidate objects based on geometric criteria (bounding box aspect ratio, area) while the software sorts remaining candidates using correlation analysis. This segmentation allows each stage to optimize for its specific function, achieving both high speed in filtering and high accuracy in final identification.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The hardware filter performs preliminary action by pre-processing the image data before software analysis. It quickly eliminates obvious non-pupil candidates based on simple geometric properties (bounding box aspect ratio between 0.8-1.2, area within expected range), reducing the computational burden on the software correlation analysis and enabling faster overall tracking while maintaining accuracy.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If comprehensive image analysis is performed to accurately identify the pupil, then tracking accuracy improves, but processing time increases

Engineering Contradiction:

Improvepupil identification accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The hardware filter performs preliminary action by pre-processing the image data before software analysis. It quickly eliminates obvious non-pupil candidates based on simple geometric properties (bounding box aspect ratio between 0.8-1.2, area within expected range), reducing the computational burden on the software correlation analysis and enabling faster overall tracking while maintaining accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies different quality levels of analysis to different candidates. The hardware filter applies strict geometric criteria to all detected objects, while the software correlation analysis applies more computationally intensive template matching only to the remaining candidate objects that passed the hardware filter. This local differentiation of analysis depth optimizes the balance between accuracy and processing time.

Inventive Principle:

Principle #3Local quality

3Reliability

If multiple candidate objects are evaluated to ensure accurate pupil identification, then reliability improves, but system complexity increases

Engineering Contradiction:

Improvepupil identification reliabilityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the eye tracking process into two distinct stages: hardware filtering (pre-processing) and software sorting (post-processing). The hardware filter divides candidate objects based on geometric criteria (bounding box aspect ratio, area) while the software sorts remaining candidates using correlation analysis. This segmentation allows each stage to optimize for its specific function, achieving both high speed in filtering and high accuracy in final identification.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The hardware filter acts as an intermediary between the image capture and the software correlation analysis. It provides a simplified, pre-processed set of candidate objects to the software, reducing the complexity of the overall system by eliminating the need for the software to handle all detected objects. This intermediary layer maintains reliability through two-stage verification while reducing system complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12535883B2Eye tracker with hardware filtering and software sorting

Publication Date: 2026.01.27 ALCON INC

AI summary

In certain embodiments, an ophthalmic surgical system that tracks the movement of an eye includes a laser device, a camera, and a computer. The laser device directs a laser beam towards the eye, and the camera captures images of the eye. The computer includes hardware and software. The hardware identifies objects in the images of the eye and determines whether each object is a candidate object according to one or more filtering criteria. A candidate object represents a candidate pupil image of the pupil of the eye. The hardware informs the software of the candidate objects. The software sorts the candidate objects according to one or more sorting criteria and identifies a candidate object as the pupil image according to the sorted candidate objects. The software tracks the movement of the eye using the pupil image.