AI Eye Protrusion Estimation From Front Facial Images

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for estimating eye protrusion value using front facial images are inaccurate and require specialized medical devices, making it difficult for ordinary individuals to accurately measure and manage exophthalmos without professional assistance.

Innovation Solution

A method utilizing a personal electronic device to capture a front facial image, generate a depth image, and estimate eye protrusion value using a pre-trained neural network model that combines facial and depth images, providing accurate measurements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a side image is used to estimate eye protrusion value, then measurement accuracy is improved, but ease of operation deteriorates because the user must face forward and capture the image from a perpendicular direction

Engineering Contradiction:

Improveeye protrusion value accuracyVSAvoidimage capture convenience

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent inverts the traditional approach by using a front image (facing the user) instead of a side image (perpendicular to the user) to estimate eye protrusion value. This inversion allows users to easily capture images with their mobile devices while maintaining measurement capability through AI-based analysis of frontal facial features.

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The patent replaces the mechanical requirement of specific positioning and angle (side view at perpendicular direction) with an AI-based image processing system that can extract eye protrusion information from front-facing images, eliminating the need for precise manual positioning.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If a front image is used to estimate eye protrusion value, then ease of operation is improved, but measurement precision deteriorates because the degree of eyeball protrusion cannot be recognized with the naked eye in a 2D image

Engineering Contradiction:

Improveimage capture convenienceVSAvoideye protrusion value accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces an AI-based image processing system as an intermediary between the front image and the eye protrusion measurement. This intermediary extracts subtle facial features and depth information from the 2D front image that are not visible to the naked eye, enabling accurate measurement without requiring side view imaging.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent compensates for the loss of depth information in 2D front images by using AI algorithms to infer three-dimensional eye protrusion characteristics from two-dimensional facial features, effectively adding a depth dimension through computational analysis.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Measurement precision

If specialized medical devices are used to measure eye protrusion value, then measurement precision is improved, but device complexity and accessibility worsen

Engineering Contradiction:

Improveeye protrusion value accuracyVSAvoidmeasurement device accessibility

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates a functional copy of medical-grade eye protrusion measurement capability using a standard mobile device camera combined with AI processing. This copy replicates the measurement function without requiring specialized medical equipment, making the technology accessible to ordinary individuals for self-monitoring.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent enables a universal mobile device to perform the specialized function of eye protrusion measurement, transforming a common consumer device into a multi-functional tool that can both capture images and provide medical-grade measurements through integrated AI processing.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12539037B2Method for estimating eye protrusion value, and system for performing same

Publication Date: 2026.02.03 THYROSCOPE INC

AI summary

According to an embodiment disclosed in the present application, proposed is a method for estimating an eye protrusion value, the method including: obtaining an image representing at least one eye of the subject, wherein the image includes a plurality of pixels assigned a value corresponding to at least one of brightness and color; obtaining a pre-processed image by performing a previously stored pre-processing for the image; obtaining a depth image corresponding to the pre-processed image by applying the pre-processed image to a pre-trained depth image generation model, wherein the depth image includes a plurality of pixels, wherein each of the plurality of pixels of the depth image is assigned a depth value representing a relative distance of an object corresponding to each of a plurality of pixels of the pre-processed image; and estimating an eye protrusion value for the eye of the subject by applying both the pre-processed image and the depth image to a pre-trained eye protrusion value estimation model.