Eye Close Degree Measurement via Relative Amplitude

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image processing technologies fail to accurately measure human eye close degrees during blinking, limiting their applicability in controlling applications based on eye movements.

Innovation Solution

A method and apparatus that determine human eye close degrees by calculating a relative amplitude of the eye open amplitude relative to a reference distance, using face key points and nose key points, and then use this measurement to control virtual eyes in face models to simulate blinking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing image processing technologies are used to detect eye movements, then basic eye detection can be achieved, but accurate measurement of human eye close degrees during blinking cannot be obtained

Engineering Contradiction:

Improveeye close degree measurementVSAvoidblink detection accuracy

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent transforms the eye detection problem from binary open/closed detection to continuous parameter measurement by calculating the distance between eye landmark points and normalizing it against a reference distance. This creates a relative amplitude parameter that continuously reflects eye closure degree, enabling precise measurement of blinking dynamics rather than simple state detection.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent introduces a reference distance as an intermediary parameter to normalize the raw eye distance measurements. By dividing the calculated eye distance by the reference distance (obtained from nose landmark points), the system creates a dimensionless relative amplitude that accurately represents eye closure degree independent of individual facial characteristics, thereby improving measurement precision and reliability.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of operation

If face models are used to simulate eye movements, then visual feedback can be provided, but the eye movements lack realism and responsiveness

Engineering Contradiction:

Improveeye control responsivenessVSAvoideye movement realism

Core Design Contradiction:

Ease of operationVSManufacturing precision

Solution Approach 1:

The patent implements a feedback loop where the calculated relative amplitude from the user's actual eye movements directly controls the eye movements of the virtual face model. The relative amplitude serves as real-time feedback that drives the animation, ensuring the model's eye movements mirror the user's actual blinking behavior with high responsiveness and realism.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent copies the user's actual eye movement patterns into the virtual face model by using the same relative amplitude calculation for both detection and control. This copying approach ensures that the simulated eye movements are an accurate reflection of the user's real-eye behavior, enhancing both realism and responsiveness simultaneously.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS11775059B2Method for determining human eye close degrees, method for controlling eyes, device, and storage medium

Publication Date: 2023.10.03 BIGO TECH PTE LTD

AI summary

A method for determining human eye close degrees includes: acquiring a face image; determining a human eye open amplitude and a reference distance in the face image; calculating a relative amplitude of the human eye open amplitude relative to the reference distance; acquiring a maximum relative amplitude; and calculating a human eye close weight in the face image based on the relative amplitude and the maximum relative amplitude, the human eye close weight being configured to measure a human eye close degree.