Eye-Gaze Authentication in Head-Mounted Displays

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing user authentication methods, such as face video authentication, are complex and time-consuming, leading to low efficiency.

Innovation Solution

An image processing method using a head-mounted display device to instruct users to observe a specified position, obtain eye images, and determine authentication based on the relationship between key points of the eyes, allowing the device to rotate with the user's head to accurately authenticate by observing the specified position.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If face video authentication is used, then user authentication can be performed, but the operation process becomes complex and time-consuming

Engineering Contradiction:
Improveauthentication accuracyVSAvoidoperation complexity
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent extracts the essential authentication element from complex face video authentication to a simple eye movement detection task. Instead of requiring multiple facial actions (blinking, shaking head, adjusting angles), the system only needs to detect eye key point positions and their relationships, simplifying the authentication process while maintaining reliability

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent inverts the traditional authentication approach by using head-mounted display that rotates with the user's head, making the device adapt to the user rather than requiring the user to adapt to the device. This eliminates the need for users to adjust photographing angles and distances

Inventive Principle:
Principle #13The other way round (Inversion)

2Reliability

If face video authentication with multiple operations is used, then authentication security can be ensured, but authentication time increases

Engineering Contradiction:
Improveauthentication securityVSAvoidauthentication duration
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent uses partial action by detecting only eye key point positions and their spatial relationships rather than requiring complete face video authentication with multiple actions. This partial detection is sufficient for authentication purposes, reducing time while maintaining security

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent changes the authentication parameter from multiple temporal actions (sequence of blinking, shaking, holding poses) to a spatial parameter (eye key point positions and their relationships). This parameter transformation enables faster authentication while preserving security

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If traditional face authentication requiring angle and distance adjustment is used, then authentication accuracy can be maintained, but user operation complexity increases

Engineering Contradiction:
Improveface capture accuracyVSAvoidauthentication system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies dynamics by making the head-mounted display rotate together with the user's head, creating a dynamic system that adapts to user movement. This eliminates the need for static positioning and angle adjustment, reducing operational complexity while maintaining capture accuracy through real-time adaptation

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS20260003947A1Image processing for authentication
Publication Date: 2026.01.01 TENCENT TECHNOLOGY (SHENZHEN) CO LTD
  • US20260003947A1 patent drawing
  • US20260003947A1 patent drawing
  • US20260003947A1 patent drawing

AI summary

Some aspects of the disclosure provide a method of image processing for authentication. In some examples, indication information is displayed by a head-mounted display device, the indication information instructs a user of the head-mounted display device to observe a specified position in a display space of the head-mounted display device. An eye image of the user is obtained. Key point positions of at least two key points of an eye of the user are obtained from the eye image. An observing position of the user is determined based on relationships between the key point positions of the at least two key points. When the observing position of the user matches with the specified position, an authentication of the user is determined to succeed. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.