Facial Recognition Authentication Using Wearable ID Codes

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Facial recognition systems for authentication are slow and lack adequate security due to the need to compare extracted facial features against all data in a database, often requiring a single level of authentication and delaying the verification process until a subject's face is identified.

Innovation Solution

A method and system that utilize a broadcast device to send an identification code, allowing pre-identification of stored facial data associated with the code, generating and comparing second facial data for rapid authentication, and optionally incorporating gait data for enhanced security.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If facial features are extracted and compared against all database data, then authentication accuracy is maintained, but authentication speed deteriorates

Engineering Contradiction:
Improveauthentication accuracyVSAvoidauthentication speed
Core Design Contradiction:
Measurement precisionVSSpeed

Solution Approach 1:

The system performs preliminary actions by receiving and processing the identification code from the wearable device before the facial recognition process begins. This pre-identification step prepares the system in advance, allowing the facial feature comparison to start immediately with pre-loaded reference data, thus maintaining accuracy while reducing wait time.

Inventive Principle:
Principle #10Preliminary action

2Device complexity

If single-level facial recognition authentication is used, then system simplicity is maintained, but security level deteriorates

Engineering Contradiction:
Improvesystem simplicityVSAvoidsecurity level
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The system merges two distinct authentication methods into a unified process: wearable device identification (first level) and facial recognition verification (second level). This combination creates a multi-factor authentication system that enhances security while maintaining operational simplicity through automated sequential processing.

Inventive Principle:
Principle #5Merging (Combining)

3Use of energy by moving object

If facial recognition process begins only after face picture is identified, then system resource usage is optimized, but user wait time increases

Engineering Contradiction:
Improvesystem resource usageVSAvoiduser wait time
Core Design Contradiction:
Use of energy by moving objectVSLoss of time

Solution Approach 1:

The system performs preliminary processing by receiving the identification code from the wearable device before initiating the facial recognition process. This allows the system to prepare reference data and configure processing parameters in advance, so that when the user presents their face, the comparison can begin immediately without delay.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10014967B2System and method for authenticating a broadcast device using facial recognition
Publication Date: 2018.07.03 ZEPP INC
  • US10014967B2 patent drawing
  • US10014967B2 patent drawing
  • US10014967B2 patent drawing

AI summary

Systems and methods for authenticating a broadcast device using facial recognition are herein disclosed. The disclosure includes receiving, from a wearable device, a broadcast signal comprising an identification code of the wearable device; determining, using a processor, whether the identification code is stored within a database; identifying first facial data stored within the database, the first facial data associated with the identification code; generating second facial data; and determining, using the processor, whether the second facial data matches the first facial data. In an implementation, the broadcast device is a Bluetooth low energy device. In a further implementation, the broadcast device comprises the wearable device. In a still further implementation, the disclosure includes detecting gait data and determining whether the gait data matches gait feature data extracted from stored gait data features.