Vehicle Face Authentication Using Mobile Terminal Learning Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional face authentication systems in vehicles suffer from decreased performance due to variations in the driver's posture, wearing sunglasses, hairstyle, or hats, which affect the accuracy of infrared image recognition.

Innovation Solution

A vehicle terminal and mobile terminal system that uses short-range wireless communication to learn facial features from images stored on the mobile terminal, allowing for improved face authentication by analyzing face images obtained through an infrared camera and automatically registering user profiles, regardless of ambient lighting conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional infrared face authentication is used, then the authentication function is provided, but the recognition performance deteriorates when driver conditions change (posture, sunglasses, hairstyle, hat)

Engineering Contradiction:
Improveface authentication performanceVSAvoidadaptability to driver condition changes
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary face registration by capturing and storing multiple face images under various conditions before actual authentication. This preliminary action creates a reference database that accounts for potential variations in driver appearance, enabling more reliable authentication when conditions change.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts authentication thresholds and parameters based on the registered variation data. Instead of using fixed authentication criteria, the system adapts its evaluation standards to account for the range of normal variations in driver appearance, improving both reliability and adaptability.

Inventive Principle:
Principle #15Dynamics

2Ease of operation

If multiple user profiles are registered, then user personalization is improved, but the complexity of managing and distinguishing profiles increases

Engineering Contradiction:
Improveuser profile personalizationVSAvoidprofile management complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system creates simplified visual copies of user profiles using representative images or icons that are easily distinguishable. Instead of managing complex profile data structures, the system uses visual representations that users can quickly identify, reducing the perceived complexity while maintaining full personalization capabilities.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system replaces manual profile selection mechanisms with automatic recognition and identification. Instead of requiring users to navigate through menus and select profiles manually, the system automatically identifies and switches between profiles using biometric or recognition-based methods, significantly reducing operational complexity.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10755083B2Terminal for vehicle and method for authenticating face
Publication Date: 2020.08.25 HYUNDAI MOTOR CO LTD
  • US10755083B2 patent drawing
  • US10755083B2 patent drawing
  • US10755083B2 patent drawing

AI summary

A vehicle terminal automatically registering a profile image of a user to a vehicle using images stored in a mobile terminal of a user and performing a face authentication includes a communicator that performs a data communication with the mobile terminal of the user, a camera that obtains a face image of the user, and a processor that registers the profile image of the user using an image among the images stored in the mobile terminal. The processor learns a facial feature of the user using the images stored in the mobile terminal as learning data and analyzes the face image obtained through the camera based on the learned facial feature of the user to perform the face authentication of the user.