Face-Based Key Generation Using Stable Feature Indices

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing facial recognition-based encryption technologies face challenges in generating unique cryptographic keys due to non-uniqueness of facial features and difficulty in maintaining consistent facial expressions, leading to inaccurate user authentication.

Innovation Solution

A system that generates a binary cryptographic key using a subset of significant features from images of a person's face, utilizing a list of indices to identify stable features and determine the order of key generation, ensuring more accurate and robust encryption and authentication.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If facial recognition techniques rely on specific facial features or consistent facial expressions, then user authentication can be performed using facial images, but the features may not be unique enough to distinguish one person from another or it can be difficult for a person to maintain the same facial expression

Engineering Contradiction:
Improveauthentication accuracyVSAvoidfeature uniqueness
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent segments the facial recognition process into multiple distinct phases: image acquisition, feature extraction, feature selection based on stability criteria, and cryptographic key generation. This segmentation allows the system to focus on stable, unique features rather than attempting to rely on all facial features or expressions, thereby resolving the contradiction between authentication reliability and feature uniqueness.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the parameters used for authentication from traditional facial expressions or simple features to a cryptographic key derived from multiple stable facial features. By transforming the authentication parameter from qualitative (expression matching) to quantitative (cryptographic key comparison), the system achieves both high reliability and precision in distinguishing individuals.

Inventive Principle:
Principle #35Parameter changes

2Loss of information

If traditional facial recognition uses all available facial features, then more information is available for authentication, but the stability and consistency of these features across different images may vary

Engineering Contradiction:
Improvefacial feature informationVSAvoidfeature stability
Core Design Contradiction:
Loss of informationVSStability of the object's composition

Solution Approach 1:

The patent extracts and selects only the most stable and significant facial features from the complete set of available features. By taking out and isolating these specific stable features (such as distances between landmarks, angles of facial contours) while excluding variable features like expressions or temporary conditions, the system maintains both information quality and feature stability.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent performs preliminary feature selection and stability analysis before generating the cryptographic key. By pre-identifying which facial features are stable across multiple images and pre-processing them into a consistent format, the system ensures that the information used for authentication is both comprehensive and stable, resolving the contradiction between information retention and feature consistency.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20240235827A1Face-based key generation
Publication Date: 2024.07.11 REALNETWORKS LLC
  • US20240235827A1 patent drawing
  • US20240235827A1 patent drawing
  • US20240235827A1 patent drawing

AI summary

A system includes a camera and a computing device. The computing device receives images captured by the camera and generates a face signature for a person in the images. Significant features are identified in the face signature. And a subset of those significant features are selected and used to generate a binary cryptographic key for the person.