Biometric Identity Shell for Lighting-Independent Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Biometric recognition systems face challenges in recognizing users in realistic environments due to lighting conditions and require manual intervention, leading to perceived slowness and inaccuracy, especially when each application manages its own recognition system rather than it being an intrinsic component of the computing system.

Innovation Solution

A biometric recognition system using an active infrared sensor with head orientation filtering, managed by a shell program, continuously running to identify users and update their profiles, allowing for automatic sign-in and offline processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If biometric data is obtained and processed in real-time for user identification, then user recognition speed is improved, but system complexity increases

Engineering Contradiction:
Improveuser recognition speedVSAvoidsystem complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by continuously capturing and preprocessing biometric data in the background before user identification is actually needed. This allows the system to have pre-processed data ready for immediate comparison and identification, achieving fast recognition without complex real-time processing during the actual identification moment.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces a biometric identity manager as an intermediary component that handles all biometric data processing, storage, and comparison operations. This mediator layer simplifies the overall system architecture by centralizing complex biometric operations, allowing other applications to interact with a standardized interface rather than implementing their own complex recognition systems.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If manual intervention is required for user identification, then identification accuracy can be improved, but user experience deteriorates due to perceived slowness

Engineering Contradiction:
Improveidentification accuracyVSAvoiduser experience
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system implements self-service by automatically performing user identification without requiring manual intervention. The biometric identity manager continuously monitors for user presence, automatically compares captured biometric data against stored profiles, and triggers application launch or user authentication without user involvement, thereby maintaining high accuracy while eliminating the slowness associated with manual processes.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system employs feedback mechanisms where the biometric identity manager continuously monitors identification confidence levels and adjusts its behavior accordingly. When confidence is high, automatic identification proceeds; when confidence is low, the system can request additional biometric samples or prompt the user for verification, thus maintaining accuracy while minimizing manual intervention in normal operations.

Inventive Principle:
Principle #23Feedback

3Adaptability or versatility

If each application manages its own biometric recognition system, then application-specific customization is improved, but system-wide consistency deteriorates

Engineering Contradiction:
Improveapplication-specific customizationVSAvoidsystem-wide consistency
Core Design Contradiction:
Adaptability or versatilityVSStability of the object's composition

Solution Approach 1:

The patent segments the biometric recognition system into two independent parts: a centralized biometric identity manager that handles core recognition logic and data management, and application-specific modules that can request identification services. This segmentation allows each application to be customized for its specific needs while relying on the consistent, centralized identity manager for accurate and uniform biometric processing across the entire system.

Inventive Principle:
Principle #1Segmentation

4Measurement precision

If biometric data is continuously collected and processed, then user identification accuracy is improved, but data processing time increases

Engineering Contradiction:
Improveuser identification accuracyVSAvoiddata processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system implements continuous useful action by constantly capturing and preprocessing biometric data in the background without interruption. This continuous data collection and preprocessing creates a ready pool of high-quality biometric information that can be immediately used for identification when needed, achieving high accuracy without incurring processing delays at the moment of actual user identification.

Inventive Principle:
Principle #20Continuity of useful action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach provides robust lighting-independent user recognition, reduces manual intervention, and enhances accuracy by continuously managing biometric identities across all applications, creating a seamless and instantaneous user identification experience.

Implementation Method 1

The sensor can be an active infrared and/or visible light camera

Methodology Applied
Scientific EffectInfrared radiation detection: Infrared Radiation

Data Source

PatentEP2956882B1Managed biometric identity
Publication Date: 2018.06.27 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP2956882B1 patent drawingFigure 1
  • EP2956882B1 patent drawingFigure 2
  • EP2956882B1 patent drawingFigure 3

AI summary

A computing system such as a game console maintains and updates a biometric profile of a user. In one aspect, biometric data of the user is continuously obtained from a sensor such as an infrared and visible light camera, and used to update the biometric profile using a machine learning process. In another aspect, a user is prompted to confirm his or her identify when multiple users are detected at the same time and/or when the user is detected with a confidence level which is below a threshold. A real-time image of the user being identified can be displayed on a user interface with user images associated with one or more accounts. In another aspect, the biometric profile is managed by a shell on the computing system, where the shell makes the biometric profile available to any of a number of applications on the computing system.