Facial Recognition Using Distributed Personal Databases

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current facial recognition systems are not accessible to the general public due to high costs and the need for a database of images, and they require individuals to be present geographically, limiting their use for identifying real-time images.

Innovation Solution

A method and system that allows individuals to determine if an unknown 'twin' exists by capturing a digital image with a wireless communication device, processing it into a feature vector, and comparing it to a large image database using facial recognition software, with results sent back to the user's device or PC, incorporating human perception values for improved matching.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If facial recognition systems are implemented using traditional centralized databases and feature recognition software, then identification accuracy is improved, but system cost and complexity increase making it inaccessible to the general public

Engineering Contradiction:
Improveidentification accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system divides the centralized database into distributed personal image databases, where each user maintains their own database locally or on personal servers. This segmentation reduces the complexity and cost barriers while maintaining identification accuracy through distributed comparison capabilities.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces wireless communication devices and image transmission protocols as intermediaries between users and the facial recognition system. This allows users to participate in the system without directly managing complex database infrastructure, reducing the perceived complexity while maintaining functionality.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If facial recognition requires geographic presence and centralized database access, then measurement precision is maintained, but ease of operation deteriorates limiting real-time image identification

Engineering Contradiction:
Improvematching accuracyVSAvoiduser accessibility
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

Users can independently upload, store, and manage their own facial images and personal databases without requiring centralized system intervention. This self-service capability enables real-time image identification from anywhere in the world, improving ease of operation while maintaining matching accuracy through consistent recognition algorithms.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system transitions from requiring geographic presence at centralized facilities to enabling remote access through wireless networks and digital image transmission. This adds the dimension of spatial freedom, allowing users to perform facial recognition operations from any location while maintaining the same level of matching accuracy.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Reliability

If large centralized databases are used for facial recognition, then identification completeness is improved, but loss of time increases due to data transmission and processing delays

Engineering Contradiction:
Improveidentification completenessVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

By distributing the large centralized database into multiple smaller personal databases, the system reduces data transmission requirements and enables faster local processing. Each personal database maintains sufficient completeness for practical identification purposes while reducing the time needed to transmit and process data.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Users pre-upload and store their facial images in personal databases before needing identification. This preliminary action ensures that when real-time identification is needed, the system can perform rapid comparisons without waiting for data transmission from centralized sources, reducing processing time while maintaining completeness.

Inventive Principle:
Principle #10Preliminary action

4Measurement precision

If traditional facial recognition systems are deployed, then measurement precision is maintained, but ease of manufacture deteriorates due to high implementation costs

Engineering Contradiction:
Improvefeature recognition accuracyVSAvoidimplementation cost
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The system replaces expensive, permanent centralized database infrastructure with cheaper, distributed personal databases that can be implemented using consumer-grade storage and processing. This reduces implementation costs significantly while maintaining feature recognition accuracy through the same underlying algorithms.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

Solution Approach 2:

The patent enables a single facial recognition algorithm to serve multiple users and purposes through distributed personal databases, eliminating the need for separate expensive implementations for each user. This universal application of the recognition technology across multiple personal databases reduces overall implementation costs while maintaining precision.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS8199980B2Digital image search system and method
Publication Date: 2012.06.12 MOTOROLA SOLUTIONS INC
  • US8199980B2 patent drawing
  • US8199980B2 patent drawing
  • US8199980B2 patent drawing

AI summary

A method and system for matching an unknown facial image of an individual with an image of an unknown twin using facial recognition techniques and human perception is disclosed herein. The invention provides a internet hosted system to find, compare, contrast and identify similar characteristics among two or more individuals using a digital camera, cellular telephone camera, wireless device for the purpose of returning information regarding similar faces to the user The system features classification of unknown facial images from a variety of internet accessible sources, including mobile phones, wireless camera-enabled devices, images obtained from digital cameras or scanners that are uploaded from PCs, third-party applications and databases. The method and system uses human perception techniques to weight the feature vectors.