Correlated Boosted Entity Model for Identity Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current identity verification methods, particularly in large-scale data searches, face inefficiencies and inaccuracies when using one-to-one verification models, especially when dealing with numerous samples, leading to time-consuming and potentially inaccurate results.
Innovation Solution
A system and method for training and utilizing a correlated boosted entity model, which groups features into subsets, uses classifiers to determine correct classifications, and employs boosting to refine features for subsequent training rounds, enhancing the accuracy and efficiency of identity verification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If one-to-one verification is performed on a specific image or template, then verification speed is improved, but verification accuracy deteriorates when the case has a large number of samples
Solution Approach 1:
The patent segments the verification process into multiple independent feature models (e.g., face, fingerprint, iris, behavioral biometrics). Each feature model processes specific features independently, allowing parallel verification operations that maintain speed while improving accuracy through multiple verification dimensions.
Solution Approach 2:
The patent creates a composite verification model that integrates multiple different feature types (facial features, fingerprints, iris patterns, behavioral biometrics) into a unified verification system. This composite approach combines the strengths of different biometric modalities to achieve both speed and accuracy.
2Measurement precision
If a large identification search is run on a gallery of data, then verification accuracy is improved, but time consumption increases significantly
Solution Approach 1:
The patent divides the large-scale identification search into multiple independent feature-based sub-searches. Each feature model (face, fingerprint, iris, etc.) performs parallel verification operations on the gallery data, reducing overall processing time while maintaining comprehensive search coverage through multiple feature dimensions.
Solution Approach 2:
The patent performs partial verification actions by checking multiple feature types simultaneously rather than exhaustively analyzing all possible features sequentially. This allows the system to achieve sufficient verification accuracy through a subset of verified features, significantly reducing time consumption.
3Measurement precision
If multiple feature models are used for verification, then verification accuracy is improved, but system complexity increases
Solution Approach 1:
The patent segments the complex verification system into multiple independent, modular feature models. Each model handles a specific feature type with dedicated processing logic, making the overall system more manageable and easier to maintain despite the increased number of components.
Solution Approach 2:
The patent implements a universal verification framework that can handle multiple feature types (face, fingerprint, iris, behavioral biometrics) through a common architecture. This multi-functional design allows the same system structure to process different biometric modalities, reducing complexity compared to having separate systems for each feature type.
Data Source
AI summary
A system, method and program product training and verifying using an identity or entity model. A training system is disclosed that includes: a feature correlation system that groups features from an inputted feature data sample into subsets; a plurality of classifiers that determine if each feature classifies into an associated one of a plurality of feature models that make up the entity model; and a boosting system that boosts features from a subset for a next round of training if any of the features classify and at least one correlated feature from the subset does not classify. A verification system is disclosed that includes an identity model for the entity comprising a plurality of feature models, wherein each feature model is utilized to model a unique feature; a system for receiving a feature data sample and partitioning the feature data sample into a plurality of features; a system for determining if each of the plurality of features classifies into an associated feature model; and a voting system for analyzing a result of each attempted classification and determining an overall verification result.