Adaptive Short Lists for Biometric Database Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large biometric databases face inefficiencies in matching processes due to the need to analyze millions of records in real-time, requiring significant processor power and resulting in lengthy processing times.
Innovation Solution
A staged scoring procedure is implemented, using increasingly accurate scoring routines to iteratively narrow down potential matches, with each phase eliminating a significant percentage of records, allowing for faster processing by focusing on smaller subsets of data, and eliminating the need for sorting by using adaptive scoring thresholds and parallel processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a comprehensive comparison is performed against all records in the biometric database, then the accuracy of match identification is improved, but the processing time increases significantly
Solution Approach 1:
The patent divides the biometric database into multiple partitions or subsets, allowing the comparison process to be broken down into smaller, manageable segments. Instead of comparing against all records simultaneously, the system processes divided portions sequentially or in parallel, reducing the time complexity from O(n) to O(n/k) where k is the number of partitions, while maintaining comprehensive coverage through systematic processing of all segments.
Solution Approach 2:
The patent implements preliminary filtering or indexing operations before the main comparison process. By pre-processing the database to create indexes, hash tables, or preliminary candidate sets based on key biometric features, the system eliminates obviously non-matching records in advance, reducing the number of records requiring full comparison and thus decreasing processing time while preserving accuracy for the remaining candidates.
2Measurement precision
If a comprehensive comparison is performed against all records in the biometric database, then the accuracy of match identification is improved, but the processor power required increases significantly
Solution Approach 1:
The patent divides the biometric database into multiple partitions or subsets, allowing the comparison process to be broken down into smaller, manageable segments. Instead of comparing against all records simultaneously, the system processes divided portions sequentially or in parallel, reducing the time complexity from O(n) to O(n/k) where k is the number of partitions, while maintaining comprehensive coverage through systematic processing of all segments.
Solution Approach 2:
The patent applies partial comparison strategies where not all biometric features are compared for every record. Instead, the system performs selective comparisons based on key discriminative features or uses progressive refinement where initial coarse comparisons filter candidates before more detailed feature-by-feature comparisons are performed on a reduced subset, reducing overall computational load while maintaining match accuracy.
3Measurement precision
If high-resolution models are used for all records, then the accuracy of comparison is improved, but the processing time and computational resources required increase
Solution Approach 1:
The patent applies different model resolutions to different records or different stages of processing based on their likelihood of being matches. High-resolution models are applied selectively to candidate records that pass preliminary filtering, while lower-resolution or simplified models are used for the majority of records that are unlikely to match, optimizing the balance between comparison accuracy and processing throughput by allocating computational resources locally where most needed.
Data Source
AI summary
A system for comparing a biometric sample against a biometric dataset is provided. In one embodiment, a system for comparing a biometric sample against a biometric dataset comprises a database storing at least one biometric dataset. The system may also comprise a comparison module configured to iteratively provide a comparison score for each record in the biometric dataset, wherein the comparison score indicates a likelihood of match between an individual record in the biometric dataset and the biometric sample; wherein, during each iteration. The steps in the iteration may comprise retrieving a model of each of the plurality of records. The steps in the iteration may also comprise comparing the model of each of the plurality of records against the biometric sample. The steps in the iteration may also comprise generating the comparison score for each of the plurality of records. The steps in the iteration may also comprise iteratively compare the biometric sample against a plurality of records. The steps in the iteration may also comprise wherein the resolution of the retrieved model increases with each iteration, and where the iterative process continues until a final list of potential match candidates is determined. The system may also comprise a processor configured to receive data indicative of the biometric sample and iteratively engage the comparison model such that results of the first iteration are provided as an input to a second iterator.