Biometric Matching Using Parallel Processing and Cloud Resources
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric matching systems face inefficiencies in identifying or authenticating biometric information due to the linear growth of time required as the database size increases, making large-scale searches time-consuming.
Innovation Solution
A system utilizing parallel processing and cloud-based resources for pre-processing and matching biometric data, employing a watch list with sorted index values and blob data stored across different partition servers for efficient searching and matching.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a typical biometric matching system compares the sample with entries in the database one by one, then the system can find matching entries, but the time to find a matching entry grows linearly and may be time consuming when the database includes many entries
Solution Approach 1:
The patent divides the biometric database into multiple partitions or subsets, allowing parallel processing of different database segments. This segmentation enables the system to process multiple entries simultaneously rather than sequentially, reducing overall search time while maintaining matching accuracy through comprehensive coverage of all database entries.
Solution Approach 2:
The patent performs preliminary processing of biometric data, such as extracting key features or creating index structures before the actual matching process. This preliminary action prepares the data in advance, enabling faster comparison operations during the matching phase without compromising the accuracy of the biometric identification.
2Productivity
If parallel processing is used to speed up biometric matching, then the search time is reduced, but the system complexity and resource requirements increase
Solution Approach 1:
The patent segments the biometric database into multiple partitions that can be processed in parallel. Each partition can be handled by separate processing units or threads, enabling concurrent matching operations. This segmentation approach increases matching speed while managing system complexity by organizing data into manageable, independent units that can be processed simultaneously.
3Power
If cloud-based resources are leveraged for parallel processing, then processing power is increased, but the cost and data transmission requirements increase
Solution Approach 1:
The patent implements a hybrid approach where only certain processing tasks are offloaded to cloud-based resources while others are handled locally. This partial action strategy allows the system to leverage cloud computing power for intensive parallel processing operations when needed, while performing simpler operations locally to reduce data transmission costs and energy consumption, optimizing the balance between processing power and resource utilization.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Biometric matching technology, in which a watch list is managed, multiple images of a potential suspect are accessed, and parallel pre-processing of the multiple images is controlled. Based on the pre-processing, an image of the potential suspect to use in matching against the watch list is determined and the determined image is used to search sorted biometric data included in the watch list. A subset of persons from the watch list is identified based on the search and parallel analysis of the determined image of the potential suspect against detailed biometric data associated with the subset of persons in the watch list is controlled. Based on the parallel analysis, it is determined whether the potential suspect matches a person in the watch list and a result is outputted based on the determination.