Biometric Acquisition Quotient via Genericized Identity Hashing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric systems often fail to quickly and reliably acquire biometric information, leading to repeated attempts and inefficiencies, as existing technologies lack effective methods to address failures in data collection and matching due to the absence of information about non-collected images.
Innovation Solution
The development of systems and methods to quantify biometric acquisition and identification by establishing ground-truth identities, determining image sufficiency, deriving biometric information, converting it into generic form, generating hashed user data, and making determinations on efficiency, effectiveness, and accuracy relative to time, using a computer-readable medium and hardware processor to facilitate these operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If biometric acquisition systems use traditional methods without quantification, then the system structure remains simple, but the speed and reliability of biometric data collection deteriorates due to repeated acquisition attempts
Solution Approach 1:
The system performs preliminary actions by establishing ground-truth identities and creating characterization scores before actual biometric matching occurs. This allows the system to pre-evaluate image sufficiency and predict acquisition outcomes, reducing the need for repeated acquisition attempts and improving overall speed without proportionally increasing complexity
Solution Approach 2:
The system implements feedback mechanisms by calculating acquisition quotients and effectiveness metrics based on ground-truth comparisons. This feedback loop enables the system to learn from previous acquisition attempts and adjust parameters to improve reliability while maintaining manageable system complexity through automated optimization
2Measurement precision
If the system performs comprehensive biometric characterization and matching, then identification accuracy improves, but processing time increases due to multiple determination steps
Solution Approach 1:
The biometric identification process is segmented into distinct determination steps: first determining image sufficiency, then deriving biometric information, converting to generic form, generating hashed user data, and finally making the matching determination. This segmentation allows each step to be optimized independently and enables parallel processing where applicable, reducing overall processing time while maintaining high accuracy
Solution Approach 2:
The system performs preliminary characterization and generates ground-truth data before actual identification operations. This pre-processing creates ready-to-use reference data that accelerates the matching process while ensuring accurate results through pre-validated characterization scores
3Reliability
If the system collects and stores detailed biometric information for analysis, then reliability of acquisition metrics improves, but information loss increases for non-collected images
Solution Approach 1:
The system uses ground-truth identities as an intermediary layer between raw biometric images and acquisition metrics. By comparing actual acquisition results against pre-established ground-truth data, the system can reliably evaluate acquisition performance without needing to store or process every individual biometric image, thus maintaining reliability while minimizing information loss
Solution Approach 2:
The system creates copies of essential reference data (ground-truth identities and characterization scores) that enable metric evaluation without requiring access to the original non-collected images. This copying approach preserves the necessary information for reliability assessment while avoiding the storage burden of complete image archives
Data Source
AI summary
Systems and methods are described, and an example system creates a transaction between a biometric station and a user in a group of users. Transaction includes establishing for the user, a ground-truth identity, capturing an image of the user in the biometric station, making a first determination of whether the image is sufficient for identification of the user. When the image is sufficient, the transaction derives biometric information from the image, converts the biometric information into a generic-form biometric information, agnostic of how the biometric information was obtained, and generated hashed user data by applying a hash function to the generic-form biometric information. The transaction makes a second determination, based on the hashed user data, of whether the user is represented in a gallery of sample images. The transactions are repeated for other users in the group. In the repeats, when the image is determined sufficient, another second determination is made, generating a plurality of second determinations. An acquisition quotient is calculated for the plurality of second determinations, based on one of efficiency, effectiveness, and accuracy relative to time.