Biometric Matching System for Small-Area Sample Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fingerprint identification systems face challenges in matching enrolled fingerprint images with live scan images due to improper orientation or small-area imaging, leading to false rejections, as the captured detail may not represent the same surface as the stored specimen.
Innovation Solution
Implementing a biometric matching system that compares large-area biometric specimens with small-area samples, using a combination of large-area and small-area biometric scanners, where the computer software determines if the small-area sample matches a portion of the large-area specimen, allowing for efficient matching even with non-optimal finger placement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If small-area biometric imaging devices are used for authorization purposes, then the cost of the biometric authorization system is reduced, but the matching accuracy deteriorates due to improper orientation or non-optimal finger placement
Solution Approach 1:
The patent segments the biometric verification process into two distinct phases: enrollment using large-area scanners to capture complete biometric specimens, and authorization using small-area scanners to capture biometric samples. This segmentation allows each scanner type to be optimized for its specific function, reducing overall system cost while maintaining accuracy.
Solution Approach 2:
The patent introduces software as an intermediary that bridges the gap between small-area samples and large-area specimens. The software performs feature extraction, registration, and comparison operations that enable accurate matching despite the area discrepancy, thereby maintaining reliability while using cheaper hardware.
2Device complexity
If small-area biometric imaging devices are used, then the device complexity is reduced, but the ability to capture sufficient biometric detail deteriorates
Solution Approach 1:
The patent performs preliminary action by capturing complete biometric specimens using large-area scanners during the enrollment phase. This preliminary capture of full detail allows subsequent small-area authorization scans to be accurately matched through software comparison, even though the authorization scans themselves contain less detail.
Solution Approach 2:
The patent creates a digital copy (enrollment specimen) using a large-area scanner that preserves complete biometric detail. This copy is stored in a database and used for comparison during authorization, allowing small-area scanners to function effectively without losing critical information.
3Reliability
If large-area biometric imaging devices are used for both enrollment and authorization, then the matching accuracy is maintained, but the system cost increases
Solution Approach 1:
The patent applies local quality by assigning different scanner types to different functional locations in the system: large-area scanners are used only where complete detail capture is critical (enrollment), while small-area scanners are used where cost reduction is prioritized (authorization). This differentiated approach maintains accuracy where needed while reducing overall cost.
Solution Approach 2:
The patent changes the parameter of scanner area between enrollment and authorization phases. Large-area scanners are used during enrollment to capture complete specimens, while small-area scanners are used during authorization to reduce costs. Software parameter adjustments enable accurate matching across this parameter change.
Data Source
AI summary
Methods and systems according to the invention may compare a large-area biometric specimen and a small-area biometric sample. For example, a large-area plain surface fingerprint image may be stored in a fingerprint database as a specimen, and then a small-area plain surface fingerprint image may be acquired as a sample. The small-area image sample may be submitted to a fingerprint matching system for comparison with a large-area image specimen from the database. A determination may be made as to whether the small-area image matches a portion of the large-area image.