Biometric Spoof Detection Using Differential Anti-Spoof Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional biometric authentication systems face challenges in distinguishing between live and spoofed fingerprints, particularly due to variations in fingerprint images from different sensors and external factors, which can lead to false rejection or acceptance rates, and existing anti-spoofing methods rely on absolute metrics rather than relative differences.
Innovation Solution
The system employs a biometric sensor and processing system that computes differential anti-spoof metrics relative to a template, using these metrics to determine whether an input image is a replica of a biometric, thereby improving spoof detection by considering deviations from known live finger characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If absolute anti-spoof metrics are used for spoof detection, then the system can identify potential spoofs, but the detection accuracy deteriorates due to variations in fingerprint images from different sensors and external factors
Solution Approach 1:
The patent transforms the anti-spoof detection approach by changing the parameter being measured from absolute metric values to differential values. Instead of comparing absolute metric values against fixed thresholds, the system computes differences between metrics extracted from the input image and corresponding template metrics. This parameter transformation makes the detection robust to variations in sensing conditions, lighting, and pressure, as these external factors affect both the input image and template similarly, canceling out in the differential computation.
2Reliability
If conventional anti-spoofing methods are used, then spoof detection is performed, but false rejection rates increase due to variations in genuine user fingerprints
Solution Approach 1:
The patent implements a feedback mechanism where the template metrics serve as a reference derived from the user's own fingerprint characteristics. By comparing input image metrics against this personalized template and computing differential values, the system adapts to individual user variations in fingerprint patterns, skin texture, and other biometric characteristics. This feedback-based approach reduces false rejections of genuine users while maintaining high spoof detection accuracy.
Data Source
AI summary
Disclosed are a system and method for performing spoof detection. The method includes: receiving, by a processor from a biometric sensor, an input image of a biometric; extracting, by the processor, one or more anti-spoof metrics from the input image; receiving, by the processor, an anti-spoof template corresponding to the biometric; for a first anti-spoof metric, computing, by the processor, a differential value between a value of the first anti-spoof metric extracted from the input image and a value of the first anti-spoof metric in the anti-spoof template; and determining, by the processor, whether the input image is a replica of the biometric based on the differential value.