Biometric Spoof Detection Using Matcher Alignment Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional biometric authentication systems face challenges in accurately distinguishing between live and spoofed fingerprint images due to the lack of alignment in anti-spoof feature extraction, leading to lower spoof detection accuracy.
Innovation Solution
The system utilizes alignment information from the matcher to identify overlapping and non-overlapping regions of the input image relative to the enrollment image, extracting anti-spoof features from these regions and assigning different weights to improve spoof detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional anti-spoof feature extraction is used without alignment information, then the processing is simpler, but the spoof detection accuracy is lower
Solution Approach 1:
The system performs alignment between the input fingerprint image and enrollment image before extracting anti-spoof features. This preliminary alignment action ensures that corresponding regions are properly matched, enabling more accurate spoof detection. The alignment information is obtained in advance and used to guide the subsequent feature extraction process from overlap and non-overlap regions.
Solution Approach 2:
The fingerprint image is divided into overlap region and non-overlap region based on alignment information. By segmenting the image into these distinct regions, the system can extract anti-spoof features differently from each region, improving detection accuracy. The overlap region contains corresponding features between input and enrollment images, while the non-overlap region contains unique features from the input image.
2Measurement precision
If alignment information is used to extract anti-spoof features from overlap and non-overlap regions, then spoof detection accuracy improves, but the processing time increases
Solution Approach 1:
The system extracts only the necessary alignment information from the matcher and uses it to identify overlap and non-overlap regions for anti-spoof feature extraction. By extracting only the essential alignment data rather than processing entire images repeatedly, the system reduces processing time while maintaining improved spoof detection accuracy through region-based feature extraction.
Data Source
AI summary
Disclosed is 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; obtaining, by the processor, alignment information that aligns the input image to an enrollment image; determining, by the processor, an overlap region and a non-overlap region of the input image relative to the enrollment image; extracting, by the processor, one or more anti-spoof features from the input image based on one or more of the overlap region and the non-overlap region; and, determining, by the processor, whether the input image is a replica of the biometric based on the one or more anti-spoof features.