3D Biometric Feature Detection Using Surface Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current biometric systems relying on two-dimensional fingerprint images lose potentially useful data when converting 3D biometric image data into grayscale or binary formats for compatibility with existing standards, limiting the effectiveness of feature detection, validation, classification, and recognition.
Innovation Solution
A system and method for processing 3D biometric data using a 3D image sensor and processing module that generates a 3D surface map, allowing for the detection and recognition of biometric features with 3D coordinates and texture data, while also converting data into 2D formats for compatibility with existing databases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If 3D biometric image data is converted into grayscale or binary formats for compatibility with existing standards, then compatibility with existing databases is improved, but detection precision and recognition accuracy deteriorate due to loss of 3D information
Solution Approach 1:
The patent applies dimensionality change by maintaining 3D surface map data alongside 2D converted data. The system processes biometric data in both 2D and 3D dimensions, using the 3D surface map to preserve depth information (ridge height, furrow depth) while also generating 2D representations for database compatibility. This allows the system to operate in multiple dimensional spaces simultaneously, resolving the contradiction between compatibility and precision.
2Adaptability or versatility
If 3D biometric image data is converted into grayscale or binary formats, then compatibility with existing standards is improved, but recognition accuracy deteriorates due to loss of useful data
Solution Approach 1:
The patent segments the biometric data processing into separate pathways: one for 3D surface map generation and analysis, and another for 2D conversion and database storage. The system segments the feature detection process to identify and extract 3D-specific features (such as ridge height and furrow depth) that would be lost in 2D conversion, while maintaining separate 2D data for standard database compatibility. This segmentation allows both 3D and 2D processing to occur simultaneously without interfering with each other.
Solution Approach 2:
The system maintains 3D dimensional information through surface maps while also producing 2D representations for database storage. By operating in both dimensional spaces, the system can leverage the enhanced accuracy of 3D feature detection while preserving compatibility with existing 2D-based databases, thus improving recognition accuracy without sacrificing adaptability.
3Device complexity
If only two-dimensional biometric images are used, then device complexity is reduced, but feature detection capability deteriorates due to loss of depth information
Solution Approach 1:
The patent introduces 3D dimensional analysis through surface map generation while maintaining the ability to process 2D data. The system adds depth information capture and processing capabilities to the existing biometric system, enabling detection of three-dimensional features such as ridge height and furrow depth that are invisible in 2D images. This dimensional enhancement improves feature detection capability without completely redesigning the system.
Data Source
AI summary
The system includes a 3D feature detection module and 3D recognition module 202. The 3D feature detection module processes 3D surface map of a biometric object, wherein the 3D surface map includes a plurality of 3D coordinates. The 3D feature detection module determines whether one or more types of 3D features are present in the 3D surface map and generates 3D feature data including 3D coordinates and feature type for the detected features. The 3D recognition module compares the 3D feature data with biometric data sets for identified persons. The 3D recognition module determines a match between the 3D feature data and one of the biometric data sets when a confidence value exceeds a threshold.