Contactless 3D Fingerprint Recognition via Photometric Stereo
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional 2D fingerprint recognition systems face challenges due to partial or degraded images from improper finger placement and sensor noise, while 3D fingerprint technologies are hindered by high cost and inability to utilize additional surface parameters, limiting their applicability in biometric identification.
Innovation Solution
A contactless 3D biometric feature identification method using a single camera with a lighting module to capture images under different illuminations, reconstructing a 3D surface model, and extracting features such as 3D coordinates, orientations, surface curvature, and local surface orientations for enhanced fingerprint recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If contactless 3D fingerprint imaging systems are used, then fingerprint recognition accuracy is improved, but system cost and device complexity increase
Solution Approach 1:
The patent combines multiple functions (illumination control, image capture, and 3D reconstruction) into a single integrated system using a standard camera and controllable light sources, eliminating the need for separate structured lighting projectors and multiple cameras while achieving comparable 3D fingerprint recognition accuracy
Solution Approach 2:
The patent creates a photometric stereo model that copies the lighting and geometric relationships of complex 3D scanning systems, using simplified illumination patterns and standard camera equipment to reproduce the essential 3D surface information needed for accurate fingerprint recognition
2Device complexity
If traditional 2D fingerprint acquisition is used, then system cost is reduced, but image quality degrades due to partial or degraded images
Solution Approach 1:
The patent transitions from 2D fingerprint imaging to 3D surface reconstruction by capturing images under multiple illumination angles and using photometric stereo algorithms to extract height and surface normal information, adding the third dimension (depth) to the fingerprint data while using only a standard camera setup
Solution Approach 2:
The patent changes the illumination parameters (light source positions, angles, and intensities) to capture different aspects of the fingerprint surface, extracting additional geometric and photometric features that improve recognition accuracy without requiring expensive specialized hardware
3Measurement precision
If structured lighting systems or multiple cameras are used for 3D fingerprint recognition, then 3D surface reconstruction capability is improved, but device complexity and cost increase
Solution Approach 1:
The patent makes a standard camera multi-functional by combining it with controllable LED light sources that can be positioned at different angles, allowing the same hardware setup to perform both 2D imaging and 3D photometric stereo reconstruction without requiring separate specialized devices
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach reduces system costs and improves fingerprint recognition accuracy by utilizing additional features, providing a low-cost alternative to traditional 3D fingerprint recognition systems and enhancing the applicability of biometric identification in various applications.
Implementation Method 1
capturing a plurality of images with different illuminations of an object
Implementation Method 2
reconstructing a 3D surface model of the object based on the captured images
Data Source
AI summary
The present invention discloses a contactless 3D biometric feature identification system and the method thereof. The system comprises of a fixed-viewpoint image capturing means, a lighting module capable of producing different illuminations on the object of interest and a microprocessor configured to execute a biometric identification algorithm. The algorithm starts with capturing a plurality of images with different illuminations. The captured images are then utilized to reconstruct a three dimensional surface model. Different features, for instance 2D and 3D coordinates and orientations of the biometric feature, surface curvature of the object and the local surface orientation of the object, are extracted from the captured images and the reconstructed 3D surface model. Different matching scores are also developed based on the aforesaid features to establish the identity of the biometric features.