Multimodal Biometric Feature Extraction for Accurate Finger Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biometric systems, such as fingerprint and finger vein identification, face challenges in accuracy and convenience due to environmental sensitivity, permanence issues, and high manufacturing costs, often relying on single biological features for identification.
Innovation Solution
An electronic device and method that integrates and simultaneously uses multiple biological features, such as fingerprint and finger vein, for improved biometric verification through an NIR optical principle, employing algorithms like particle swarm optimization and asymmetric encryption to enhance accuracy and convenience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple biological features are integrated for identification, then identification accuracy is improved, but device complexity increases
Solution Approach 1:
The patent combines multiple biological feature acquisition capabilities (fingerprint and finger vein) into a single integrated device. The imaging unit can capture both fingerprint images and finger vein images, merging what would traditionally require separate devices into one unified system, thereby improving identification accuracy without proportionally increasing device complexity
Solution Approach 2:
The imaging unit is designed with multi-functionality to acquire different types of biological features (fingerprint and finger vein) using the same hardware component. This universal design allows a single device to perform multiple identification functions, reducing the need for separate specialized devices and minimizing overall system complexity
2Reliability
If finger vein identification is used, then identification security is improved, but manufacturing cost increases
Solution Approach 1:
The patent merges finger vein identification with fingerprint identification in a single integrated system. By combining these features, the patent leverages the high security of finger vein recognition while offsetting the increased manufacturing cost through the addition of relatively low-cost fingerprint sensing capabilities, creating a cost-effective high-security solution
3Ease of operation
If fingerprint identification is used, then ease of operation is improved, but identification security deteriorates due to fraud risk
Solution Approach 1:
The patent segments the identification process into two independent verification stages: fingerprint verification and finger vein verification. This segmentation allows the system to maintain the ease of fingerprint operation while adding a second layer of security through finger vein verification, thereby reducing fraud risk without significantly impacting user convenience
Solution Approach 2:
The patent implements preliminary fingerprint verification before proceeding to finger vein verification. This preliminary action allows the system to quickly filter out obvious mismatches using the easy-to-operate fingerprint scan, and only require the more secure but potentially more complex finger vein verification when needed, thereby maintaining ease of operation for legitimate users while enhancing security
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
The method achieves high accuracy and convenience in biometric verification by optimizing feature extraction and using multi-modal identification, suitable for applications in access control and attendance management, and can be integrated into the Internet of Things for broader business applications.
Implementation Method 1
A principle of finger vein identification is to irradiate a finger with NIR light, so that hemoglobin flowing in veins may absorb the NIR light, and the unabsorbed NIR light may enter a sensor to obtain a clear vein image.
Implementation Method 2
projecting the finger onto a complementary metal oxide semiconductor (CMOS) or a charge coupled device (CCD) by built-in near infrared ray (NIR) irradiation to form an image through absorption
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An electronic device and a method for obtaining features of biometrics are provided. The method includes: obtaining an image including a plurality of biological features; obtaining a plurality of feature points of the biological features in the image; dividing the image into a plurality of sub-images, and obtaining a region in each of the sub-images; and identifying from among a plurality of second feature points in the region in each of the sub-images a plurality of third feature points for performing a biometric operation.