Finger Vein Authentication via NIR Illumination and Median Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric authentication systems for handheld devices like smartphones and tablets face limitations due to size, cost, and computational capacity when utilizing human vein structures for secure user authentication.
Innovation Solution
An image processing apparatus using near-infrared (NIR) light to capture and fuse images of a finger's intermediate phalange, employing high pass filtering, normalization, and median filtering to extract a clear vein map, which is then processed using a Gabor filter bank for vein structure extraction and authentication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional biometric authentication systems are implemented in handheld devices, then user security is improved, but device size, cost, and computational capacity requirements increase
Solution Approach 1:
The patent extracts and isolates the vein pattern information from the finger image through image processing techniques. By focusing only on the vein structure rather than processing entire high-resolution images, the system reduces computational requirements while maintaining authentication security. The vein patterns are extracted as simplified representations that retain biometric uniqueness.
Solution Approach 2:
The patent creates simplified copies of the vein structure in the form of vein maps and patterns. These vein map representations serve as compressed biometric templates that require minimal storage space and computational resources for comparison, enabling secure authentication in resource-constrained handheld devices.
2Measurement precision
If multiple images are captured and processed to improve vein map quality, then measurement precision is improved, but processing time and computational load increase
Solution Approach 1:
The patent applies preliminary image processing steps such as high-pass filtering and normalization to enhance vein visibility before final vein map extraction. By pre-enhancing the images with optimized filtering parameters, the system reduces the computational burden of subsequent vein detection while improving accuracy.
Solution Approach 2:
The patent optimizes processing parameters such as filter thresholds, normalization ranges, and vein detection sensitivity to achieve high precision with minimal processing steps. By carefully tuning these parameters, the system extracts accurate vein maps from fewer processed images, reducing overall processing time.
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
Enables fast, inexpensive, and effective extraction of finger vein maps for user registration and authentication within the form factor of handheld devices, overcoming exposure challenges and improving vein structure visibility.
Implementation Method 1
Near-infrared (NIR) light (940 nm) illumination is used to penetrate the human tissue, based on the fact that haemoglobin highly absorbs NIR light, whereas surrounding human tissue transmits NIR light.
Data Source
AI summary
An image processing apparatus comprises a set of infra-red (IR) sources surrounding an image capture sensor and a processor operatively coupled to said IR sources and said image capture sensor. The processor being arranged to acquire from the sensor a succession of images, each illuminated with a different combination of the IR sources. The processor is further arranged to combine component images corresponding to the succession of images by selecting a median value for corresponding pixel locations of the component images as a pixel value for the combined image.