Biometric Verification Using Non-Visible Light Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional identity verification methods, such as key-based and biometric systems, face challenges in ensuring secure access control due to issues like key duplication, environmental limitations, and high false acceptance/false rejection rates, particularly in varying light conditions and large populations.
Innovation Solution
A system utilizing an edge capture device that emits non-visible light, detects reflected and radiated light, and generates a biometric template by calculating weighted values and ranking distances to enhance facial recognition accuracy, reducing dependency on visible light and improving security through subdermal feature analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional biometric sensors are used for facial recognition, then access control can be implemented, but the system performance is compromised in direct sunlight due to glares, shadows, and other artifacts
Solution Approach 1:
The patent changes the wavelength parameter of light from visible spectrum to infrared spectrum. The infrared illumination source emits light at wavelengths invisible to the human eye, and the infrared sensor detects reflected infrared light from facial features. This parameter change allows the system to operate independently of visible ambient lighting conditions, eliminating the harmful effects of sunlight, glares, and shadows that plague traditional visible-light biometric sensors.
2Measurement precision
If mega-pixel camera technology is used to capture facial features, then resolution is improved, but features are still obscured by ambient lighting, face position changes, background, and camera angles
Solution Approach 1:
The patent introduces infrared light as an intermediary medium between the illumination source and the facial features. The infrared illumination source emits infrared light that reflects off the facial features, and the infrared sensor detects this reflected light. This intermediary infrared light pathway bypasses the harmful effects of visible ambient lighting, face position changes, background interference, and camera angle variations that obscure features in traditional visible-light systems.
3Reliability
If traditional biometric sensors operate in visible light, then facial features can be captured, but the system has increased false acceptance and false recognition rates due to light shadowing and intensity changes
Solution Approach 1:
The patent changes the operational wavelength parameter from visible light to infrared light. This parameter change fundamentally alters how light interacts with facial features - infrared light penetrates skin differently and is less affected by surface variations, shadows, and intensity changes. The infrared sensor detects reflected infrared light patterns that remain consistent regardless of visible lighting conditions, thereby reducing false acceptance and false recognition rates while improving both reliability and measurement precision.
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 system provides robust and secure keyless access control by minimizing environmental impact on facial recognition, reducing false positives/negatives, and increasing the difficulty of duplicating biometric templates, thus enhancing identity verification and authentication.
Implementation Method 1
detects reflected and radiated light
Implementation Method 2
emits non-visible light, detects reflected and radiated light
Data Source
AI summary
Aspects of the present disclosure include methods for generating a sampled profile including a plurality of sampling points having a plurality of characteristic values associated with the detected non-visible light, identifying one or more macroblocks each includes a subset of the plurality of sampling points, calculating a number of occurrences of the local pattern value within each subset of the plurality of the sampling points for each of the one or more macroblocks, generating a first array including a plurality of weighted values by calculating the plurality of weighted values based on the numbers of occurrences of the local pattern value and corresponding sizes of the one or more macroblocks, assigning a unique index to each of the plurality of weighted values, generating a second array of the unique index by ranking the plurality of weighted values, and generating a third array including a plurality of ranking distances.