Liveness Detection via Multi-Region Screen Reflection Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing liveness detection technologies, such as those described in Patent Literature 1, are limited in their ability to accurately differentiate between living beings and non-living objects due to the lack of flexibility in illumination patterns, leading to potential impersonation issues.
Innovation Solution
A liveness detection apparatus and method that employs a display control unit to display multiple screens with different regions having distinct displays, capturing images with a camera, and analyzing these images to determine if the target is a living being, utilizing varied light patterns to enhance differentiation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single uniform illumination pattern is used for liveness detection, then the device complexity is low, but the measurement precision of liveness detection deteriorates
Solution Approach 1:
The display screen is divided into multiple distinct regions (e.g., first region with white background, second region with black background, third region with grid pattern) that illuminate different portions of the user's face. This segmentation allows the system to capture multiple illumination patterns simultaneously, improving liveness detection accuracy without requiring sequential pattern changes that would increase temporal complexity
Solution Approach 2:
Different regions of the display screen provide different illumination characteristics (brightness, color, pattern) to different regions of the captured image. For example, the first region provides bright illumination for one area while the second region provides dark or contrasting illumination for another area, enabling localized analysis of reflected light properties to distinguish living from non-living objects
2Measurement precision
If multiple screens with different displays are displayed sequentially, then the liveness detection accuracy improves, but the loss of time increases
Solution Approach 1:
Multiple illumination patterns that would traditionally be displayed sequentially are merged into a single display frame showing multiple regions simultaneously. The display control unit outputs one image containing multiple regions (e.g., first region, second region, third region) that are captured together in a single photograph, eliminating the time delay associated with sequential pattern display while maintaining the ability to analyze different illumination responses
Solution Approach 2:
The system transitions from temporal dimension (sequential display of different patterns over time) to spatial dimension (simultaneous display of multiple patterns in different spatial regions). By arranging multiple illumination patterns side-by-side in the display screen, the system achieves diverse illumination data collection without the time penalty of sequential presentation
3Reliability
If the display screen shows uniform content, then the ease of operation is high, but the reliability of liveness detection deteriorates
Solution Approach 1:
The display screen is segmented into multiple functional regions with distinct visual characteristics (solid colors, patterns, textures) that create varied illumination reflections when captured. This segmentation provides reliable liveness detection by ensuring that different portions of the face receive different illumination treatments, making it difficult for impersonators to replicate the complex reflection patterns with photographs or masks
Solution Approach 2:
The multiple regions are designed with asymmetric and non-uniform characteristics (e.g., different colors, patterns, brightness levels) rather than uniform symmetric design. This asymmetry creates unique reflection signatures that are difficult to replicate, thereby improving impersonation prevention reliability while the regions remain clearly distinguishable and easy to process
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 significantly improves the accuracy of distinguishing between living and non-living objects by exploiting differences in reflected light patterns, thereby enhancing security against impersonation.
Implementation Method 1
a display control unit configured to cause a display apparatus to display a first screen including a display in each of a plurality of regions
Implementation Method 2
determining whether or not the target is a living body using a plurality of the captured images
Data Source
AI summary
A liveness detection apparatus (2000) causes a display apparatus (20) to display a plurality of screens (30). At least one of the plurality of screens (30) has a plurality of regions (32). At least two of the plurality of regions (32) include different indications. The liveness detection apparatus (2000) acquires a plurality of captured images (40). The captured image (40) is generated by capturing an image of a target object (50) with a camera (10) while the screen (30) is displayed. The liveness detection apparatus (2000) determines whether or not the target object (50) is a living body by using the plurality of captured images (40).