Biometric Authentication Device Using Line-of-Sight Synchronization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biometric authentication methods face challenges in preventing unauthorized use, particularly when face authentication is performed after biometric determination, and they often require high processing loads, special equipment, or compromise user convenience.
Innovation Solution
A biometric authentication device that outputs display information about a symbol to be moved on a display device, acquires a face image while the symbol is displayed, detects the line-of-sight position, and performs biometric authentication only when the line-of-sight position coincides with the symbol's position, thereby determining if the subject is a living body and ensuring authentication reliability with a lower processing load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If continuous image processing is performed to detect time change in line of sight, then measurement precision of line-of-sight detection is improved, but device complexity and processing load increase
Solution Approach 1:
The system performs image processing at specific periodic intervals rather than continuously. The controller captures face images at predetermined time intervals and performs line-of-sight detection only at these intervals, reducing processing load while maintaining detection accuracy through periodic measurement cycles.
Solution Approach 2:
The system performs preliminary actions by capturing multiple face images in advance and storing them temporarily. Before performing line-of-sight detection, the system has already acquired and stored the necessary image data, allowing processing to be done at optimal moments rather than requiring continuous processing.
2Reliability
If biometric determination and face authentication are separated into different processes, then reliability of biometric determination is improved, but device complexity increases
Solution Approach 1:
The system merges biometric determination and face authentication into a single integrated process. The controller simultaneously performs line-of-sight detection (biometric determination) and face recognition (authentication) on the same captured face images, eliminating the need for separate processing stages while maintaining reliability through unified evaluation criteria.
3Reliability
If special equipment is used for 3D scanning to detect face irregularities, then reliability of spoofing detection is improved, but ease of operation decreases
Solution Approach 1:
The system uses self-service by utilizing the device's own built-in imaging resources. The controller uses the device's internal camera and display to capture face images and present verification patterns, eliminating the need for external 3D scanning equipment while maintaining spoofing detection capability through software-based line-of-sight analysis.
Data Source
AI summary
The device outputs, to a display device, display information on a symbol which is to be moved and displayed; acquires a face image of a subject which has been captured by an image capturing device at a capturing timing while the display device displays the symbol; detects, from the face image, a line-of-sight position; determines that the subject of the face image is a living body when one or more prescribed conditions including a case in which the line-of-sight position matches a display position of the symbol at the image-capturing timing are all satisfied; and outputs an authentication result indicating success of the authentication when the subject is determined to be a living body and the biometric authentication is successful, and outputs an authentication result indicating failure of the authentication when the subject is determined not to be a living body or when the biometric authentication fails.