Face Recognition Eligibility Filtering via Depth Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Face recognition systems are vulnerable to being cracked using pictures or videos, which can compromise personal information security.
Innovation Solution
An auxiliary filtering device and method for electronic devices that utilize face recognition, which includes a first camera, a second camera, and a processor. The device performs an additional filtering procedure to determine if the face is an eligible object by calculating face positions and sizes, and comparing them with predetermined size ranges corresponding to specific distances or positions, thereby excluding ineligible objects such as photos or videos.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If face recognition is used for electronic security lock, then identity recognition capability is improved, but vulnerability to picture/video cracking increases
Solution Approach 1:
The patent applies preliminary action by performing depth map analysis and face position verification before the final identity recognition decision. The system calculates expected face positions based on camera parameters and compares them with actual detected face positions to verify eligibility before proceeding with security authentication, thereby preventing picture/video cracking attacks in advance
Solution Approach 2:
The patent introduces depth maps as an intermediary element between the captured image and the identity recognition process. By generating and analyzing depth maps to determine face eligibility (real face vs. picture/video), the system creates an additional verification layer that mediates between the input image and the security decision, effectively blocking cracking attacks
2Reliability
If multiple bio-recognition methods are incorporated to improve protection, then security protection is improved, but product cost increases
Solution Approach 1:
The patent applies multi-functionality by enabling a single camera system to perform multiple functions: capturing images for face recognition, generating depth maps for eligibility verification, and calculating face positions for authentication. This unified approach provides enhanced security through depth analysis without requiring additional biometric sensors or significantly increasing device complexity
Solution Approach 2:
The patent changes the parameter analysis approach by utilizing depth information and spatial position parameters from the captured image. By analyzing face position coordinates, distance from camera, and depth map characteristics, the system enhances security verification capabilities using existing hardware parameters rather than adding new biometric recognition methods
Data Source
AI summary
An electronic device for face recognition is provided. The electronic device is used to exclude an ineligible object to be identified according to the relative relationship between object distances and image sizes, the image variation with time and/or the feature difference between images captured by different cameras to prevent the possibility of cracking the face recognition by using a photo or a video.