Face ID Ranging Sensor Gating for Spoof Resistance and Lower Power
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Facial recognition systems in electronic devices are vulnerable to spoofing by photos or images and consume excessive power due to unnecessary camera activation, leading to inefficiencies and security risks.
Innovation Solution
Integrate a time-of-flight ranging sensor to detect human skin reflectivity and distance, activating the camera only when conditions align with expected use, such as arm's length and appropriate reflectivity, to enhance security and reduce power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the camera is always on and scanning for the user's face, then facial recognition security is improved, but power consumption increases
Solution Approach 1:
The patent applies preliminary action by using the ranging sensor to detect skin reflectivity and distance before activating the camera for facial recognition. This preliminary detection ensures that the camera only activates when a real face is present within the appropriate range, preventing unnecessary power consumption while maintaining security reliability
Solution Approach 2:
The patent introduces an intermediary component - the ranging sensor - that mediates between the always-on condition and camera activation. This intermediary detects skin reflectivity characteristics and distance, providing a filtering mechanism that determines when the camera should activate, thus resolving the contradiction between continuous monitoring and power consumption
2Reliability
If the camera is used for facial recognition, then user identification is achieved, but the system is vulnerable to spoofing by photos or images
Solution Approach 1:
The patent applies local quality by detecting specific local characteristics of human skin - the reflectivity at 940 nm wavelength - that are unique to real skin and not present in photos or images. By focusing on this specific local property rather than general facial features, the system achieves accurate user identification while resisting spoofing attacks
Solution Approach 2:
The patent utilizes the reflectivity characteristic of human skin at 940 nm wavelength as a form of optical signature. Real human skin exhibits a specific reflectivity range at this wavelength due to its biological composition, while photos and images do not. This optical property detection enables the system to distinguish real faces from spoofing attempts
3Use of energy by moving object
If button press or movement detection triggers facial recognition, then power consumption is reduced, but false positives increase leading to unnecessary camera activation
Solution Approach 1:
The patent implements feedback by using the ranging sensor to continuously monitor skin reflectivity and distance, and using this information to control camera activation. The sensor provides feedback about the presence of a real face, creating a closed-loop system that activates the camera only when appropriate conditions are met, thus reducing false positives while maintaining low power consumption
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
Reduces false positives and power consumption by ensuring the camera is activated only when a real face is present, thereby enhancing security and reducing the risk of spoofing.
Implementation Method 1
The ranging sensor determines a reflectivity of a user's face in response to a specific wavelength of light transmitted from the ranging sensor. At 940 nm, human skin has a reflectance factor that is relatively high as compared to other wavelengths of light.
Implementation Method 2
The ranging sensor determines a distance between a user's face and the electronic device
Data Source
AI summary
The present disclosure is directed to a system and method of controlling a facial recognition process by validating preconditions with a ranging sensor. The ranging sensor transmits a ranging signal that is reflected off of a user's face and received back at the ranging sensor. The received ranging signal can be used to determine distance between the user's face and the mobile device or to determine the reflectivity of the user's face. Comparing the distance to a range of distances corresponding to normal operation of the device or normal reflectivities associated with human skin tones can reduce the number of false positive activations of the facial recognition process. Furthermore, a multiple zone ranging sensor can produce a face depth map that can be compared to a stored face depth map or can produce a reflectivity map that can be compared to a stored face reflectivity map to further increase power efficiency and device security.


