Living Body Detection via Dynamic Light and Sight Line Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing living body detection methods are ineffective against video injection attacks, as they cannot distinguish between a real living body and a forged or replayed video, compromising the accuracy and security of identity authentication systems.
Innovation Solution
A method and apparatus for living body detection that generates a detection interface with a portrait region and a light emission region, where the locations of these regions change randomly, and projects light onto a detection object to analyze the reflected light and track the sight line of the object, determining if the object is a living body based on the matching sequences of light emission and portrait region changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a living body detection solution based on reflection principle is used, then it can detect face features based on light changes, but it is ineffective against video injection attacks
Solution Approach 1:
The patent applies dynamics by making the portrait region and light emission region change positions dynamically during detection. The portrait region moves to different locations and the light emission region changes accordingly, creating a dynamic detection process that cannot be captured by static video playback attacks. This dynamic behavior ensures that the detection sequence generated by a real living body tracking the moving portrait region cannot be replicated by pre-recorded video attacks.
2Object-affected harmful factors
If the portrait region and light emission region locations change randomly, then video injection attacks are resisted, but the detection interface complexity increases
Solution Approach 1:
The patent applies preliminary anti-action by pre-defining the movement relationship between the portrait region and light emission region. The light emission region is positioned relative to the portrait region according to a predetermined rule, and both regions move together in a coordinated manner. This preliminary setup of movement patterns allows the system to resist attacks while maintaining controlled complexity through predictable, rule-based region transitions.
3Measurement precision
If light projection and reflected light analysis are used, then sight line tracking becomes possible, but the detection process becomes more complex
Solution Approach 1:
The patent applies merging by combining multiple detection functions into a unified process. The system simultaneously performs light projection, reflected light analysis, portrait region tracking, and sight line change detection through an integrated detection interface. By merging these functions into a single coordinated process where the portrait region and light emission region work together, the system achieves precise sight line tracking without proportionally increasing overall system complexity.
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 solution effectively resists synthetic face attacks and video injection attacks by utilizing the dynamic changes in reflected light and sight line information, significantly improving the accuracy and security of living body detection and identity authentication.
Implementation Method 1
a mobile phone screen emits different colors of light to illuminate a face
Implementation Method 2
based on the principle of reflection. That is, a mobile phone screen emits different colors of light to illuminate a face, then face features are analyzed based on changes in face pictures before and after a light-changing point
Data Source
AI summary
A method of living body detection includes generating a detection interface in response to a receipt of a living body detection request for a verification of a detection object. The detection interface includes a first region with a viewing target for the detection object to track, a position of the first region in the detection interface changes during a detection time according to a first sequence of a position change of the first region. The method also includes receiving a video stream that is captured during the detection time, determining a second sequence of a sight line change of the detection object based on the video stream, and determining that the detection object is a living body at least partially based on the second sequence of the sight line change of the detection object matching the first sequence of the position change of the first region.