Liveness Detection via Dynamic Facial Feature Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current biometric systems that verify identity through facial images struggle to differentiate between a living face and a photograph, allowing fraudsters to deceive the system by presenting a photo instead of their own face.
Innovation Solution
A method and device that capture a sequence of facial images, detect features, measure liveness indicators such as eye blinking, face proportions, and gaze direction, and determine if a combination of these indicators is present to verify if the face is living, using parameter scores and thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a photo is used for identity verification, then the verification process is simple and fast, but fraudsters can deceive the system by presenting a photo instead of their own face
Solution Approach 1:
The system captures a sequence of facial images over time and analyzes dynamic changes in facial features such as eye blinking, mouth movement, and facial expressions. This dynamic analysis transforms the static photo verification into a dynamic process that can detect living faces while maintaining fast verification speed through automated temporal analysis.
Solution Approach 2:
The system measures multiple parameters including eye blinking frequency, mouth opening extent, gaze direction changes, and facial proportion variations. By monitoring changes in these parameters across a sequence of images, the system can distinguish between living faces and static photos, resolving the contradiction between simple verification and fraud prevention.
2Reliability
If multiple liveness indicators are measured to improve detection accuracy, then the reliability of living face detection increases, but the device complexity and processing time increase
Solution Approach 1:
The detection system is divided into multiple independent modules, each responsible for detecting specific liveness indicators such as eye blinking detection, mouth movement detection, gaze direction analysis, and facial proportion measurement. This segmentation allows the complex detection task to be broken down into manageable components that can be processed independently and efficiently.
Solution Approach 2:
A single facial image sequence is used to extract multiple liveness indicators simultaneously. The same input data (sequence of facial images) serves multiple detection purposes including eye blinking, mouth movement, gaze direction, and facial proportion analysis, reducing the need for separate sensing mechanisms and simplifying the overall system architecture.
3Reliability
If multiple liveness indicators are measured to improve detection accuracy, then the reliability of living face detection increases, but the processing time increases
Solution Approach 1:
The system processes facial images continuously as a sequence rather than analyzing each indicator separately after complete data collection. By performing multiple indicator measurements on the same continuous image sequence simultaneously, the system avoids repeated capture and processing cycles, maintaining high detection accuracy while minimizing processing time through efficient parallel analysis.
Data Source
AI summary
The present disclosure concerns a method of verifying the presence of a living face in front of a camera (112), the method including: capturing by said camera a sequence of images of a face; detecting a plurality of features of said face in each of said images; measuring parameters associated with said detected features to determine whether each of a plurality of liveness indicators is present in said images; determining whether or not said face is a living face based on the presence in said images of a combination of at least two of said liveness indicators.