Face Liveness Detection via Facial and Background Feature Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional facial recognition technologies with face liveness detection require user cooperation, leading to low detection rates as they rely on interactive actions like head shaking and eye blinking, which are not always feasible or effective.
Innovation Solution
A method that involves obtaining a target image, extracting facial feature data and background feature data, and using two recognition models to determine the likelihood of a live face, thereby improving detection accuracy and efficiency without user interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If interactive actions such as head shaking and eye blinking are used for face liveness detection, then the system can distinguish real human beings from photos, but the detection rate is low because it requires user cooperation and correct interactive actions
Solution Approach 1:
The system performs face liveness detection automatically without requiring user cooperation. The detection model analyzes facial images and background information autonomously to determine whether the subject is alive, eliminating the need for users to perform interactive actions like head shaking or eye blinking.
Solution Approach 2:
The system extends detection beyond the facial region by incorporating background information from extended regions around the face. This multi-dimensional approach combines facial features with background context to improve detection accuracy without requiring user interaction.
2Measurement precision
If only facial feature data is used for recognition, then the recognition process is simple, but the accuracy of face liveness detection is insufficient
Solution Approach 1:
The system divides the image processing into distinct segments: extracting facial feature data from the face region and extracting background feature data from extended regions around the face. These segmented features are then combined for comprehensive liveness detection, improving accuracy while maintaining clear processing steps.
Solution Approach 2:
The system merges facial feature data with background feature data to perform comprehensive face liveness detection. By combining multiple feature sources, the system achieves higher detection accuracy without proportionally increasing complexity, as the features are integrated through a unified recognition model.
Data Source
AI summary
A face liveness recognition method includes: obtaining a target image containing a facial image; extracting facial feature data of the facial image in the target image; performing face liveness recognition according to the facial feature data to obtain a first confidence level using a first recognition model, the first confidence level denoting a first probability of recognizing a live face; extracting background feature data from an extended facial image, the extended facial image being obtained by extending a region that covers the facial image; performing face liveness recognition according to the background feature data to obtain a second confidence level using a second recognition model, the second confidence level denoting a second probability of recognizing a live face; and according to the first confidence level and the second confidence level, obtaining a recognition result indicating that the target image is a live facial image.