Neural Network Liveness Test Model for Face Anti-Spoofing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing face anti-spoofing technologies rely on manual feature extraction methods, which are resource-intensive and less accurate, making them inefficient in real-time authentication and prone to erroneous authentication due to high processing demands and lower pixel resolutions.
Innovation Solution
A neural network-based liveness test method that extracts interest regions from input images, using texture and spatial information to determine liveness, with a recurrent connection structure for temporal consideration, allowing for efficient and accurate authentication by reducing processing resources and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If manual feature extraction methods are used for face anti-spoofing, then the system can be implemented with simpler architecture, but the processing resource consumption increases and accuracy decreases
Solution Approach 1:
The patent replaces manual feature extraction methods with a neural network-based automated extraction system. The neural network model automatically learns and extracts relevant facial features and texture patterns from input images, eliminating the need for hand-crafted feature engineers and reducing computational complexity while improving accuracy.
2Device complexity
If manual feature extraction methods are used, then the system implementation is simpler, but processing time increases and real-time authentication becomes difficult
Solution Approach 1:
The patent substitutes manual feature extraction with a trained neural network model that can rapidly process images and extract features in real-time. The model has been pre-trained on extensive datasets to efficiently identify authentic faces versus spoofs, enabling fast authentication decisions without manual intervention.
3Use of energy by moving object
If manual feature extraction is used, then the system requires less computational power for training, but the pixel resolution and detection precision deteriorate
Solution Approach 1:
The patent replaces manual feature extraction with a neural network that processes high-resolution images directly. The model maintains and enhances pixel resolution throughout the processing pipeline, using convolutional layers to preserve fine-grained texture details that are crucial for distinguishing authentic faces from spoofs, while the automated system efficiently handles the computational load.
Data Source
AI summary
A liveness test method and apparatus is disclosed. A processor implemented liveness test method includes extracting an interest region of an object from a portion of the object in an input image, performing a liveness test on the object using a neural network model-based liveness test model, the liveness test model using image information of the interest region as provided first input image information to the liveness test model and determining liveness based at least on extracted texture information from the information of the interest region by the liveness test model, and indicating a result of the liveness test.