3D Face Recognition via Single Camera Sweep
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Two-dimensional image-based face recognition is prone to errors due to variations in lighting, pose, expression, and aging, and is vulnerable to deception, while three-dimensional face recognition is computationally expensive for mobile devices and often requires stereoscopic image-capture devices that are not commonly found on mobile devices.
Innovation Solution
A mobile device generates a three-dimensional model of a user's face by capturing and processing a set of two-dimensional images from various orientations using an image sensor and a motion sensor, such as a gyroscope, to determine orientation information and detect facial features, allowing for secure identification and authentication without the need for multiple cameras or complex computations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If three-dimensional image-based face recognition is implemented using stereoscopic image-capture devices with multiple cameras, then measurement precision and reliability are improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent transforms a 2D image-based recognition problem into a 3D recognition problem by capturing images at multiple orientations and reconstructing a three-dimensional model of the face. This dimensional transformation allows the system to achieve the security and accuracy of 3D recognition while using a single camera, avoiding the need for complex stereoscopic devices.
Solution Approach 2:
The system changes the parameter of image orientation by capturing images from multiple different angles and orientations. By varying the orientation parameter and combining these images with orientation information, the system reconstructs a 3D model, achieving high measurement precision without requiring multiple cameras simultaneously.
2Reliability
If three-dimensional image-based face recognition is implemented, then reliability and security are improved, but computational cost and processing complexity increase
Solution Approach 1:
The system performs preliminary actions by capturing multiple images at different orientations during a registration phase and pre-processing them to extract features and construct a 3D model. This preliminary processing allows the actual authentication to be faster and less computationally intensive, as the complex 3D reconstruction work has already been done in advance.
Solution Approach 2:
The patent creates a three-dimensional model as a copy or representation of the actual face. This model can be stored and compared during authentication without requiring real-time complex computations on the original images. The system compares the live capture against the pre-created 3D model, significantly reducing computational energy consumption during authentication.
3Measurement precision
If multiple images are captured from various orientations, then measurement precision and three-dimensional model quality are improved, but loss of time and number of captured images increase
Solution Approach 1:
The system uses periodic action by capturing images at regularly spaced orientations as the user rotates their head or the device moves through a series of predetermined angular positions. This periodic capture pattern ensures comprehensive coverage of the face from multiple angles while maintaining a systematic and time-efficient capture sequence, reducing total capture time compared to random or manual positioning.
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 approach provides a secure and efficient method for user identification and authentication on mobile devices, reducing errors associated with 2D face recognition and overcoming the computational limitations of 3D recognition, while being cost-effective and widely applicable.
Implementation Method 1
uses an image-capture device to capture a set of images of a person's face from various orientations as the person or any another user sweeps the mobile device across the person's face. The device determines orientation information for the captured images, and detects a plurality of features of the person's face from the captured images
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A mobile device can generate a three-dimensional model of a person' s face by capturing and processing a plurality of two-dimensional images. During operation, the mobile device uses an image- capture device to capture a set of images of the person from various orientations as the person or any other user sweeps the mobile device in front of the person's face from one side of his/her face to the opposing side. The device determines orientation information for the captured images, and detects a plurality of features of the person's face from the captured images. The device then generates a three- dimensional model of the person's face from the detected features and their orientation information. The three-dimensional model of the person's face facilitates identifying and/or authenticating the person's identity.