Face Recognition Gaze Alignment for Non-Cooperative Users
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Face recognition technology in interactive terminals, such as public-space touch-interactive information terminals, suffers from poor recognition reliability due to factors like varying gaze directions and suboptimal lighting conditions, which are difficult to control in non-cooperative user applications.
Innovation Solution
A method and device that influence a user's gaze direction using a screen-based point of interest, capture images at the adopted gaze direction, and perform face recognition using enrolment images classified by the same gaze direction, along with features extraction and location detection to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If control based solutions are used to optimize the image capture environment, then the reliability of face recognition is improved, but the ease of operation deteriorates because the user must cooperate with the image capture process
Solution Approach 1:
The system automatically controls lighting and pose guidance without requiring user awareness or active cooperation. The terminal itself serves the dual purpose of both the interactive display and the face recognition control mechanism, eliminating the need for separate control interfaces.
Solution Approach 2:
The system dynamically adjusts lighting parameters and display content based on detected user presence and gaze direction, automatically optimizing capture conditions without manual intervention. The terminal modifies environmental parameters (lighting, display positioning) in response to sensor feedback.
2Reliability
If mitigation based solutions are used to minimize adverse effects, then the reliability of face recognition is improved, but the device complexity increases due to multiple processing steps
Solution Approach 1:
The face recognition system merges lighting control, pose guidance, and image capture functions into a single integrated terminal device. The display and camera work together as a unified system that simultaneously provides user interface and biometric capture capabilities.
Solution Approach 2:
The terminal serves multiple functions: it is both the interactive display device and the face recognition system. The same hardware components (camera, display, processor) perform both user interaction and biometric verification tasks, reducing overall system complexity.
3Reliability
If the image capture environment is tightly controlled, then the reliability of face recognition is improved, but the adaptability deteriorates because the solution is not suitable for non-cooperative user applications
Solution Approach 1:
The system dynamically adapts its behavior based on the situation. It automatically detects when a user is present and activates face recognition mode, adjusting lighting and display content in real-time. The system can operate in both cooperative and non-cooperative modes depending on user interaction levels.
Solution Approach 2:
The system uses feedback from the camera and sensors to automatically adjust lighting and display settings. By continuously monitoring user presence and gaze direction, the system optimizes capture conditions without requiring explicit user input, making it suitable for both cooperative and non-cooperative applications.
Data Source
AI summary
This invention relates to a method for face recognition and a device for implementing said method, the method comprising the steps of: displaying a point of interest on the screen such that a user adopts a gaze direction with respect to the screen; capturing an image of the user at the adopted gaze direction; and performing a face recognition algorithm on the image of the user, using an Enrollment image classified by said gaze direction.