Dual-Camera Face Recognition Using Infrared Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing two-dimensional face recognition systems using a single camera suffer from poor recognition performance due to factors like ambient light, capturing angles, and facial expressions, which are exacerbated by the complexity and expense of three-dimensional face recognition systems.
Innovation Solution
A dual-camera face recognition system that captures complementary face images using one camera in black and white and another in color, with infrared filters to enhance light adaptability and improve recognition performance by computing the sum of similarities between candidate objects from both images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single camera is used for two-dimensional face recognition, then the device complexity is low, but the recognition performance is poor due to ambient light, capturing angles, and facial expressions
Solution Approach 1:
The face recognition system is segmented into two independent camera subsystems: a first camera for capturing color face images and a second camera for capturing black and white face images. Each camera independently processes recognition, and their results are combined through a voting mechanism. This segmentation allows each subsystem to specialize in different lighting conditions while maintaining overall system simplicity.
Solution Approach 2:
The system merges the recognition results from two independent camera channels by computing a voting score that combines similarity measurements from both color and black and white images. This combining approach leverages the complementary strengths of each camera type to improve overall recognition reliability without significantly increasing system complexity.
2Reliability
If three-dimensional face recognition is used, then the recognition performance is improved, but the device complexity and cost increase due to complex capturing systems and face reconstruction algorithms
Solution Approach 1:
Instead of using complex three-dimensional reconstruction systems, the patent creates a virtual two-dimensional composite image that combines the strengths of both color and black and white images. This virtual copy compensates for the limitations of single-image recognition without requiring actual three-dimensional hardware or algorithms, thereby maintaining system simplicity while improving recognition performance.
3Adaptability or versatility
If infrared transmission filters are used in the first camera, then light adaptability is improved, but the color information is lost resulting in black and white images
Solution Approach 1:
The system segments the image capture function into two specialized cameras: one with infrared transmission filters that captures black and white images with superior light adaptability, and another without such filters that captures color images. This segmentation ensures that each camera is optimized for its specific function, with the first camera excelling in various lighting conditions and the second camera preserving color information.
Solution Approach 2:
Different parts of the imaging system have different qualities optimized for their specific purposes. The first camera is equipped with infrared transmission filters and optimized for grayscale imaging with enhanced light adaptability, while the second camera maintains full color capability. Each camera's local quality is tailored to its specific role in the overall recognition system.
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
Significantly improves recognition performance and user experience by employing dual cameras with infrared lighting and filters to enhance light adaptability and reduce the impact of ambient conditions, while maintaining cost-effectiveness.
Implementation Method 1
an infrared transmission filter, arranged in front of the first camera, for filtering out visible lights such that a black and white face image is captured by the first camera
Implementation Method 2
an infrared cut filter, arranged in front of the to second camera, for filtering out infrared lights such that a color face image is captured by the second camera
Data Source
AI summary
A dual-camera face recognition device and method are disclosed. The device includes: a first camera, for capturing a face image; a second camera, arranged at a different position from the first camera, for capturing a face image; a face recognition processing unit, for receiving and recognizing the face image captured by the first camera and obtaining a first candidate set, and for receiving and recognizing the face image captured by the second camera and obtaining a second candidate set. The face recognition processing unit is also adapted to select from the first candidate set and the second candidate set a candidate object whose similarity complies with a predetermined rule as a recognition result.