Dual-Camera Iris Recognition Using RGB Feature Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current iris recognition systems in electronic devices face challenges with low accuracy and high power consumption due to the narrow capture angle of IR cameras, leading to longer analysis times and user inconvenience from flickering light emitters.
Innovation Solution
The implementation of a dual-camera system, where a RGB camera is used to detect feature points and adjust the capture angle, allowing the IR camera to activate only when the specified conditions are met, reducing power consumption and improving recognition speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If an IR camera device with a narrow capture angle is used to detect iris area, then the accuracy of iris recognition is improved, but the time required to detect the iris area increases significantly
Solution Approach 1:
The patent uses an RGB camera to perform preliminary detection of the user's face and eye region before activating the IR camera. This preliminary action narrows down the search area and provides initial positioning information, so that when the IR camera is activated, it can quickly acquire the iris image without needing to scan the entire field of view, thus reducing detection time while maintaining accuracy
Solution Approach 2:
The patent introduces an RGB camera as an intermediary device between the user and the IR camera. The RGB camera captures face images and extracts feature points (eyes, eyebrows, nose) to determine the position and orientation of the user's face. This intermediary provides guidance information that helps the IR camera quickly locate and capture the iris, resolving the contradiction between narrow capture angle and detection time
2Measurement precision
If an IR camera device is continuously activated to ensure accurate iris recognition, then the recognition accuracy is maintained, but the power consumption of the electronic device increases
Solution Approach 1:
The patent implements periodic activation of the IR camera based on detection results from the RGB camera. Instead of continuous operation, the IR camera is activated only when the RGB camera detects that the user's face and eyes are in the correct position and orientation. This periodic action based on trigger conditions maintains recognition accuracy while significantly reducing power consumption compared to continuous operation
Solution Approach 2:
The system uses the RGB camera's face detection capabilities to automatically determine when conditions are suitable for iris recognition, eliminating the need for continuous IR camera operation. The RGB camera serves the dual purpose of both initial detection and trigger generation for the IR camera, allowing the system to self-regulate power consumption based on actual recognition needs
3Productivity
If the capture angle of the camera is increased to reduce detection time, then the detection speed is improved, but the accuracy of iris area detection decreases
Solution Approach 1:
The patent segments the detection process into two stages: first, the RGB camera captures a wide field of view to locate the user's face and eyes; second, based on the extracted feature points, the system determines the precise position and orientation, and only then activates the IR camera with its narrow capture angle to capture the iris. This segmentation allows the system to combine wide-angle initial detection with narrow-angle precise detection, achieving both speed and accuracy
Data Source
AI summary
A method of operating an iris recognition function, and an electronic device thereof are provided. The electronic device includes a first camera device, a second camera device, and at least one processor operatively connected to the first camera device and the second camera device. The at least one processor is configured to, if an execution of an iris recognition function is requested, obtain a first image associated with a subject, based on the first camera device, and output information about a feature point of the obtained first image on a display, and if the information about the feature point satisfies a specified condition, obtain a second image associated with the subject based on the second camera device, and wherein a display location of the information about the feature point on the display is changed depending on a capture angle between the subject and the first camera device.