Two-Stage Face Recognition for Power Reduction in Portable Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Portable electronic devices consume excessive power when capturing high-resolution images, limiting their usage in power-sensitive situations.
Innovation Solution
A portable electronic device that operates in a suspend and work state, using a low-power always-on image sensor to detect face information in low-resolution images, triggering a higher-resolution camera only when necessary for facial recognition, thereby reducing power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the camera captures high-resolution images continuously, then the image quality is improved, but the power consumption increases
Solution Approach 1:
The patent segments the image capture process into two distinct stages: a first stage using a low-power image sensor for low-resolution monitoring, and a second stage using the high-resolution camera only when face information is detected. This segmentation allows the system to maintain image quality when needed while reducing power consumption during normal operation.
Solution Approach 2:
The patent implements preliminary action by using the image sensor to pre-detect face information in low-resolution images before activating the high-resolution camera. This preliminary detection step filters out non-relevant scenes, ensuring the camera is activated only when necessary, thus reducing overall power consumption while maintaining image quality for actual recognition events.
2Measurement precision
If the camera is activated continuously for face recognition, then the recognition accuracy is improved, but the power consumption increases
Solution Approach 1:
The patent introduces an intermediary component (the image sensor) that acts as a mediator between the environment and the high-resolution camera. This intermediary continuously monitors for face information and only triggers the camera when relevant data is detected, thereby maintaining recognition accuracy while significantly reducing the camera's activation time and power consumption.
Solution Approach 2:
The patent applies partial action by using the low-resolution image sensor for continuous monitoring and only deploying the high-resolution camera partially (intermittently) when face information is detected. This partial deployment of the camera maintains recognition accuracy for actual face capture events while avoiding the excessive power consumption of continuous high-resolution imaging.
3Speed
If the image sensor operates continuously to detect face information, then the response speed is improved, but the power consumption increases
Solution Approach 1:
The patent changes the resolution parameter of the imaging system based on operational requirements. The image sensor operates continuously at low resolution to detect face information, providing fast response speed. When face information is detected, the system switches to high-resolution camera capture. This parameter change allows continuous monitoring with low power consumption while maintaining fast response capability.
Data Source
AI summary
A portable electronic device and an operation method are provided. The portable electronic device includes a body, a screen, a camera, an image sensor and a main system. The image sensor continually captures a first image outside the body with a first resolution and a first power consumption. The camera is turned on in the first state of the portable electronic device by the main system to capture a second image outside the body with a second power consumption and a second resolution only when the face image information appeared for over two seconds on the screen is detected by the image sensor from the first image. The second resolution is higher than the first resolution, and the second power consumption is higher than the first power consumption.