Eye Sight Recognition for Device Wake-Up
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for waking up intelligent devices are cumbersome or prone to mis-unlocking, particularly when using manual operations, portrait identification, or iris identification.
Innovation Solution
A method and apparatus that acquire an environment image, recognize a face region, extract facial landmarks to obtain left and right eye images, and classify eye sight to determine if the user is looking at the device, thereby waking it up accurately and conveniently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual operations or portrait identification are used to wake up devices, then ease of operation is improved, but reliability deteriorates due to mis-unlocking
Solution Approach 1:
The patent segments the face recognition process into multiple independent verification stages: face region detection, eye region extraction, iris pattern recognition, and gaze direction analysis. Each stage independently verifies specific features, and all must succeed for device activation. This multi-stage segmentation prevents mis-unlocking by requiring comprehensive verification rather than relying on a single identification method.
2Reliability
If iris identification is used to wake up devices, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent extracts only the necessary iris and eye region features from the captured image, rather than processing the entire face image or requiring full biometric scanning. By isolating and analyzing specifically the iris patterns and eye gaze direction, the system achieves high reliability with reduced computational complexity compared to comprehensive biometric identification systems.
3Measurement precision
If eye sight classification is used to determine user intent, then accuracy of wake-up trigger is improved, but measurement precision requirements increase
Solution Approach 1:
The patent performs preliminary classification of eye sight direction into discrete categories (looking at device, looking away, closing eyes, blinking) before making the wake-up decision. This preliminary categorization simplifies the final determination logic and provides sufficient accuracy for triggering device activation without requiring extremely precise angular measurements, thereby balancing accuracy with measurement feasibility.
Data Source
AI summary
A method and apparatus for waking up a device, an electronic device, and a storage medium are provided, which are related to fields of image processing and deep learning. The method includes: acquiring an environment image of a surrounding environment of a target device in real time, and recognizing a face region of a user in the environment image; acquiring a plurality of facial landmarks in the face region, and acquiring a left eye image and a right eye image according to the facial landmarks; acquiring a left eye sight classification result and a right eye sight classification result according to the left eye image and the right eye image; and waking up the target device in a case of determining that the user is looking at the target device according to the left eye sight classification result and the right eye sight classification result.