Wearable Hand Authentication with Shoulder Position Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wearable devices struggle to distinguish between the hands of a genuine user and those of others, leading to potential inadvertent or intended manipulation by third parties, and lack effective methods to notify users about the presence of their hands within the detection area.
Innovation Solution
A wearable device equipped with sensors recognizes hands in a detection area, estimates the position of connected body parts like shoulders, and determines the authenticity of the hand based on probability distributions, allowing it to differentiate between genuine and non-genuine users, and provides notification through visual, audible, or vibration signals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the wearable device uses hand detection to enable user interaction, then the ease of operation is improved, but the reliability deteriorates due to inability to distinguish genuine user from third party
Solution Approach 1:
The patent extends hand detection from two-dimensional image recognition to three-dimensional spatial verification by detecting shoulder position and calculating distance. This additional dimensional verification ensures that only hands belonging to the genuine user (within a predetermined distance) can trigger device functions, thereby improving reliability while maintaining ease of operation.
Solution Approach 2:
The patent introduces shoulder position detection as an intermediary verification step between hand detection and gesture recognition. By first determining whether a shoulder exists at the estimated position and verifying the distance, the system creates a reliable intermediary layer that prevents third-party manipulation while allowing genuine user interaction to proceed smoothly.
2Reliability
If the wearable device continuously monitors hand presence in detection area, then the reliability is improved, but the use of energy deteriorates
Solution Approach 1:
The patent implements periodic hand detection cycles rather than continuous monitoring. The sensor detects hands at predetermined time intervals, and the processor performs shoulder position estimation and distance verification only when hands are detected in the detection area. This periodic action maintains reliable user authentication while significantly reducing energy consumption compared to continuous monitoring.
Solution Approach 2:
The patent performs preliminary hand detection in the detection area before executing the more computationally intensive shoulder position estimation and distance verification. This preliminary action filters out false positives early, ensuring that energy-intensive verification operations are only performed when necessary, thus balancing reliability with energy efficiency.
3Reliability
If the wearable device adds shoulder position estimation and probability verification, then the reliability is improved, but the device complexity deteriorates
Solution Approach 1:
The patent leverages the existing sensor system (camera or depth sensor) to serve multiple functions: initial hand detection, shoulder position estimation, and distance verification. By making the sensor system multi-functional, the patent improves reliability through comprehensive verification without proportionally increasing device complexity, as the same hardware components perform multiple verification tasks.
Solution Approach 2:
The processor uses the output from the sensor system to automatically perform shoulder position estimation and distance calculation without requiring additional specialized hardware. The system serves itself by utilizing the existing computational resources and sensor data to complete the verification process, thereby improving reliability while minimizing the increase in device complexity.
Data Source
AI summary
Provided is a method of identifying a hand of a genuine user wearing a wearable device. According to an embodiment, the method includes using a sensor included in the wearable device to recognize a hand located in a detection area of the sensor; estimating a position of a shoulder connected to the recognized hand based on a positional relation between the orientation of the recognized hand and at least one body part connected to the recognized hand; and using information about a probability of a shoulder of the genuine user being present in the estimated position to determine whether the recognized hand is a hand of the genuine user.