Hand Recognition Using Smartphone Posture and Acceleration Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current hand recognition processes in portable terminals, such as smartphones, face challenges in accurately distinguishing between left and right hands due to variations in hand shapes and postures, leading to reduced recognition accuracy and increased processing time.
Innovation Solution
A recognition apparatus and method that utilizes an optical sensor to perform hand recognition by determining the posture of the smartphone relative to gravitational acceleration, allowing for efficient left and right hand decision-making, and employing specific dictionaries for each hand type to improve recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a general hand recognition process is used without considering smartphone posture, then the recognition process is simpler, but the recognition accuracy decreases due to inability to distinguish left and right hands correctly
Solution Approach 1:
The system performs preliminary determination of smartphone posture relative to gravitational acceleration before executing the hand recognition process. By pre-establishing the coordinate system and orientation based on acceleration sensor data, the recognition process can accurately distinguish between left and right hands without requiring complex post-processing or multiple recognition attempts.
Solution Approach 2:
The hand recognition process is segmented into distinct phases: first determining smartphone posture using acceleration sensors, then selecting appropriate recognition algorithms based on the determined orientation, and finally executing the recognition. This segmentation allows each phase to be optimized independently, improving overall accuracy without proportionally increasing complexity.
2Measurement precision
If specific recognition processes are performed for left and right hands based on smartphone posture, then the recognition accuracy is improved, but the processing time increases
Solution Approach 1:
The smartphone posture and coordinate system are determined in advance using acceleration sensor data before the hand recognition process begins. This preliminary action eliminates the need for time-consuming trial-and-error recognition attempts, allowing the system to directly apply the appropriate recognition algorithm for the detected hand orientation.
Solution Approach 2:
The acceleration sensor serves as an intermediary that provides posture information to guide the hand recognition process. By using this intermediate data source, the system can quickly determine the correct recognition approach without performing exhaustive analysis, thus reducing processing time while maintaining high accuracy.
3Measurement precision
If the optical sensor receives light without posture-based processing, then the system operation is simpler, but the recognition accuracy decreases due to variations in hand shapes and postures
Solution Approach 1:
The system preliminarily determines the smartphone's spatial orientation relative to gravitational acceleration before processing optical sensor data for hand recognition. This preliminary step establishes the correct coordinate transformation and recognition parameters, enabling accurate distinction between left and right hands despite variations in hand shapes and user postures.
Solution Approach 2:
The system dynamically changes recognition parameters based on the determined smartphone posture. By adjusting the coordinate system and recognition thresholds according to the device's orientation in space, the system maintains high recognition accuracy across different holding positions and hand configurations without requiring complex manual configuration.
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
The solution significantly enhances hand recognition accuracy and reduces processing time by correctly identifying hands based on smartphone posture and using appropriate dictionaries, resulting in an improved user interface.
Implementation Method 1
an optical sensor that receives light, a hand reflected in an image obtained by sensing of the optical sensor
Implementation Method 2
a posture of a portable terminal including an optical sensor that receives light
Data Source
AI summary
There is provided a program, a recognition apparatus, and a recognition method that make it possible to improve a recognition accuracy of a hand recognition process. As a hand recognition process for recognizing, according to a posture of a portable terminal including an optical sensor that receives light, a hand reflected in an image obtained by sensing of the optical sensor, a hand recognition process for the left hand or a hand recognition process for the right hand is performed. The present technology can be applied to a case in which a hand is recognized.