Pen State Detection Circuit Using Local Capacitance Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic pens with two electrodes face estimation accuracy issues due to varying relations between inclination angle and detection position caused by three-dimensional shapes, leading to inconsistent performance when one electrode is not in contact with the detection surface.
Innovation Solution
A pen state detection circuit using a capacitance touch sensor with machine learning to estimate the state of an electronic pen based on signal distributions from fewer sensor electrodes, employing local feature values and different computation rules for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If two electrodes are physically separated in an electronic pen, then the pen can be used for position and posture estimation even when the hand is not touching the detection surface, but the estimation accuracy varies depending on the position and posture due to the three-dimensional shapes of the electrodes
Solution Approach 1:
The patent changes the parameter of electrode configuration from two separate electrodes to a single planar electrode. This parameter change eliminates the variability caused by three-dimensional shapes and physical separation, providing consistent estimation accuracy across different pen positions and postures while maintaining the capability to detect hover states
2Loss of information
If all sensor electrodes are used for detection, then complete signal distribution is obtained, but the processing load increases
Solution Approach 1:
The patent extracts only the necessary portion of signal distribution data by using a threshold to identify sensor electrodes with significant capacitance changes. This extraction approach maintains the essential information needed for accurate pen state detection while reducing the number of electrodes that require processing, thereby lowering the computational load
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
Enhances estimation accuracy of the electronic pen's position and inclination angle by reducing processing load and offset errors through machine learning, facilitating precise detection patterns.
Implementation Method 1
a capacitance touch sensor including a plurality of sensor electrodes arranged in a plane shape
Data Source
AI summary
Provided are a pen state detection circuit, a pen state detection system, and a pen state detection method that can improve estimation accuracy for a pen state in an electronic pen including at least one electrode. A pen state detection circuit acquires, from a touch sensor, a first signal distribution indicating a change in capacitance associated with approach of a first electrode and uses a machine learning estimator to estimate an instruction position or an inclination angle of an electronic pen from first feature values related to the first signal distribution. The first feature values include first local feature values related to a first local distribution corresponding to sensor electrodes in a number fewer than the number of arranged sensor electrodes exhibiting the first signal distribution.