Capacitive Touch Classification for Continuous Press-State Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing capacitive touchscreen technologies struggle to accurately classify and predict the state of touch, such as normal touch versus heavy press, without requiring additional hardware, and fail to handle transitions between these states during continuous touch gestures.
Innovation Solution
A method using a machine learning model, specifically a convolutional neural network and recurrent neural network, processes a sequence of capacitive images to continuously classify the state of touch, including techniques for handling partial finger touches and calibrating decision boundaries based on user input.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional capacitive sensing is used, then touch location detection is achieved, but touch state classification (normal touch vs heavy press) cannot be accurately determined
Solution Approach 1:
The patent replaces mechanical pressure sensing hardware with software-based machine learning classification. The system uses a capacitive touchscreen's existing sensor data, processed through a neural network model, to infer touch state (normal touch vs heavy press) without requiring additional pressure-sensitive hardware layers.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between the capacitive sensor and the touch state determination. This intermediary processes raw capacitive images and temporal sequences to classify touch states, enabling accurate measurement without direct mechanical pressure detection.
2Measurement precision
If additional hardware is added to measure pressure and force, then touch state classification accuracy is improved, but device complexity increases
Solution Approach 1:
The patent enables the existing capacitive touchscreen to classify touch states using its own sensor data and integrated machine learning model, without requiring external pressure sensing hardware. The system serves itself by leveraging its inherent capacitive sensing capabilities for multi-dimensional touch analysis.
3Adaptability or versatility
If touch state classification is performed continuously during gestures, then user interaction dimensionality is increased, but processing time and computational load increase
Solution Approach 1:
The patent performs preliminary actions by pre-processing capacitive images to extract key features and preparing temporal sequences for classification. The machine learning model is trained in advance on diverse touch patterns, enabling rapid inference during actual user interaction without real-time complex computations.
Solution Approach 2:
The patent maintains continuous touch state classification during gestures by processing capacitive images in real-time temporal sequences. The system continuously updates touch state predictions as users interact, enabling dynamic response to gesture transitions without significant processing delays.
4Adaptability or versatility
If partial finger readings are used when finger lands outside touchscreen, then edge case handling is improved, but measurement accuracy decreases
Solution Approach 1:
The patent uses the machine learning model as an intermediary to handle partial finger readings. The model processes incomplete capacitive images from edge touches and infers the complete touch state by comparing against learned patterns from complete finger touches, bridging the gap between partial and complete measurements.
Solution Approach 2:
The patent employs feedback mechanisms where the system compares partial finger readings against stored patterns of complete finger touches. The machine learning model uses this feedback to adjust and refine its classification, improving accuracy even when only portions of the finger contact the touchscreen.
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
Enables continuous prediction of touch states like normal touch and heavy press, even during transitions, without additional hardware, enhancing user interaction capabilities on capacitive interfaces.
Implementation Method 1
When an input device (e.g., a user's finger, conductive stylus, etc.) touches or is brought near the surface of a capacitive touchscreen, the local electrostatic field is distorted. The resultant change in capacitance can be measured and used to detect the touch input and determine its location on the touchscreen.
Implementation Method 2
When an input device (e.g., a user's finger, conductive stylus, etc.) touches or is brought near the surface of a capacitive touchscreen, the local electrostatic field is distorted.
Data Source
AI summary
Embodiments of the present application provide methods for classifying a detected touch input on a capacitive interface. A sequence of capacitive images representing capacitive sensor data associated with touch inputs detected during a continuous touch gesture is obtained. The capacitive images are sequentially processed using a machine learning model. A touch region of the capacitive image that corresponds to an area of the capacitive interface associated with a current touch input for the capacitive image is identified. A set of features of the identified touch region is extracted using the machine learning model. A state of touch of the capacitive image is determined based on the extracted set of features and one or more previous capacitive images associated with previously detected touch inputs during the continuous touch gesture.