Unlock instant, AI-driven research and patent intelligence for your innovation.

A Touch Angle Estimation Method Based on Capacitance Detection and Machine Learning

A technology of machine learning and angle estimation, which is applied in neural learning methods, instruments, calculations, etc., can solve the problems of high cost and low accuracy of touch angle, and achieve the effect of low cost

Active Publication Date: 2021-01-01
BEIHANG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the methods for detecting the touch angle in the prior art, the accuracy of the touch angle is not high, and hardware support is required in the detection process, and the cost is relatively high. Therefore, there is an urgent need for a low-cost touch angle detection that does not require special hardware support. method

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Touch Angle Estimation Method Based on Capacitance Detection and Machine Learning
  • A Touch Angle Estimation Method Based on Capacitance Detection and Machine Learning
  • A Touch Angle Estimation Method Based on Capacitance Detection and Machine Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] Embodiment 1 A touch angle estimation method based on capacitance detection and machine learning

[0023] like figure 1 Shown is a touch angle estimation method based on capacitive detection and machine learning, including the following steps:

[0024] 1. Use a capacitive touch screen with an electrode array of 2*2 to collect data, fix the gyroscope on the finger model used for touch, randomly select an angle in the angle range of 15-90° to touch, and record the finger touch area under different angles And the relative capacitance value of the covered area under the projection of the finger, and record the current touch angle value at the same time, and obtain the data set corresponding to the relative capacitance value-touch angle value;

[0025] In this embodiment, the angle is selected in the vertical direction relative to the capacitive touch screen, wherein the gyroscope is used to detect the touch angle of the finger model, and each sample in the data set is a fi...

Embodiment 2

[0034] Embodiment 2 A touch angle estimation method based on capacitance detection and machine learning

[0035] A method for estimating a touch angle based on capacitance detection and machine learning, comprising the following steps:

[0036] 1. Use a capacitive touch screen with an electrode array of 5*5 to collect data, fix the gyroscope on the finger model used for touch, randomly select an angle in the angle range of 15-90° to touch, and record the finger touch area under different angles And the relative capacitance value of the covered area under the projection of the finger, and record the current touch angle value at the same time, and obtain the data set corresponding to the relative capacitance value-touch angle value;

[0037] In this embodiment, the angle is selected in the vertical direction relative to the capacitive touch screen, wherein the gyroscope is used to detect the touch angle of the finger model, and each sample in the data set is a 26-dimensional vec...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of touch angle detection and discloses a touch angle estimation method based on capacitance detection and machine learning. The method comprises the following steps: 1, acquiring data by using a capacitive touch screen with an electrode array of N * N, wherein N is an integer greater than or equal to 2, fixing a gyroscope on a finger model used for touch, randomly selecting an angle within an angle range of 15-90 degrees for touch, and obtaining a data set corresponding to a relative capacitance value-touch angle value of a finger touch area and a coverage area under finger projection; 2, training a neural network regression model by using the data set and a small-batch stochastic gradient descent method; and 3, by utilizing the trained neural network regression model, taking a relative capacitance value of the electrode array obtained during touch as an input, so as to obtain a touch angle output value. The method is used for estimating thetouch angle of the capacitive touch screen, the touch angle can be judged by detecting the change of the relative capacitance value, and the cost is low.

Description

technical field [0001] The invention belongs to the field of touch angle detection technology, in particular to a touch angle estimation method based on capacitance detection and machine learning. Background technique [0002] In recent years, as a very convenient input device for human-computer interaction, the touch screen has been widely used in many fields such as cameras and mobile phones. The accuracy requirement is also getting higher and higher. If the touch angle of the finger can be measured in real time, it can be used to realize some special gesture operations, such as changing the touch angle by the finger to realize operations such as photo rotation or zooming in. The touch angle provides human-computer interaction. Therefore, the detection of touch angle has attracted extensive attention. In the methods for detecting the touch angle in the prior art, the accuracy of the touch angle is not high, and hardware support is required in the detection process, and th...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F3/044G06F3/041G06N3/08
CPCG06F3/0416G06F3/044G06N3/084
Inventor 高硕黄安彪郭嵘邵明启徐立军
Owner BEIHANG UNIV