Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Handwriting recognition method and system based on ultrasonic waves, mobile terminal and server

A handwriting recognition and ultrasonic technology, applied in the field of handwriting recognition, can solve the problems of passive perception and difficult segmentation of long sequences, achieve good word segmentation ability and improve the effect of robustness

Pending Publication Date: 2022-03-01
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the shortcomings of the prior art described above, the purpose of this application is to provide an ultrasonic-based handwriting recognition method, system, mobile terminal and server to solve the problems of handwriting recognition in the prior art, such as long sequences that are difficult to segment and passive perception Cross-environmental issues faced

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
  • Handwriting recognition method and system based on ultrasonic waves, mobile terminal and server
  • Handwriting recognition method and system based on ultrasonic waves, mobile terminal and server
  • Handwriting recognition method and system based on ultrasonic waves, mobile terminal and server

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0038] In one or more achievable application scenarios, the specific embodiments of the ultrasonic-based handwriting recognition system described in the application can be as follows:

[0039] For example, in a landing application, the handwriting recognition software used by the user is implemented on the mobile terminal 100 in the form of an input method, such as an Android phone or an Apple phone. The source code of the input method used includes the source code of the input method from AOSP (Android OpenSource Project), which is customized for the application scene and does not display the interface such as the keyboard.

[0040] In terms of function realization, first, towards the direction of handwriting action, the pre-generated ultrasonic audio signal is played through the speaker 110 to reduce the amount of computation, and then the reflected ultrasonic audio signal is received through the microphone 120, converted into an audio file, and then uploaded to the server th...

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

According to the handwriting recognition method and system based on the ultrasonic waves, the mobile terminal and the server, the ultrasonic waves and handwriting recognition are combined, a new input mode is provided, and through the CTC loss and LSTM combined machine learning technology, the system achieves real-time recognition of handwriting input; the ultrasonic wave carried by the self-correlation sequence is adopted, so that the robustness aiming at environmental change is improved, and relatively high letter recognition accuracy is achieved in a cross-environment experiment; according to the method, a machine learning model has good segmentation capability on intervals among words, continuous handwriting input recognition can be supported, the problem that long sequence input is difficult to segment in practical application is solved, the cross-environment problem faced by passive perception is partially solved, and the huge potential of ultrasonic passive recognition in the commercial field is shown.

Description

technical field [0001] This application relates to the technical field of handwriting recognition, in particular to an ultrasonic-based handwriting recognition method, system, mobile terminal and server. Background technique [0002] Passive sensing system is a system that uses wireless signals generated by widely distributed wireless sensors in daily life to perceive human behavior. At present, the commercial speakers and microphones of intelligent electronic products have the ability to send and receive ultrasonic waves, and the use of ultrasonic waves to build passive perception systems can expand the ability of human-computer interaction. Compared with computer vision-based perception methods, passive perception has less risk of user privacy, and has a great advantage in energy consumption, which has important application value. Handwriting recognition based on ultrasound is more in line with people's daily behavior habits than keyboard or touch screen input, and it is ...

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 Applications(China)
IPC IPC(8): G06K9/00G06F3/04883G06N3/04G06N3/08
CPCG06F3/04883G06N3/08G06N3/044G06N3/045G06F2218/08G06F2218/12
Inventor 金雪怡王东
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com