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

A method for intelligent recognition of handwritten input

An intelligent recognition and handwriting input technology, applied in the field of handwriting, can solve problems such as poor real-time handwriting rendering, affecting user interaction experience, and customers signing at will, to simplify business processing processes, improve data validity, and save paper.

Active Publication Date: 2021-07-20
北京爱知之星科技股份有限公司
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, in the process of signing on the digital electromagnetic screen, on the one hand, some customers often sign at will, which is obviously different from the actual name, which seriously affects the subsequent business audit
On the other hand, in the process of handwriting visualization on the digital electromagnetic screen, the real-time rendering effect of handwriting is not good, which seriously affects the user's interactive experience

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 method for intelligent recognition of handwritten input
  • A method for intelligent recognition of handwritten input
  • A method for intelligent recognition of handwritten input

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] In the first embodiment, the handwriting trajectory is directly fitted, rendered and displayed according to the Bezier curve. Specific steps are as follows,

[0054] In order to fit a curve, it is not enough to use a cubic Bezier curve. If a high-order Bezier curve is used for fitting, the amount of calculation is large, and the fitting accuracy is not good. In the handwriting action, the segmentation is fitted with a Bezier curve, which solves this problem well. A certain point of each cubic Bezier curve is used as a double guide point to form a point on two adjacent line segments before and after, and the endpoints of the curve segment coincide with the corresponding endpoints of the preceding and following curve segments. Specific steps are as follows.

[0055] The feature vector p of the signer's handwriting point obtained according to S2 i (X, Y, Z, T), the fitting interpolation formula of the cubic Bezier curve, as shown in formula (1),

[0056]

[0057] Am...

Embodiment 2

[0065] In the second embodiment, the outline is drawn in real time according to the Bezier curve, and then the outline is filled and rendered to obtain the rendered handwriting. Specific steps are as follows,

[0066] Step 1, according to the feature vector p of the signer's handwriting point obtained from S2 i (X, Y, Z, T), the fitting interpolation formula of the cubic Bezier curve, as shown in formula (1). From the same set of handwriting actions α i Select m (m>2) handwriting points in the t+m time period for contour calculation. Specific steps are as follows,

[0067] Step 1.1, for each handwriting point, draw a circumscribed rectangle of the handwriting point, each circumscribing rectangle contains k auxiliary points, such as image 3 As shown, the position of the Bezier curve is determined by k points on each rectangle.

[0068] Step 1.2, draw k Bezier curves for each m handwriting points to form a closed Bezier curve outline, such as image 3 shown. Specific ste...

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 discloses a method for intelligent recognition of handwriting input, which relates to the technical field of handwriting. First, according to the customer name in the business document message, the method needs to obtain the signature information entered by the customer through the digital electromagnetic screen, and then compare the obtained signature information with the real name, if the signed text matches the real name , the signature is passed, otherwise, the word needs to be re-signed until the signature matches the real name, so as to ensure that every word signed by the customer is consistent with its real name, and the system will not recognize the customer due to random signing There is an obvious difference between the signature and the actual name, which seriously affects the follow-up business audit, which greatly improves the data validity of business processing, not only saves a lot of paper, but also plays a role in energy saving and emission reduction, and simplifies It streamlines the business handling process, improves the efficiency of business handling, and realizes a real paperless office.

Description

technical field [0001] The invention relates to the field of handwriting technology, in particular to a method for intelligently recognizing handwriting input. Background technique [0002] With the rapid development of information technology, it is very important to effectively identify a person's identity in the field of information security. Handwritten signature is a biometric feature. Using handwritten signature for personal identity authentication has the characteristics of good anti-counterfeiting and is not easy to be lost or forgotten. An important means of personal identification. [0003] In the process of business processing in various industries, a large number of businesses require customers to sign and confirm. Handwritten signature is divided into offline signature and online signature. Offline signature is mainly to input the original handwritten signature into the computer through input devices such as scanners, and then analyze it; online signature is mai...

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): G06K9/00
CPCG06V40/37G06V40/388
Inventor 郑炎平陈祖家刘备赵欢
Owner 北京爱知之星科技股份有限公司
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