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

Method for analyzing handwriting characteristics by using machine learning algorithm

A technology of machine learning and algorithm analysis, applied in the field of data recognition, can solve problems such as handwriting analysis that cannot be applied in a wider range, and achieve good economic and social benefits

Active Publication Date: 2019-08-30
SHANDONG INSPUR SCI RES INST CO LTD
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, computer vision and machine learning using AI technology have been developed for many years, and the technology is relatively mature, but it has not been able to have a deeper and wider application in handwriting analysis.

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
  • Method for analyzing handwriting characteristics by using machine learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] combined with figure 1 , this embodiment proposes a method for analyzing handwriting features by using a machine learning algorithm, and the specific implementation process of the method includes:

[0042] Step 1. According to the general handwritten font data set and the correspondence between handwriting and personality in handwriting research, build a gene map model of handwriting and personality;

[0043] Step 2, collecting the user's handwritten font image;

[0044] Step 3: Perform segmentation processing on the collected handwritten font image to form a single handwritten font image;

[0045] Step 4: Using machine learning algorithms to detect and analyze a single handwritten font image through AI computer vision, and extract the handwriting features of the single handwritten font image;

[0046] Step 5. Find and extract the font with the highest similarity in handwriting features in the general handwritten font data set, and output the general character feature...

Embodiment 2

[0065] combined with figure 1 , this embodiment proposes a method for analyzing handwriting features by using a machine learning algorithm, and the specific implementation process of the method includes:

[0066] Step 1. According to the general handwritten font data set and the correspondence between handwriting and personality in handwriting research, build a gene map model of handwriting and personality;

[0067] Step 2, collecting the user's handwritten font image;

[0068] Step 3: Perform segmentation processing on the collected handwritten font image to form a single handwritten font image;

[0069] Step 4: Using machine learning algorithms to detect and analyze a single handwritten font image through AI computer vision, and extract the handwriting features of the single handwritten font image;

[0070] Step 5. Find and extract the font with the highest similarity in handwriting features in the general handwritten font data set, and output the general character feature...

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 analyzing handwriting characteristics by using a machine learning algorithm, and relates to the technical field of data identification. The technical scheme of themethod includes the steps: utilizing a general handwritten font data set and a corresponding relation between handwriting and characters in handwriting research to construct a handwriting and character gene map model; collecting a handwriting font image of the user and extracting handwriting characteristics; obtaining the character characteristics of the user through identification by an expert according to the handwriting characteristics while inputting the extracted handwriting characteristics into the model; when the output result of the model is inconsistent with the expert identificationresult, correcting and revising the model by using the expert identification result; and when the model output result is not smaller than the set threshold value, obtaining the handwriting and characteristic gene atlas highly similar to the real character characteristics of the user to which the handwriting characteristics belong by analyzing the handwriting characteristics by the identificationmodel, wherein the handwriting and characteristic gene atlas can be applied to various criminal investigation case analysis, human resource analysis and other aspects.

Description

technical field [0001] The invention relates to the technical field of data recognition, in particular to a method for analyzing handwriting features using a machine learning algorithm. Background technique [0002] Handwriting has always been a very important part in real life and work. The ubiquitous signatures and records that prove one's identity, a person's handwriting is a personal manifestation, which can show a person's psychology, personality and other characteristics. "Handwriting identification" is a specialized subject field. The traditional model mainly relies on the identification of handwriting identification experts with naked eyes or auxiliary tools. The actual application is time-consuming and laborious, and the accuracy and feature effects are also limited by human factors. Difficult to be widely used. [0003] With the development of artificial intelligence technology, algorithms such as machine learning and deep learning can be used to identify objects...

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): G06K9/00G06K9/62
CPCG06V30/2268G06F18/22
Inventor 于静于治楼姜凯
Owner SHANDONG INSPUR SCI RES INST CO LTD