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

Parkinson's disease patient handwritten character automatic recognition method based on machine learning

A Parkinson's disease and machine learning technology, applied in the field of identification, can solve the problems of expensive and inconvenient shockproof devices, achieve the effect of facilitating daily work and life, improving accuracy, and reducing the cost of manual identification

Inactive Publication Date: 2017-12-08
邱宇轩 +1
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The corresponding anti-shock device is quite expensive and needs to be carried around, which is very inconvenient. There are many inconveniences and uncertainties in daily operation or use.

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
  • Parkinson's disease patient handwritten character automatic recognition method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the present invention more comprehensible, a preferred embodiment is now described in detail with accompanying drawings as follows.

[0026] Such as figure 1 As shown, a method for automatic recognition of handwritten characters of Parkinson's patients based on machine learning comprises the following steps:

[0027] Step 1. Pre-collect a large number of handwritten characters of Parkinson's patients;

[0028] Step 2, each character is made into a corresponding image, and all images are converted into a unified image specification, the image specification includes image size, image color, image brightness and image format; each image is set to a unified specifications to enhance recognition accuracy;

[0029] Step 3, classify all images one by one according to the content of the image, such as: classify all collected "big" characters into one category, group all collected "small" characters into one category, and classify all "small" characters "Many...

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 provides a Parkinson's disease patient handwritten character automatic recognition method based on machine learning. The method comprises the steps that 1, Parkinson's disease patient handwritten characters are collected in advance; 2, each character is manufactured into a corresponding image and the image is converted into the unified image specification; 3, all the images are classified one by one according to the content of the images; 4, an image model is established for the classified images one by one; 5, the image in the image model is cyclically called to perform iterative training so as to reduce the error of the image model and finally optimize the accuracy of each image model; and 6, when the user inputs the image, the similarity of the inputted image and the images pre-stored in all the image models is compared and whether the similarity is higher than the preset similarity threshold is judged, and the inputted image content is automatically recognized if the judgment result is yes; or the user is prompted to input the corresponding character of the inputted image through handwriting and the process enters the step 2. The content of the Parkinson's disease patient handwritten characters can be automatically recognized so that daily life is facilitated.

Description

technical field [0001] The invention relates to a recognition method, in particular to a machine learning-based automatic recognition method for handwritten characters of Parkinson's patients. Background technique [0002] Parkinson's Disease (PD for short), also known as Parkinson's Disease. Parkinson's syndrome is a chronic degenerative disorder of the central nervous system. According to statistics, there are about 5 million patients with Parkinson's disease in the world. With the increasing aging problem in China, the prevalence rate of Parkinson's disease in urban population over 65 years old is close to 2%. Parkinson's disease has seriously threatened the health of middle-aged and elderly people in my country. healthy. Patients with Parkinson's disease usually have different degrees of movement disorders, clinically characterized by resting tremor, bradykinesia, muscle stiffness, and posture and gait disturbance. The resting tremor of Parkinson's patients is caused b...

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): G06K9/00G06F17/30
CPCG06F16/5846G06V30/40G06V30/10
Inventor 邱宇轩李筱萌
Owner 邱宇轩
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