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

3D handwriting recognition svm classifier kernel parameter selection method and application

A technology of handwriting recognition and kernel parameters, which is applied in the field of 3D handwriting recognition, can solve the problems of the firefly algorithm not fast enough, limited application, unstable algorithm convergence, etc., to achieve the effect of increasing the convergence speed, compensating for the decline in accuracy, and improving the recognition rate

Inactive Publication Date: 2017-01-11
ZHEJIANG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the convergence speed of the firefly algorithm is not fast enough, and the convergence instability will appear in the later stage of the algorithm. These shortcomings limit the application of the firefly algorithm in 3D handwriting recognition.

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
  • 3D handwriting recognition svm classifier kernel parameter selection method and application
  • 3D handwriting recognition svm classifier kernel parameter selection method and application
  • 3D handwriting recognition svm classifier kernel parameter selection method and application

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention mainly relates to the algorithm improvement of SVM kernel parameter selection, such as figure 1 As shown, it shows that adding the brightness factor when the position is updated will affect the size of the moving step; combined figure 1 Explain that the specific process of selecting SVM core parameters is as follows:

[0021] In the basic firefly algorithm, first randomly distribute n fireflies in the solution space. Each firefly has its own initial brightness value, and their brightness is related to the function value of their current location. The better the location, then The higher the brightness. Each firefly has a line of sight (also known as a dynamic decision domain). In this line of sight, it looks for a firefly with a higher brightness than itself, and forms a neighbor set, and then selects the firefly with the highest relative brightness through the roulette probability method And move towards it. After the move, update your own brightnes...

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 3D-handwritten-recognition SVM classifier nuclear-parameter selection method which improves a position update formula of glowworms in a GSO (Glowworm Swarm Optimization) algorithm and introduces lightness features in an individual movement process so that accuracy and convergence of the algorithm are improved significantly and thus an optimal SVM nuclear function parameter is selected and a classifier excellent in performance is constructed. Through use of the method, a better 3D-handwritten-recognition system can be constructed and the identification rate of the 3D-handwritten-recognition system is improved effectively.

Description

Technical field [0001] The present invention belongs to the technical field of 3D handwriting recognition, and particularly relates to the problem of SVM classifier optimization in 3D handwriting recognition technology. Background technique [0002] Handwriting recognition technology is a popular technology gradually developed under the trend of human-computer interaction technology. Compared with the traditional plane handwriting recognition, 3D handwriting recognition is an emerging handwriting recognition technology that can provide users with a more natural and efficient human-computer interaction experience. It has gradually become a research hotspot in handwriting recognition technology in these years. The development trend of handwriting recognition in the future. [0003] The optimization of the kernel function parameters of the SVM classifier has been a key technology in the 3D handwriting recognition process. The performance of the kernel function has an important influe...

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): G06K9/66G06N3/00
Inventor 沈海斌杨海
Owner ZHEJIANG 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