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

A Formed Component Classification Method Based on SVM

A classification method and tangible technology, applied in the field of image recognition, can solve the problems of limited accuracy, incomplete application of SVM recognition and classification algorithm classification and recognition, and achieve good application results

Active Publication Date: 2020-01-17
DIRUI MEDICAL TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the deficiencies in the above-mentioned prior art, the object of the present invention is to provide a method for classifying formed components based on SVM, aiming at solving the incompleteness and accuracy of the existing SVM recognition and classification algorithm in the classification and identification of formed components. limited rate problem

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 Formed Component Classification Method Based on SVM
  • A Formed Component Classification Method Based on SVM
  • A Formed Component Classification Method Based on SVM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The invention provides a method for classifying shaped components based on SVM. In order to make the object, technical solution and effect of the present invention more clear and definite, the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0052] Such as figure 1 Shown is the SVM-based shaped component classification method of the specific embodiment of the present invention. The method can be specifically divided into two stages: an SVM training stage and a formed element recognition and classification stage.

[0053] Wherein, the SVM training phase includes:

[0054] S1. Obtain sample pictures containing several types of formed elements as training samples. The sample picture specifically refers to a medical microscopic image containing vario...

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 classifying formed components based on SVM. The method includes: SVM training stage: A, acquiring a sample picture containing several kinds of formed components as a training sample; B, dividing the sample picture into several formed component images; C, extracting the formed component images and according to the image features, the formed component images are classified, and a library of several cascaded formed component pictures is constructed; D, constructing several cascaded SVM classifiers and using corresponding formed component pictures library for training, and the stage of recognition and classification of formed components: E, extract the image features of the formed component images to be identified and classified; F, assign the formed component images to corresponding SVM classifiers for identification according to the image features Classification. Multiple cascaded SVM classifiers are used to carry out multi-level classification of the formed component graph, thus effectively improving the classification accuracy of the SVM classifier for the formed component.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method for classifying formed components based on SVM. Background technique [0002] Image recognition technology is a relatively popular technology in recent years. Whether it is license plate recognition, face recognition, fingerprint recognition or cell recognition, the object of recognition is relatively single, and in most cases, recognition and classification are realized based on neural networks. The neural network simulates the human nerves and is a simplified description of the cognitive behavior of the human brain. Without a complete theoretical system, it is easy to fall into a local minimum. [0003] SVM, or support vector machine, can get much better results than other algorithms on a small sample training set, and is currently one of the most commonly used and best classifiers. It has a complete theoretical system, is based on the theory of structural ...

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): G06K9/62G06N3/00
CPCG06N3/002G06F18/2411
Inventor 任迪唐松
Owner DIRUI MEDICAL TECH CO LTD
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