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

Wrist bone grade recognition method based on secondary classification

A secondary classification and recognition method technology, applied in the field of grade recognition, can solve the problem of inaccurate wrist bone grade recognition and achieve the effect of improving the recognition rate

Active Publication Date: 2019-07-05
浙江康体汇科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the inaccurate shortcomings of the existing wrist bone level recognition, and introduce the image recognition method based on deep learning into the wrist bone level recognition method to achieve more accurate judgment in the case of insufficient samples of certain categories

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0017] This embodiment provides a method for identifying wrist bone grades based on secondary classification, and the specific steps are divided into:

[0018] Step 1) Use a batch of wrist bone sample sets to train a fully classified deep learning network model according to the actual situation. Each wrist bone sample in the sample set has been calibrated with the bone development level;

[0019] Step 2) for the sample set, count the number of samples of each level, and use Nmax to represent the number of the highest level samples;

[0020] Step 3) Find out the grades whose number of samples is less than 0.25*Nmax, and use x1, x2,...,xn to represent these grades;

[0021] Step 4) For each i∈{1,2,…,n}, use the wrist bone sample set to train a support vector machine three-category model with xi-2, xi-1 and xi as output and A support vector machine three-category model with xi, xi+1 and xi+2 as outputs;

[0022] Step 5) For any wrist bone piece that needs to judge the grade, us...

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 wrist bone grade recognition method based on secondary classification. According to the invention, a deep learning method is used for judging the medical image, and the support vector machine and the deep learning network are combined for use to achieve a better effect. On the premise that judgment of other types of pictures is not affected, the more accurate judgment canbe made on a small number of types of pictures.

Description

technical field [0001] The present invention relates to the technical field of bone age grade assessment, in particular, the present invention relates to a method for identifying wrist bone grade based on secondary classification. Background technique [0002] Deep learning has very broad prospects in image recognition, natural language processing, speech recognition and other fields. Since some levels of data sets in deep learning are limited, how to accurately identify a small number of levels of data is one of the key issues to be studied. [0003] Deep learning networks are very poor at learning data sets with too few categories. For example, assuming that the number of weak categories is only one-tenth of the number of strong categories, then the final trained model is very inaccurate in judging weak categories. Therefore, how to improve the recognition accuracy of data with a small number of categories is an important issue worthy of continuous and in-depth research....

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/10G06V2201/033G06F18/24G06F18/214
Inventor 毛科技杨威斌池凯凯宦若虹许星原
Owner 浙江康体汇科技有限公司
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