Electronic laryngoscope image classification method based on binuclear convolution feature extraction

A feature extraction and electronic throat technology, applied in the field of computer vision and pattern recognition, can solve the problems of low efficiency and accuracy of classification and recognition

Pending Publication Date: 2021-04-20
XIAN UNIV OF POSTS & TELECOMM
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such methods often ignore the particularity and detailed information features of electronic laryngoscope images, which easily lead to low classification and recognition efficiency and accuracy.

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
  • Electronic laryngoscope image classification method based on binuclear convolution feature extraction
  • Electronic laryngoscope image classification method based on binuclear convolution feature extraction
  • Electronic laryngoscope image classification method based on binuclear convolution feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0037] Step 1: Data preprocessing stage, such as figure 1 shown;

[0038] Step 2: First, we extract a picture currently to be processed from step 1, such as figure 2 , entered into image 3 In the dual-kernel convolutional feature extraction network. Secondly, in order to demonstrate the effect of network extraction features, we obtain the features of the previous layer of the fully connected layer and visualize them, as follows: Figure 4 result. Finally, the image gets a 1*512-dimensional image feature F through the fully connected layer.

[0039] F=[0,0,0.24433999,0,0.7739287,2.735432,1.2492355,0,0,5.9589076,...,2.735432,1.2492355,0,0,0,5.9589076]

[0040] Step 3: Input the F obtained i...

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 an electronic laryngoscope image classification method based on binuclear convolution feature extraction. The invention belongs to the field of computer vision and pattern recognition. The method comprises the following steps: firstly, preprocessing a laryngoscope image, including frame splitting and image cutting, retaining effective image information, and then adjusting the image size to 224 * 224; secondly, designing a deep convolutional neural network capable of acquiring detail information features of the image, inputting the image into the network, and extracting high-order image features with detail information; and then, training an integrated classifier from the obtained image feature information by using an extreme gradient boost (Xgboost) integration method to obtain an electronic laryngoscope image classification result. The extracted image features have rich detail features such as texture features, shape features and position information, and the accuracy of electronic laryngoscope image classification is effectively improved in combination with an Xgboost integrated classification method.

Description

technical field [0001] The invention belongs to the fields of computer vision and pattern recognition. Specifically: Invented a deep convolutional neural network (CNN) that can extract rich and detailed features, and combined with the extreme gradient boosting (Xgboost) integrated classification method to classify and recognize electronic laryngoscope images. This method can classify and identify low-level texture features, shape features and location information and other electronic laryngoscope image parts that are not obvious signs, thereby improving the classification and recognition of nasopharynx and vocal cord closure parts in electronic laryngoscope images, and improving the overall classification. the accuracy rate. Background technique [0002] Electronic laryngoscope is the main auxiliary tool for otolaryngologists to diagnose otolaryngology diseases, and the analysis of electronic laryngoscope images is a direct reference for doctors to judge otolaryngology dise...

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): G06K9/62G06N3/04G06N3/08
Inventor 陈皓闫庆元郝马阳
Owner XIAN UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap