Classification network of three-dimensional image and method thereof and image processing equipment

A classification network and three-dimensional image technology, applied in the field of image processing, can solve the problems of inability to provide a three-dimensional image classification method, low three-dimensional image classification efficiency, etc., to improve the classification efficiency and achieve the effect of direct processing

Pending Publication Date: 2022-02-11
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a classification network, method and image processing equipment for three-dimensional images, aiming to solve the problem of low efficiency of three-dimensional image classification due to the inability of the prior art to provide an effective three-dimensional image classification method

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
  • Classification network of three-dimensional image and method thereof and image processing equipment
  • Classification network of three-dimensional image and method thereof and image processing equipment
  • Classification network of three-dimensional image and method thereof and image processing equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] figure 1 The structure of the three-dimensional image classification network provided by the first embodiment of the present invention is shown, and for the convenience of description, only the parts related to the embodiment of the present invention are shown.

[0024] The three-dimensional image classification network 1 provided by the embodiment of the present invention includes a first three-dimensional convolutional layer 11, a three-dimensional maximum pooling layer 12, a plurality of sequentially connected three-dimensional moving inversion bottleneck modules 13, a second three-dimensional convolutional layer 14, and a full connection Modulo 15, where:

[0025] The first three-dimensional convolutional layer 11 is used to perform a convolution operation on the input image to be classified to obtain a three-dimensional feature map of multiple channels, the three-dimensional feature map is a local feature map of the image to be classified, and the image to be class...

Embodiment 2

[0033] figure 2 The structure of the three-dimensional image classification network provided by the second embodiment of the present invention is shown, and for the convenience of description, only the parts related to the embodiment of the present invention are shown.

[0034] The three-dimensional image classification network 2 provided by the embodiment of the present invention includes a first three-dimensional convolutional layer 21, a three-dimensional maximum pooling layer 22, a plurality of sequentially connected three-dimensional moving inversion bottleneck modules 23, a second three-dimensional convolutional layer 24, and a full connection Module 25, wherein the first three-dimensional convolutional layer 21 is used to perform a convolution operation on the input image to be classified to obtain a three-dimensional feature map of multiple channels, the three-dimensional feature map is a local feature map of the image to be classified, and the image to be classified ...

Embodiment 3

[0049] Figure 4 It shows the implementation process of the three-dimensional image classification method provided by the third embodiment of the present invention. The three-dimensional image classification method classifies the input three-dimensional image through the three-dimensional image classification network in the above embodiment. For the convenience of description, only The parts relevant to the embodiments of the present invention are described in detail as follows:

[0050] In step S401, the input image to be classified is convoluted through the first three-dimensional convolution layer to obtain a three-dimensional feature map of multiple channels, the three-dimensional feature map is a local feature map of the image to be classified, and the image to be classified is 3D image;

[0051] In step S402, the three-dimensional feature map output by the first three-dimensional convolutional layer is compressed through the three-dimensional maximum pooling layer to ob...

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 is suitable for the technical field of image processing, and provides a three-dimensional image classification network and an image processing device and a method thereof, and the network comprises a first three-dimensional convolution layer, a three-dimensional maximum pooling layer, a plurality of three-dimensional mobile inverted bottleneck modules, a second three-dimensional convolution layer, and a full connection module. The method comprises the following steps: carrying out convolution on a to-be-classified image through a first three-dimensional convolution layer, compressing a three-dimensional feature map output by the first three-dimensional convolution layer through a three-dimensional maximum pooling layer, and processing the three-dimensional feature map output by the three-dimensional maximum pooling layer through a plurality of three-dimensional mobile inverted bottleneck modules, and by improving the channel dimension of the three-dimensional feature map output by the last module in the plurality of three-dimensional mobile inverted bottleneck modules through a second three-dimensional convolutional layer, finally, connecting the features output by the second three-dimensional convolutional layer through a full connection module, and determining the category of the to-be-classified image is determined according to the features obtained through connection, so that the direct processing of the three-dimensional image is realized, and the classification efficiency of the three-dimensional image is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a three-dimensional image classification network, method and image processing equipment. Background technique [0002] Magnetic Resonance Imaging is also called Magnetic Resonance Imaging (abbreviated as MRI). This technology uses the principle of nuclear magnetic resonance, and according to the different attenuation of the released energy in different structural environments inside the material, the emitted energy is detected by an external gradient magnetic field. Electromagnetic waves of the object can be used to know the position and type of the atomic nucleus that constitutes the object, and based on this, the internal structure image of the object can be drawn. The application of this technology in clinical diagnosis and scientific research has become a reality, which has greatly promoted the development of medicine, cognitive neurology and other discip...

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): G06V10/764G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06N3/045G06F18/241
Inventor 征博文高昂黄晓娜李宇涵梁栋隆晓菁
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
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