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

Image classification method based on visual features and capsule network

A technology of visual features and classification methods, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problems of high computational complexity of image data, gray and color histograms do not match the image position, etc. The effect of increased efficiency, prevention of image overfitting, significant performance benefits

Pending Publication Date: 2022-05-10
电子科技大学成都学院
View PDF0 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 address the deficiencies and defects of the prior art. In order to effectively solve the technical problems of high computational complexity of a large amount of image data and the lack of image positions in the grayscale color histogram, a creative method based on Image classification method based on visual features and capsule network

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
  • Image classification method based on visual features and capsule network
  • Image classification method based on visual features and capsule network
  • Image classification method based on visual features and capsule network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] The method of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0012] Such as figure 1 As shown, an image classification method based on visual features and capsule network, including the following steps:

[0013] Step 1: Compress the grayscale of the image, and extract the visual features using the co-occurrence matrix.

[0014] Specifically, let the gray level of the image be A, the size of the co-occurrence matrix B is A×A, B(m,n) represents the probability that the gray value m and n appear simultaneously in the image, and the relative distance between two pixels with angles D and φ, respectively.

[0015] In order to reduce the calculation problem caused by a large amount of data, the grayscale of the image is compressed to between 0-255. Then, the visual features are extracted by co-occurrence matrix.

[0016] Step 2: Use fractal dimension to describe the degree of self-similarity of image texture...

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 relates to an image classification method based on visual features and a capsule network, and belongs to the field of computer image processing. According to the method, the gray level of the image is compressed, visual features are extracted by adopting a co-occurrence matrix and fractal dimensions, and various attribute information contained in the image is expressed by adopting the output of neurons in a capsule network. And representing the relationship between the capsule and the sub-capsule through a dynamic routing algorithm, and continuously calculating the dynamic routing in training and testing to obtain the output of the capsule network. An image big data classification algorithm is deployed on cloud computing nodes, a data model updated in batches is adopted, a training set of images is divided into numerous data blocks for parallel training, training samples are used for forward and backward propagation to obtain weight gradients, an average value of the weight gradients of all the training samples is calculated, and sample weights are updated at the same time. Compared with the prior art, the method has the advantages that the image classification accuracy and efficiency are obviously improved, and remarkable performance advantages are shown.

Description

technical field [0001] The invention relates to an image classification method, in particular to an image classification method based on visual features and a capsule network (CapsNet), belonging to the field of computer image processing. Background technique [0002] With the rapid development of information technology, tens of thousands of images are generated every day. Especially with the continuous development of the mobile cloud era, image classification has attracted more and more attention. How to mine important image information from massive data is one of the hot issues in current research. [0003] In order to extract image data information, it is necessary to use a variety of technologies, such as database, data mining and so on. However, with the increase of data types and the diversification of data structures, the general data mining technology can no longer meet the special application requirements, and new methods are needed to solve the problems of large ...

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): G06V10/40G06V10/774G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06F18/24G06F18/214
Inventor 罗丹鲍海宁
Owner 电子科技大学成都学院
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