Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Complex support vector machine classification method based on unitary space multi-feature fusion

A multi-feature fusion and support vector machine technology, which is applied to computer parts, instruments, calculations, etc., can solve the problem of low classification accuracy and achieve the effect of improving accuracy and reducing training and testing time

Pending Publication Date: 2021-11-12
SHENZHEN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above defects of the prior art, the present invention provides a complex support vector machine classification method based on unitary space multi-feature fusion, aiming to solve the problem of low classification accuracy based on SVM in the prior art

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
  • Complex support vector machine classification method based on unitary space multi-feature fusion
  • Complex support vector machine classification method based on unitary space multi-feature fusion
  • Complex support vector machine classification method based on unitary space multi-feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Such as figure 1 Shown, in an embodiment of described classification method, comprise step:

[0052] S100. Extract a first feature and a second feature of an object to be classified.

[0053] The object to be classified can be an image, text, etc., and the first feature and the second feature are features extracted by different feature extraction methods, that is, the first feature is a feature extracted by the first feature extraction method, and the second feature is Using the features extracted by the second feature extraction method, taking the object to be classified as an example, the first feature can be an LBP (local binary pattern) feature, and the second feature can be a SURF (accelerated robust) feature, or, The first feature is the SURF feature, and the second feature is the LBP feature. As a global feature, the LBP feature is invariant to rotation and grayscale, but in some cases, such as when key parts are lost or occluded, the recognition rate is low. C...

Embodiment 2

[0127] Based on the above embodiments, the present invention also provides a corresponding classification device, such as Figure 10 As shown, the classification device includes:

[0128] An initial feature extraction module, the initial feature extraction module is used to extract the first feature and the second feature of the object to be classified, specifically as described in the first embodiment;

[0129] A feature fusion module, the feature fusion module is used to use the first feature of the object to be classified as a real part, and use the second feature of the object to be classified as an imaginary part to combine to obtain the complex feature corresponding to the object to be classified , specifically as described in Example 1;

[0130] A feature selection module, the feature selection module is used to perform feature selection on the complex features corresponding to the object to be classified according to a preset matrix, and extract the target feature cor...

Embodiment 3

[0133] Based on the above embodiments, the present invention also provides a corresponding terminal, such as Figure 11 As shown, the terminal includes a processor 10 and a memory 20 . Figure 11 Only some components of the terminal are shown, but it should be understood that implementation of all illustrated components is not required, and more or fewer components may be implemented instead.

[0134] The storage 20 may be an internal storage unit of the terminal in some embodiments, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk equipped on the terminal, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD ) card, flash memory card (Flash Card), etc. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and 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 complex support vector machine classification method based on unitary space multi-feature fusion, and the method comprises the steps: extracting the initial features of a to-be-classified object, the initial features comprising a first feature and a second feature; taking the first feature of the to-be-classified object as a real part, taking the second feature of the to-be-classified object as an imaginary part, and combining to obtain a complex feature corresponding to the to-be-classified object; performing feature selection on the complex features corresponding to the to-be-classified object according to a preset matrix, and extracting target features corresponding to the to-be-classified object; and inputting the target feature corresponding to the to-be-classified object into a trained classification vector machine to obtain the category of the to-be-classified object. According to the method, the classification accuracy can be improved by combining different features, and the training and detection time of the classification vector machine is shortened by performing feature selection on the features obtained by combining the extracted different features before the features are input into the classification vector machine.

Description

technical field [0001] The invention relates to the technical field of classification, in particular to a complex support vector machine classification method based on unitary space multi-feature fusion. Background technique [0002] Classification tasks are very common in life. Accurate and efficient classification algorithms have always been a research hotspot. Among the existing classification algorithms, SVM (Support Vector Machine) algorithms are widely used. SVM-based classification algorithms extract the characteristics of classified objects and input them into the support However, the accuracy of the classification algorithm based on SVM in the prior art needs to be improved. [0003] Therefore, the prior art still needs to be improved and improved. Contents of the invention [0004] In view of the above-mentioned defects of the prior art, the present invention provides a complex support vector machine classification method based on unitary space multi-feature fus...

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): G06K9/62
CPCG06F18/2411G06F18/253G06F18/214Y02P90/30
Inventor 徐颖郑润晓蔡大森唐文涛陈晓清张文杰庾名星
Owner SHENZHEN UNIV
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
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