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

Novel digital image classification method

A digital image and classification method technology, applied in the field of image processing, can solve the problems of high degree of automation and achieve the effect of high degree of automation and low classification accuracy

Inactive Publication Date: 2020-01-14
FUJIAN NORMAL UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The invention provides a new type of digital image classification method, which can overcome the complicated problem of manually extracting features in the current digital image classification, can accurately classify most scenes, does not require manual intervention, and has a high degree of automation

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
  • Novel digital image classification method
  • Novel digital image classification method
  • Novel digital image classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0028] figure 1 It is the overall processing flow chart of the present invention. Such as figure 1 As shown, 101 is the step of constructing feature extraction model, 102 is the step of training feature extraction model, 103 is the step of extracting feature vector, 104 is the step of feature vector dimensionality reduction, 105 is the feature fusion step, 106 is the step of constructing and training classifier, 107 It is the step of inputting the digital image to be classified, and 108 is the step of outputting the classification result.

[0029] Step 101: Construct a feature extraction model, and create a digital image collection D={D 1 ,D 2 ,...,D k ,...,D T } And the data identification set L corresponding to the digital image set D = {L 1 ,L 2 ,...,L k ,...,L T }, T is the number of image categories contained in the digital image collectio...

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 a novel digital image classification method. The method comprises the following steps: step 1, constructing a feature extraction model; step 2, training a feature extraction model; step 3, extracting a feature vector; step 4, performing feature vector dimension reduction; step 5, performing feature fusion on the feature vector MFV after dimension reduction to obtain a fused feature vector; step 6, constructing and training a classifier; step 7, inputting a digital image to be classified; and step 8, outputting a classification result. The method has the beneficial effects that the problem of low classification precision in digital image classification is solved, and the algorithm is fully automatic. The method can be used for remote sensing image classification, natural scene classification and other fields.

Description

Technical field [0001] The invention relates to the field of image processing, in particular to a new type of digital image classification method. Background technique [0002] Digital image classification is an image processing method that distinguishes different types of targets or scenes based on different features reflected in digital image information. It uses a computer to quantitatively analyze digital images, and classify each pixel or area in the image or image as one of a certain category to replace human visual interpretation. With the popularization of network technology and the explosive growth of multimedia information, the types and quantities of digital image content are increasing day by day. Nowadays, in the face of massive image data, relying on traditional manual classification and labeling methods is far from satisfying the demand, not only a huge waste of human resources Moreover, the timeliness and reliability of the work cannot be guaranteed. Digital ima...

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): G06K9/62
CPCG06F18/214G06F18/2415G06F18/253
Inventor 施文灶程姗乔星星刘芫汐林耀辉
Owner FUJIAN NORMAL UNIV
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