Image classification method based on crowd-sourcing integrated learning

An integrated learning and classification method technology, which is applied in the field of image classification based on integrated learning, can solve the problems of inability to modify classification conditions, inconvenient use, and image classification methods that cannot be classified.

Active Publication Date: 2019-07-02
BEIJING UNIV OF TECH
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the fact that most of the existing image classification methods cannot classify images according to feature points, and cannot modify the classification conditions at

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 crowd-sourcing integrated learning
  • Image classification method based on crowd-sourcing integrated learning
  • Image classification method based on crowd-sourcing integrated learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0009] The operation process of the image classification method based on crowd intelligence ensemble learning includes:

[0010] Step 1, obtain an image dataset with annotations, and perform image preprocessing operations;

[0011] Step 2, perform feature extraction and selection on the preprocessed data set;

[0012] Step 3, construct the basic learning model;

[0013] Step 4, a collection of multiple basic models;

[0014] Each step is described in detail below:

[0015] (1) Image preprocessing: This step first renames the image, and then normalizes the original image through target detection, including size normalization, enhanced lighting operations, and converts it to a grayscale image.

[0016] (2) Feature selection: By performing principal component analysis (PCA) and kernel PCA on each grayscale image, features that retain more than 95% of the information are extracted.

[0017] (3) Basic learning model construction: A basic learning model is adopted, that is, a su...

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 crowd intelligence ensemble learning. The technical scheme adopted by the invention is a method for improving the accuracy of image classification based on an ensemble learning method. A traditional svm training mode is changed, the traditional svm is combined with the thought of a random forest, and a final prediction result is morerobust and more reliable. For a face data set collected from a system database of the endocrinology department of a certain hospital, the optimal performance of the comprehensive classifier is 88.1%for the correct classification rate of a face image detection task. It is proved that the integrated learning method can achieve classification of the face images, and in other scene image data sets,the method also achieves a very good effect.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image classification method based on integrated learning. The invention can classify images conveniently, has simple classification steps, is easy to realize, can improve classification accuracy, avoids classification errors, and has a simple method and convenient use. Background technique [0002] Image classification is an image processing method that distinguishes different types of objects according to the different characteristics reflected in the image information. It is the problem of taking an input image and outputting a description of the content classification of the image. It is at the heart of computer vision and has a wide range of practical applications. The traditional method of image classification is feature description and detection. This kind of traditional method may be effective for some simple image classification, but due to the complexity of...

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
CPCG06F18/2135G06F18/2148G06F18/2411G06F18/254G06F18/259
Inventor 李建强姚国红赵青高翔
Owner BEIJING UNIV OF TECH
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