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

A massive image classification method based on distributed k-means

A classification method and distributed technology, applied in character and pattern recognition, instruments, calculations, etc., to achieve the effect of reducing classification complexity, time cost and resource overhead

Active Publication Date: 2019-05-14
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention will solve the problem of feature extraction of large-scale images, so as to achieve the purpose of image classification, aiming at the accuracy of image classification, a method based on distributed K-means is proposed The massive image classification method, the research is based on the big data processing platform Hadoop, a parallel image feature extraction algorithm is proposed, the multi-classification problem of the image, and the final image classification is completed by using the DAG-SVM classifier

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
  • A massive image classification method based on distributed k-means
  • A massive image classification method based on distributed k-means
  • A massive image classification method based on distributed k-means

Examples

Experimental program
Comparison scheme
Effect test

example

[0036] The test experiment hardware and software environment of this embodiment is as follows, and its experimental topology is as follows Figure 5 Shown:

[0037] Hardware environment:

[0038] Computer type: desktop;

[0039] CPU: Pentium(R) Dual-Core CPU E5600@2.93GHz

[0040] Memory: 4.00GB (3.49GB available)

[0041] System type: 32-bit operating system

[0042] Graphics card: integrated graphics

[0043] Software Environment:

[0044] IDE: Eclipse

[0045] Image processing SDK: JavaCV

[0046] Development language: Java;

[0047] like figure 1 The present invention is aimed at the system feature extraction algorithm of large-scale image classification, comprises the following steps:

[0048] Step 1. Training image preprocessing;

[0049] Input the training image data set, divide each training image into multiple image blocks, perform regularization and whitening operations on each image block in turn to remove interference information, retain key information,...

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 provides a massive image classification method based on distributed K-means, which belongs to the technical field of machine learning and image processing. The invention can be used for large-scale image classification, and the method uses a distributed K-means algorithm to extract image features on the big data processing platform Hadoop, and finally realizes the purpose of classifying large-scale images. The present invention learns a dictionary on large-scale image data, constructs a feature mapping function and designs a classification algorithm, and proposes a feature extraction algorithm based on distributed K-means on the basis of the big data processing platform Hadoop. This method avoids the tedious work of artificially designing large-scale image features, and reduces the training time under the premise of ensuring the classification accuracy.

Description

technical field [0001] The invention belongs to the technical field of machine learning and image processing, and relates to massive image processing on a distributed platform, in particular to a massive image classification method based on distributed K-means. Background technique [0002] In recent years, clustering algorithms have been widely used in daily life. In business, clustering algorithms help analysts extract specific consumption information from various consumption databases, and summarize the consumption patterns reflected in the consumption information. Clustering algorithm is an important part in the field of data mining. It can usually be used as a good tool to discover the deep-level feature expression in the database. At the same time, it can summarize the characteristics of each specific category. Most importantly, clustering Algorithms can be used as preprocessing steps of various algorithms in the field of data mining. With the continuous increase 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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/2411
Inventor 董乐张宁
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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