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

K-means and deep learning-based image classification algorithm

A classification algorithm and deep learning technology, applied in the information field, can solve the problems of insufficient training samples and gradient dispersion, and achieve the effect of less training parameters, high time efficiency, and improved image classification effect.

Inactive Publication Date: 2017-06-13
HUBEI UNIV OF TECH
View PDF8 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose an image classification algorithm based on K-means and deep learning for the problems of gradient dispersion, insufficient training samples and local optimum in the traditional neural network training method

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
  • K-means and deep learning-based image classification algorithm
  • K-means and deep learning-based image classification algorithm
  • K-means and deep learning-based image classification algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0057] Such as figure 1 with figure 2 Shown, a kind of image classification algorithm based on K-means and deep learning of the present invention comprises the following steps:

[0058] 1) Take an unlabeled image as an input image, and randomly extract image blocks to form an unlabeled image set of the same size. In this embodiment, the number of samples in the unlabeled image set is set to 100,000, and the size of the corresponding samples is an image block of 12*12*3.

[0059] Preprocess the unlabeled image set, including normalization and whitening.

[0060] The normalization process is as follows:

[0061]

[0062] Among them, x is a sample of the input unlabeled image set, Indicates the samples in the unlabeled image set after normalization processing, var and mean represent the variance and mean, respectively, and σ is...

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 K-means and deep learning-based image classification algorithm. The algorithm comprises the steps of 1) taking untagged images as input images, and randomly extracting image blocks to form an untagged image set of the untagged images same in size; 2) extracting a primary optimal clustering center by adopting a K-means algorithm; 3) constructing a feature mapping function, and extracting image features of the untagged image set; 4) performing pooling operation and normalization processing; 5) extracting a secondary optimal clustering center by adopting the K-means algorithm, extracting final image features by adopting convolution operation, and performing standardization processing on the final image features; and 6) classifying the final image features subjected to the standardization processing through a sorter. The algorithm has the advantages of simplicity, high efficiency, few training parameters and the like, and has a very good effect for classification of massive high-dimensional images; and the input images are preprocessed, so that the effects of improving the image classification effect and enhancing the classification precision are achieved.

Description

technical field [0001] The invention belongs to the field of information technology, and specifically refers to an image classification algorithm based on K-means and deep learning, which is suitable for the classification of massive high-dimensional data images in the Internet, and is also used for network image retrieval, video retrieval, Image data classification in remote sensing image classification, interactive games, intelligent robots and other fields. Background technique [0002] In the field of massive image data processing technology, deep learning is a relatively common algorithm. As an algorithm, deep learning was proposed by Hinton in 2006 and has been widely recognized and applied. Its essence is to learn useful and abstract information by establishing an artificial neural network model with multiple hidden layers and large-scale training data. features, the final result is to improve the accuracy of image classification. Therefore, deep learning can well s...

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
CPCG06F18/24137G06F18/23213
Inventor 王改华李涛吕朦袁国亮
Owner HUBEI UNIV OF TECH
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