Image classification method based on deep ridgelet neural network

A neural network and classification method technology, applied in the field of intelligent image processing, can solve the problems of reducing data, difficult to satisfy image data, and difficult to achieve the optimal solution, etc., to achieve the effect of increasing the approximation rate, improving the classification accuracy, and improving the sparse approximation ability

Active Publication Date: 2017-03-22
XIDIAN UNIV
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The classification method based on the feature space can reduce the dimension of the data and the computational complexity to a certain extent, but the correlation betwe...

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 deep ridgelet neural network
  • Image classification method based on deep ridgelet neural network
  • Image classification method based on deep ridgelet neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The technical solutions and effects of the present invention will be described in further detail below with reference to the accompanying drawings.

[0040] refer to figure 1 , the implementation steps of the present invention are as follows:

[0041] Step 1, obtain training samples and test samples.

[0042] Randomly select 10% of all image samples from the image library as the training image sample set, wherein the nth training image sample is recorded as P(n), n=1,..., N is the number of training image samples, the first The class label of n training image samples is L(n), and the remaining samples are used as test image samples, Q(m) is the mth test image sample, m=1,...,M, M is the number of test image samples number.

[0043] Step 2, regroup the training samples.

[0044] For each training image sample P(n), rearrange it into a column vector S according to the row-first rule 1 (n):

[0045]

[0046] in, represents the column vector S 1 The i-th element...

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 an image classification method based on a deep ridgelet neural network, and mainly solves problems that the prior art based on the neural network is long in image classification training time, and is not high in classification precision. The method comprises the implementation steps: 1, selecting 10% of data in an image library as a training sample, wherein the remaining data serves as test samples; 2, building a network structure of the deep ridgelet neural network, and enabling the training sample to serve as the input of the network; 3, carrying out the layered learning of parameters of each layer in the deep ridgelet neural network through a ridgelet auto-encoder; 4, enabling a parameter result of layered learning to serve as the initial values of parameters in the deep ridgelet neural network, carrying out the training of the parameters in the whole network through a gradient descending method, and obtaining a trained network; 5, inputting the test samples into the network, and obtaining a class label of each test sample. The method is high in classification precision, is high in training speed, and can be used for target detection and analysis and the detection of social activities.

Description

technical field [0001] The invention belongs to the technical field of intelligent image processing, and in particular relates to an image classification method, which can be used for target recognition, target analysis and social activity detection. Background technique [0002] With the progress of society and the rapid development of science and technology, images have become more and more important means for people to obtain information. In recent years, the number of images that appear in people's lives has increased rapidly. For a huge amount of image data, people need to quickly, effectively and reasonably analyze and process these massive image data and identify and classify the analyzed images. Greatly improve the efficiency of people finding the information they need from massive image information. In this era of digital and information technology that pursues efficiency, it takes a lot of labor and time resources to use manual participation to classify massive im...

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): G06K9/62G06N3/08
CPCG06N3/084G06F18/2415
Inventor 刘芳郝红侠石程焦李成杨淑媛尚荣华马文萍马晶晶
Owner XIDIAN 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
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