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

Non-negative matrix factorization and convolutional neural network-based color image processing method

A technology of non-negative matrix decomposition and convolutional neural network, which is applied in the field of image processing and color image processing of convolutional neural network, can solve problems such as overfitting, long calculation time, and low classification accuracy, and achieve less reconstruction errors , high classification efficiency, good representative effect

Inactive Publication Date: 2018-09-04
NANJING UNIV OF INFORMATION SCI & TECH
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Deep learning has received more and more attention in the fields of image recognition, automatic speech recognition, and natural language processing, but there are still many problems such as overfitting, long calculation time, and low classification accuracy.

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
  • Non-negative matrix factorization and convolutional neural network-based color image processing method
  • Non-negative matrix factorization and convolutional neural network-based color image processing method
  • Non-negative matrix factorization and convolutional neural network-based color image processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0045] The color image processing method based on non-negative matrix factorization and convolutional neural network of the present embodiment comprises the following steps:

[0046] Step 1. Image preprocessing

[0047] 1.1 Normalize the pixel values ​​of the color image, change the pixel value range of the image to make it change from 0 to 1; connect all the columns of the three colors of red, green and blue, and express a single image as a data matrix Among them, 3 sub-data matrices Represents the data matrix of red, green and blue respectively, j∈{1,2,...,N} represents the sample index, N is a positive integer, representing the number of samples;

[0048]1.2 Divide each color image in the original color image set to obtain several sub-patches, assuming a fixed attribute, so that each sub-patch of the image is statistically similar base...

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 non-negative matrix factorization and convolutional neural network-based color image processing method. The method comprises a step of obtaining a color image by acquisitionequipment and preprocessing the color image, wherein the preprocessing comprises the following steps of: extracting image features by adoption of a non-smooth non-negative matrix factorization algorithm; and combining a convolutional neural network to optimize a color image classification and reconstruction process: firstly reading an image data matrix to obtain a row number and a column number,initializing corresponding parameters, and combining the convolutional neural network to complete image classification and reconstruction. In color image processing, the image processing method is more accurate in feature extraction, few in reconstruction errors and high in classification efficiency.

Description

technical field [0001] The patent of the present invention relates to image processing in the field of artificial intelligence, in particular to a color image processing method based on a convolutional neural network based on non-negative matrix factorization, and belongs to the technical fields of computer vision and virtual reality. Background technique [0002] Images are an important means for human beings to acquire, express and transmit information. In the past 20 years, with the rapid development of computer technology and electronic technology, the research on color image processing has been continuously deepened. Deep learning has received more and more attention in the fields of image recognition, automatic speech recognition and natural language processing, but there are still many problems such as overfitting, long calculation time, and low classification accuracy. Contents of the invention [0003] In order to solve the problems in the prior art, the present ...

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
CPCG06F18/2132G06F18/2135G06F18/2413
Inventor 张小瑞吴韵清孙伟宋爱国牛建伟
Owner NANJING UNIV OF INFORMATION SCI & 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

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