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

Image denoising method based on ELM

An image and original image technology, applied in the field of fast image denoising based on ELM, can solve the problems of a large amount of time spent and a long training process, and achieve the effects of improving training speed, convenient application, and reducing training time consumption

Inactive Publication Date: 2015-08-05
ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF2 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method has the following disadvantages: the training process is long, and it takes a lot of time to train (days or even months)

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 denoising method based on ELM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0050] The image denoising method based on ELM of the present embodiment, comprises the steps:

[0051] (1) Construct the basic network according to the size of the image to be processed (note that the size of the image to be processed is M×N).

[0052] Such as figure 1As shown, the basic network of this embodiment is a basic feed-forward neural network, including three layers, namely an input layer, a feature extraction layer and an output layer.

[0053] The input layer has M*N nodes, and inputs the pixel information of the image to be processed; the feature extraction layer has H nodes (H is usually 1000~1500, and H=1200 in the present embodiment); the output layer has M*N nodes, Output the image processed by this network in size M*N, that is, the image after denoising of the image to be processed.

[0054] In the feedforward neural net...

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 denoising method based on an ELM. The method comprises the following steps: establishing a basic feedforward neural network according to size of a to-be-processed image; aimed at the basic feedforward neural network, establishing a training sample set; using the training sample set to train the basic feedforward neural network based on an ELM method, to obtain a trained neural network; and inputting the to-be-processed image to the trained neural network, and the corresponding output being a de-noised image. Through customizing the training set and using the elm, the method trains connection parameters, so a training process can be completed rapidly, thereby greatly improving training efficiency. The method establishes the network training set according to noise types of an application scene, just the network training set established aimed at the application scene is needed to obtain the trained neural network aimed at different noise types to eliminate noise of an image. The method can be conveniently applied in different noise scenes.

Description

technical field [0001] The invention relates to the technical field of computer image processing, in particular to an ELM-based fast image denoising method. Background technique [0002] Image denoising is a prerequisite for many image processing, therefore, image restoration and noise removal has always been a hot issue in the field of image processing. In the field of image restoration, the difficult problem is to remove the noise while retaining the original information structure. To achieve this goal, three main categories of methods have been proposed for decades to solve this problem: spatial domain methods, transformed domain methods, and learning-based methods. [0003] The more representative ones in the spatial domain method are BF (Bilateral filter, bilateral filter method), NLM (non-local means, non-local mean method). BF uses the correlation of adjacent positions and the correlation of adjacent color gamuts to eliminate image noise; NLM starts from the overall...

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): G06T5/00
Inventor 林志洁
Owner ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
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