Density-adaptive image salt-pepper noise switching filtering method

A salt and pepper noise, self-adaptive technology, applied in the direction of image communication, color TV parts, TV system parts, etc., to achieve the effect of protecting edge images

Inactive Publication Date: 2011-11-23
NANJING UNIV OF INFORMATION SCI & TECH
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there is a lack of a fully automatic adaptive noise density salt and pepper noise filtering 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
  • Density-adaptive image salt-pepper noise switching filtering method
  • Density-adaptive image salt-pepper noise switching filtering method
  • Density-adaptive image salt-pepper noise switching filtering method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Such as figure 1 Shown, a kind of self-adaptive image salt and pepper noise switching filter method of the present invention comprises the following steps:

[0026] Step 1: Use training images with different noise densities to train two neural networks for accurately detecting noise locations.

[0027] Set a noise density threshold T1 (optimally 0.25), the threshold is between 0 and 1, when training images with noise density lower than the threshold, use a 3*3 window, and use a window of 3*3 for images higher than the threshold When training the training image, a 5*5 window is used. Obtain the pixel value in the center of the window, the median value of all pixels in the window, and the ROLD statistic as the input of the neural network, and calculate the possibility y(i, j) of each pixel in the training image as a noise point. Since the value of the possibility is a continuous quantity, it needs to be determined whether it is a noise point or not during post-processin...

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 density-adaptive image salt-pepper noise switching filtering method, which comprises the following steps of: training a plurality of neural networks adaptable to the accurate detection of noise positions under certain noise densities by using training images with different noise densities; rapidly and roughly evaluating the salt-pepper noise densities of the images; selecting corresponding neural networks according to the evaluated salt-pepper noise densities to perform accurate noise detection on the images; and performing window-adaptive switch weighted mean filtering on the images according to the accurately detected noise positions. By the method, the magnitudes of the noise densities can be automatically judged, and the accurate noise detection can be performed by adopting the corresponding neural networks for the densities with different magnitudes.

Description

technical field [0001] The invention relates to an image noise filtering method, in particular to an adaptive density image salt and pepper noise switching filtering method. Background technique [0002] Salt and pepper noise is a kind of noise that is often introduced in the process of image transmission and processing due to various reasons, which degrades the quality of the image and affects the subsequent processing of the image. At present, median filtering is the most commonly used processing method, and its operation is simple and fast. Its filtering effect is affected by the size of the filtering window, which may cause blurring of the image and loss of important details. The idea of ​​the switching median filtering method is to first judge whether a certain point may be a noise point, and if so, carry out the corresponding median filtering process, if not, keep the original value unchanged, so as to reduce the distortion of the image. Judgment, but did not propose ...

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): H04N5/213
Inventor 胡凯曹晶晶陶瑞莲
Owner NANJING UNIV OF INFORMATION SCI & TECH
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