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

Edge-preserving self-adaptive weighted filtering method for natural scene images

A natural scene image, adaptive weighting technology, applied in the field of image processing

Active Publication Date: 2012-10-03
SERVICE CENT OF COMMLIZATION OF RES FINDINGS HAIAN COUNTY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] Aiming at the deficiencies of the existing image filtering technology, the present invention provides an adaptive weighted filtering method for natural scene images while maintaining image brightness / color edge characteristics and depth edge characteristics

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
  • Edge-preserving self-adaptive weighted filtering method for natural scene images
  • Edge-preserving self-adaptive weighted filtering method for natural scene images
  • Edge-preserving self-adaptive weighted filtering method for natural scene images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with the drawings.

[0049] Such as figure 1 As shown, an edge-preserving natural scene image adaptive weighted filtering method, its specific steps are as follows:

[0050] Step (1) According to the standard deviation of the Gaussian filter , Calculate the Gaussian template, the radius of the Gaussian template . The Gaussian template calculation method is a mature technology.

[0051] Step (2) uses the dark channel prior method proposed by K. He et al. to obtain the depth cues in the original image, and normalize it to [0,255] to generate a depth prior image. The original image is a natural scene image.

[0052] Step (3) Calculate the spatial proximity weight of each coordinate point on the Gaussian template.

[0053] The calculation method of the spatial proximity weight is specifically:

[0054] For the coordinate points in the Gaussian template , The nearest neighbor distance from the coordinate point t...

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 an edge-preserving self-adaptive weighted filtering method for natural scene images. The method comprises the following steps of firstly, calculating a Gaussian template according to the standard deviation of a Gaussian filter, obtaining depth clues in an original image by adopting a dark channel transcendental method, and carrying out normalization to form a depth transcendental image; secondly, calculating a spacial adjacent weight of each coordinate point on the Gaussian template, and calculating the luminance / color similarity weights of two pixels on the original image; calculating the depth difference weight between the two pixels on the original image, and calculating a self-adaptive weighted filtering template of the center of the template corresponding to the pixels; and finally, calculating a self-adaptive weighted filtering result of each pixel in the original image. The method takes into consideration on the characteristic that the sensitivities of eyes to luminance difference and color difference are different during the calculation of the luminance / color similarity weights, so that the method is applicable to biological models.

Description

Technical field [0001] The invention belongs to the field of image processing, and in particular relates to a natural scene image adaptive weighted filtering method that simultaneously maintains image brightness / color edge characteristics and depth edge characteristics. Background technique [0002] Image filtering is a key technology in image preprocessing algorithms. This technology implements local neighborhood operations in the image space by constructing a filter template, such as arithmetic mean filtering, Gaussian smoothing filtering, Laplacian filtering, etc. The purpose is to reduce noise in the image to improve image quality, or It is to filter out the high frequency components of the image to establish the image scale space. This technology is widely used in most image processing algorithms such as image segmentation, image restoration, image feature extraction, image understanding and analysis, and image compression. [0003] The idea of ​​image filtering originates f...

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 Patents(China)
IPC IPC(8): G06T5/10G06T5/00
Inventor 周文晖楼斌孙志海张桦韦学辉戴国骏
Owner SERVICE CENT OF COMMLIZATION OF RES FINDINGS HAIAN COUNTY
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