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

Blurred kernel inversion method for blurred retouching images based on blurred deformation Riemann measure

A fuzzy kernel, image technology, applied in image enhancement, image data processing, instruments, etc., can solve the problems of trust crisis, defrauding public trust, and reducing the credibility of digital media.

Active Publication Date: 2014-08-20
NANJING TECH UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, edited images are used in advertisements, media, and the Internet to defraud public trust, reduce people's credibility in digital media, and trigger a crisis of trust

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
  • Blurred kernel inversion method for blurred retouching images based on blurred deformation Riemann measure
  • Blurred kernel inversion method for blurred retouching images based on blurred deformation Riemann measure
  • Blurred kernel inversion method for blurred retouching images based on blurred deformation Riemann measure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The technical scheme of the present invention is described in detail below in conjunction with accompanying drawing:

[0020] As a two-dimensional signal, an image can be represented in multiple transform domains, such as frequency domain (Fourier transform domain), Laplace domain, etc. The essence of Gaussian blur is image filtering. The Gaussian kernel function (normal distribution) is used to calculate the blur matrix, and the blur matrix is ​​convolved with the source image to perform blurring. The blur operation can be expressed in the time domain as the convolution of the source image I(x,y) and the Gaussian blur kernel function G(x,y,δ), as shown in the following formula.

[0021] I blur ( x , y ) = I ( x , y ) * G ( ...

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 blurred kernel inversion method for blurred retouching images based on blurred deformation Riemann measure and belongs to the technical field of digital image trusted authentication. Isometries before and after image blurring of logarithm Fourier domains are used, and blurred kernels are recovered from the blurred irrelevant amount before and after the image blurring through Riemann geodesic distance. According to the blurred kernel inversion method, Gaussian blur kernels can be recovered effectively and accurately from the blurred retouching images, the recovered Gaussian blur kernels can be used for manufacturing blurred images from source images and identifying whether the images are subjected to blurred retouching, and the method can be further used for recovering 'clean' images from the blurred images.

Description

technical field [0001] The invention discloses a fuzzy kernel inversion method for a fuzzy retouched image based on a fuzzy invariant Riemann measure, and belongs to the technical field of digital image credible authentication. Background technique [0002] With the rapid development of image acquisition and image editing technology, digital images have been integrated into modern people's lives. Using image editing software, it is easy to retouch and synthesize existing images to create pleasing pictures. These beautifully edited images are mostly used on the Internet, digital media documents, social media, etc., and play an irreplaceable role in expressing individuality, beautifying media space, and enriching people's spiritual communication. At the same time, edited images are used in advertisements, media, and the Internet to defraud the public's trust, reduce people's credibility in digital media, and trigger a crisis of trust. Therefore, it is very urgent to study dig...

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): G06T5/00
Inventor 杜振龙金雨霏李晓丽
Owner NANJING TECH UNIV
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