Unlock instant, AI-driven research and patent intelligence for your innovation.

Blurring kernel multi-scale iteration estimation method using directional derivative of image local structure

A technology of local structure and directional derivative, applied in image data processing, image enhancement, calculation and other directions, can solve the problem of unsatisfactory image restoration effect, and achieve the effect of reducing ringing effect, wide application prospect and strong continuity

Active Publication Date: 2015-07-01
NANJING UNIV OF SCI & TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method uses the edge information of the blurred image to perform shock filtering on the blurred edge, and then alternately iteratively estimates the blur kernel and restores the image. This method can quickly and better estimate the blur kernel, but for images with more textures, this method is not ideal for image recovery

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
  • Blurring kernel multi-scale iteration estimation method using directional derivative of image local structure
  • Blurring kernel multi-scale iteration estimation method using directional derivative of image local structure
  • Blurring kernel multi-scale iteration estimation method using directional derivative of image local structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention utilizes the fuzzy kernel multi-scale iterative estimation method of image local structure directional derivative, based on image decomposition and local structure directional derivative, solves the directional gradient vector field through multi-scale iterative, predicts fuzzy kernel and restores the image alternately, To achieve the purpose of fuzzy kernel estimation. The invention uses image decomposition to decompose the blind restoration image in the iterative process into a cartoon part and a texture part, obtains the direction gradient field of the cartoon part after shock filtering, uses the obtained gradient field to finely predict the blur kernel and the restored image alternately, and terminates the iteration Then get the final blur kernel.

[0040] Such as figure 1 As shown, the present invention utilizes the fuzzy kernel multi-scale iterative estimation method of the directional derivative of the image local structure, including the i...

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 blurring kernel multi-scale iteration estimation method using a directional derivative of an image local structure. The blurring kernel multi-scale iteration estimation method comprises inter-scale updating, intra-scale iteration estimation and inter-scale iteration termination judgment. A blurring kernel and a recovering image are estimated from coarse scale iteration to fine scale iteration. The intra-scale iteration estimation comprises the following steps: calculating an enhanced type direction gradient filed of a current scale; estimating a blurring kernel of the current scale rapidly; calculating a directional derivative approximate spectrum of a current image; and recovering an image of the current scale. Gradient information of image jumping edges is utilized, with a quick Fourier transform technology based on, the blurring kernel is quickly estimated in a small time complexity, and the blurring kernel multi-scale iteration estimation method can be used for conducting blind deblurring on various actual blurring images.

Description

technical field [0001] The invention belongs to the field of computer digital image processing, in particular to a fuzzy kernel multi-scale iterative estimation method using the directional derivative of the local structure of the image. Background technique [0002] Camera shake is a problem that has always plagued photographers. An unstable camera can cause blurred photos. Especially the small and high-resolution digital cameras that are popular at present are difficult to hold stably when they are in use due to the light weight of the body. Many photos capture fleeting precious moments that cannot be reproduced, and if there is a camera shake at this time, these precious moments are completely lost. Therefore, it is particularly important to work on finding ways to remove camera shake from a single photo. [0003] Image deblurring can be mainly divided into two categories: non-blind image deblurring and blind image deblurring. Image non-blind deblurring refers to the p...

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 王凯肖亮韦志辉
Owner NANJING UNIV OF SCI & TECH