Image filling method, terminal equipment and storage medium

A technology in images and images, applied in the field of image processing, can solve problems such as staircase effects, achieve good sparsity, improve iterative algorithms, and avoid time steps.

Inactive Publication Date: 2019-08-02
MINNAN NORMAL UNIV
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with other inpainting models based on variational PDE, the TV inpainting equation is a second-order equation, so its numerical format is simple and has good convergence. In addition, the TV inpainting model can remove noise while inpainting the image, and Keep the edge of the image, but TV can only effectively approximate the slice constant function, so the ladder effect often appears in its repair results

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 filling method, terminal equipment and storage medium
  • Image filling method, terminal equipment and storage medium
  • Image filling method, terminal equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] Embodiment 1 of the present invention provides a generalized full variational image filling method based on the Lp pseudo-norm, such as figure 1 As shown, it is a schematic flow chart of the image denoising method described in Embodiment 1 of the present invention, and the method may include the following steps:

[0063] S1: Input the image G to be restored.

[0064] Such as figure 2 as shown, figure 2 (a) is the original image without noise, figure 2 (b) is a local enlarged image of the original image, which is figure 2 (c) is an image with Gaussian noise, figure 2 (d) is a partial enlarged view of an image with Gaussian noise, and the observation image input in this embodiment is figure 2 (c) The image with Gaussian noise is restored, and the restored image is as close as possible to the original image without noise.

[0065] S2: Initialize the image model, set parameters: F (0) = G, V (0) =0, m (0) = 0, N (0) =0, δ, μ, p, τ, β>0, number of iterati...

Embodiment 2

[0129] The present invention also provides an image filling terminal device, which includes a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the implementation of the present invention is realized. Steps in the above method embodiment of Example 1.

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 provides an image filling method, terminal equipment and a storage medium. on the basis of second-order generalized total variation, total variation based on an L1 norm is popularized tobe based on an Lp pseudo norm for describing a fidelity item, and compared with the L1 norm, one degree of freedom is increased, and sparse gradient information can be better described. In order to accelerate the convergence speed of the model, the first-order primal-dual algorithm is used for iterative computation, the algorithm avoids the time step length, and the effect of accelerating convergence is achieved by effectively using alternative iteration.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to an image filling method, terminal equipment and a storage medium. Background technique [0002] Digital image restoration is a hot issue in digital image processing and computer graphics, and ancient book image filling is one of the problems to be solved urgently. It has high application value for cultural relics protection and digitization of ancient book images. [0003] In daily life and scientific research, we often encounter image information defects, such as image damage, occlusion removal, and so on. How to restore these missing or occluded information has become a problem that people pay more and more attention to. Digital image restoration technology refers to the use of undamaged image information to fill in the lost or damaged part of the digital image according to certain rules, so that the restored image is close to or achieves the visual effect of the origin...

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): G06T5/00
CPCG06T5/002G06T5/005
Inventor 王灵芝陈颖频柯素玲
Owner MINNAN NORMAL UNIV
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