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

Image restoration method based on BSCB model

An image and model technology, applied in the field of computer image restoration, which can solve the problem of insufficient information in non-stained areas

Inactive Publication Date: 2018-06-01
DALIAN UNIV OF TECH
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to provide a color image initialization model based on the BSCB model, which can solve the shortcomings of existing algorithms that consider insufficient information in non-defaced areas, and achieve better image restoration effects and restorations through further data processing. rate

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 restoration method based on BSCB model
  • Image restoration method based on BSCB model
  • Image restoration method based on BSCB model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the specific implementation manners of the present invention will be further described in detail below.

[0021] In this paper, on a PC with Matlab7.0, Pentium4, 2.4GHz, and 256M memory, it uses pure white initialization, related random initialization and the "inverse proportional distance weight initialization" algorithm proposed in this paper, and then combines the repair algorithm of the BSCB model to perform color image patched. In this method, the color image is divided into three channels of R, G, and B, which are respectively processed by the model, and then recombined to obtain the inpainted image. In order to compare these three initialization algorithms subjectively, the repaired effects of the three algorithms and the visual effects after initialization are compared under the same number of iterations. At the same time, in order to compare the visual effects of ...

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 belongs to the technical field of computer image restoration and relates to an image restoration method based on a BSCB model. The model takes account of a relationship between the correlation and the distance between pixels in eight directions, and uses the surrounding pixels to pre-estimate the damaged pixels. An inversely proportional relationship between inter-pixel distance andcorrelation is introduced. Compared with other image restoration schemes based on the BSCB model, the algorithm used in the invention is shorter than the relevant random initialization time when achieving the same mean square error. With the same number of iterations, the algorithm of the invention makes a better image restoration effect. The invention provides a new computer image restoration method which can improve the restoration efficiency and obtain a better restoration effect, and provides a new solution for image restoration.

Description

technical field [0001] The invention belongs to the technical field of computer image restoration, and relates to a color image restoration algorithm based on the BSCB (the initials of the four authors who proposed the model) model. Background technique [0002] Image restoration (Image Inpainting) technology originally originated from the reproduction of works of art. Precious works of art have changed hands many times, long-term exposure, weathering and other reasons have caused the ink to fall off and be partially damaged. In the past, image restoration work was performed by professionals with rich restoration experience to manually fill in damaged images, so that the restored works could be as consistent as possible with the original style. [0003] Today, many precious cultural relics, pictures, classic movies, and archival photos are preserved for a long time through scanning technology. Scratches, creases, stains, and missing areas of art paintings are at high risk ...

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
CPCG06T5/77G06T5/70
Inventor 王智慧王宁李建军李豪杰罗钟铉
Owner DALIAN UNIV OF TECH