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

Figure image processing method for preventing background deformation

A technology of image processing and deformation map, applied in the field of image processing, can solve the problems of small distance weight, meaningless distance weighting, loss of discrimination, etc.

Active Publication Date: 2020-04-17
CHENDU PINGUO TECH CO LTD
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In an application with a large unknown area, this method will make the distance weight in the center of the unknown area very small and the distance weights of a considerable part of its surroundings are so small that the discrimination is lost, resulting in the distance weighting of the area with a large distance become meaningless

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
  • Figure image processing method for preventing background deformation
  • Figure image processing method for preventing background deformation
  • Figure image processing method for preventing background deformation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] A character image processing method for preventing background deformation, the method comprising the following steps:

[0071] Step 1: Obtain the original image of the character image, such as figure 2 As shown, the original image of the character image is segmented to obtain the mask image of the original image, as shown in image 3 shown;

[0072] Among them, there are many methods for obtaining the original picture of the person image, which may be taking a selfie with a mobile device with a camera function, or obtaining a selfie image from a storage medium. The present invention does not limit the method for obtaining the original picture of the person image.

[0073] The mask image of the original image is artificially a single-channel binary grayscale image. Let the mask image of the original image be M here, then the part of M=1 is the portrait area, and the area of ​​M=0 represents the background area.

[0074] Step 2: Carry out deformation and slimming proc...

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 a figure image processing method for preventing background deformation. The method comprises the following steps: 1, segmenting a figure image original image to obtain an original image masking image; 2, deforming the two images to obtain an original image deformation image and an original image mask deformation image; 3, filtering the figure image original image layer by layer and generating a masking pattern to obtain an image pyramid; carrying out expansion and distance transformation on the masking pattern; 4, calculating the gradient of an unknown region and carrying out SVD decomposition; 5, performing neighbor search, cross search and limited random search in sequence from the top layer of the pyramid to obtain an optimal matching block position; 6, filling the optimal matching block position of each unknown pixel position; 7, repeating the steps 5 and 6, wherein the updated pyramid bottom layer is a filling result graph; and 8, synthesizing the original image deformation image, the original image mask deformation image and the filling result image to obtain a character image with an undeformed background. According to the invention, the nature of theimage background can be maintained while the figure image is slimmed.

Description

technical field [0001] The invention belongs to image processing technology, in particular to a character image processing method for preventing background deformation. Background technique [0002] People hope that they can present a beautiful and unique image on social networks, and they always hope that their photos are more beautiful than themselves in reality. Portrait beautification has become a standard function of image retouching applications, but the current image retouching applications mainly focus on portrait skin beautification, and there are not many applications that can slim down people's images, and the effect after slimming is not satisfactory. [0003] The Patch-Match algorithm is a widely used algorithm when searching for unknown pixel positions in an image. This algorithm uses other areas in the image to restore the unknown edge area. However, this algorithm is likely to cause disorder in the spatial structure of the image, resulting in distortion and ...

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): G06T3/00G06T7/155
CPCG06T7/155G06T2207/30196G06T3/053Y02D10/00
Inventor 黄亮徐滢
Owner CHENDU PINGUO TECH CO LTD
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