A global image editing propagation method and system

An image editing and global technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of poor communication effect and low real-time performance

Active Publication Date: 2018-05-22
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a method and system for global image editing and dissemination to solve the technical problems of poor dissemination effect and low real-time performance in the prior art

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
  • A global image editing propagation method and system
  • A global image editing propagation method and system
  • A global image editing propagation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] The present invention proposes a global image editing and dissemination method, see figure 1 It is a real-time global image editing and dissemination flow chart of the first embodiment of the present invention, including the following steps:

[0053] S1. Read in the original image and edit by the user.

[0054] Obtain the original image I that the user desires to edit and the stroke image G composed of different color marks (ie strokes) in the original image I. The area covered by the stroke image G in the original image I is used to mark the editing area I p∈G Indicates that the area of ​​the original image I that is not covered by the stroke image G is used as an uncalibrated editing area Means; where p is the pixel on the original image I.

[0055] S2. Calculate pixel block matching information.

[0056] For unmarked editing area Middle pixel point i, get pixel block A corresponding to pixel point i i , In the calibration edit area I p∈G Get and pixel block A i The most ...

Embodiment 2

[0062] In a specific embodiment of the present invention, step S2 in the first embodiment described above uses random communication block matching in the defined mark editing area I p∈G Get pixel block A i Closest matching pixel block Since steps S1 and S3 in this embodiment are the same as the processing procedures in the foregoing embodiment, they will not be repeated here, and step S2 specifically includes:

[0063] S21. Initialization: Get the uncalibrated editing area Middle pixel i(x i ,y i ) Corresponding pixel block A i , Randomly select calibration editing area I p∈G Mid-pixel i'(x i' ,y i' ) Corresponding pixel block B i' As pixel block A i Initial matching pixel block

[0064] S22. Global area search: in the calibration edit area I p∈G And search pixel block A within multiple different limited radius i The best matching pixel block B i' , Including the following steps:

[0065] S221. Select N different search radii w 1 ,...,W N , These N search radius w 1 ,...,W N Dec...

Embodiment 3

[0075] In a specific embodiment of the present invention, the step S21 and step S22 in the foregoing second embodiment further includes a step of "local area optimization", which is used for matching the initial matching pixel block randomly obtained in step S21. Perform local area optimization to get a more similar initial matching pixel block Since steps S1 and S3 in this embodiment are the same as the processing procedures in the foregoing embodiment, they will not be repeated here, and step S2 specifically includes:

[0076] S21. Initialization: Get the uncalibrated editing area Middle pixel i(x i ,y i ) Corresponding pixel block A i , Randomly select calibration editing area I p∈G Mid-pixel i'(x i' ,y i' ) Corresponding pixel block B i' As pixel block A i Initial matching pixel block

[0077] S22. Local area optimization: detecting initial matching pixel blocks Is there any adjacent pixel block with pixel block A i If there is a pixel block with higher similarity, use this...

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 global image editing and dissemination method and system. The dissemination method includes the following steps: S1. Obtaining an original image and a stroke image edited by a user, the area covered by the stroke image of the original image is the calibration editing area, and the original image is not The area covered by the stroke image is the uncalibrated editing area; S2, for the pixel point i in the uncalibrated editing area, obtain the pixel block Ai corresponding to the pixel point i, and obtain the pixel block Bi with the highest similarity with the pixel block Ai in the calibrated editing area ' as the optimal matching pixel block of the pixel block Ai; S3. Propagating the user edit covered at the target pixel point i' corresponding to the optimal matching pixel block Bi' to the target pixel point i corresponding to the pixel block Ai. The method establishes a propagation scheme based on the global random pixel block matching information of the image, and propagates the existing editing scheme to the global image quickly, accurately and effectively.

Description

Technical field [0001] The present invention relates to the field of digital image processing, in particular to a global image editing and dissemination method and system. Background technique [0002] With the maturity of digital computing photography, researchers have dig deep into the high-level editing technology of digital images and videos to meet the increasing demand. In the image editing domain framework based on propagation, users specify different types of sparse editing regions, which are automatically propagated to adjacent regions in the feature space through a specific propagation method. According to the results of the dissemination, the color, structure, and chromaticity of the image can be modified. [0003] Traditional image editing and dissemination methods include manual selection and optimization-based dissemination. In the image processing process, the user specifies a region of interest (ROI) and generates a mask, and operates on different masks. This met...

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): G06T7/231G06T5/00
Inventor 王好谦郭震远崔宇浩李凯张永兵王兴政戴琼海
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA 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