Global image edition propagating method and system thereof

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

Active Publication Date: 2015-08-12
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF1 Cites 4 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
  • Global image edition propagating method and system thereof
  • Global image edition propagating method and system thereof
  • Global image edition propagating method and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

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

[0053] S1. Reading in the original image and editing by the user.

[0054] Obtain the original image I that the user expects 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 of the original image I is used as the marked editing area I p∈G Indicates that the area of ​​the original image I not covered by the stroke image G is the unmarked edited area Represents; among them, p is the pixel on the original image I.

[0055] S2. Calculate pixel block matching information.

[0056] For unmarked editing regions Middle pixel i, get pixel block A corresponding to pixel i i , in the calibration editing area I p∈G Get with pixel block A i The pixel blo...

Embodiment 2

[0062] In a specific embodiment of the present invention, step S2 in the foregoing embodiment 1 uses random communication block matching in the defined mark editing area I p∈G Get pixel block A i closest matching pixel block Since step S1 and step S3 in this embodiment are the same as the processing process in the above-mentioned embodiment, they will not be described in detail here, and step S2 specifically includes:

[0063] S21. Initialization: Obtain the unmarked editing area Medium pixel i(x i ,y i ) corresponding to the pixel block A i , randomly select the calibration editing area I p∈G Middle pixel i'(x i' ,y i' ) corresponding to the pixel block B i' as pixel block A i The initial matching pixel block of

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

[0065] S221. Select N different search radii w...

Embodiment 3

[0075] In a specific embodiment of the present invention, the step "local area optimization" is also included between step S21 and step S22 in the second embodiment, which is used to optimize the initial matching pixel block randomly obtained in step S21 Perform local area optimization to obtain more similar initial matching pixel blocks Since step S1 and step S3 in this embodiment are the same as the processing process in the above-mentioned embodiment, they will not be described in detail here, and step S2 specifically includes:

[0076] S21. Initialization: Obtain the unmarked editing area Medium pixel i(x i ,y i ) corresponding to the pixel block A i , randomly select the calibration editing area I p∈G Middle pixel i'(x i' ,y i' ) corresponding to the pixel block B i' as pixel block A i The initial matching pixel block of

[0077] S22. Local area optimization: detecting initial matching pixel blocks Is there any adjacent pixel block with pixel block A i If...

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 edition propagating method and a system thereof. The global image edition propagating method comprises the steps of S1, acquiring an original image and a pen touch image which is obtained through user edition, wherein the area which is covered by the pen touch image in the original image is a calibrated editing area, and the area which is not covered by the pen touch image in the original image is a non-calibrated editing area; S2, for a pixel point I in the non-calibrated editing area, acquiring a pixel block Ai which corresponds with the pixel point I, and obtaining a pixel block Bi' with a highest similarity with the pixel block Ai in the calibrated editing area as an optimal matching pixel block of the pixel block Ai; and S3, propagating the user edition which is covered by the target pixel point i' which corresponds with the optimal matching pixel block Bi' to the target pixel point i that corresponds with the pixel block Ai. According to the global image edition propagating method, a propagating solution is established based on image global random pixel block matching information, thereby propagating an existing edition solution to the global image quickly, accurately and effectively.

Description

technical field [0001] The invention relates to the field of digital image processing, in particular to a method and system for global image editing and dissemination. Background technique [0002] As digital computational photography matures, researchers are digging deeper into high-level editing techniques for digital images and videos to meet increasing demands. In the framework of the propagation-based image editing domain, users specify different categories of sparse edited regions, which are automatically propagated to adjacent regions in the feature space by a specific propagation method. According to the result after propagation, the color, structure, chroma and other related information of the image can be modified. [0003] Traditional methods of image editing and dissemination include manual selection and optimization-based dissemination. During image processing, the user specifies a region of interest (ROI) and generates a mask, operating on different masks. T...

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): G06T7/00G06T5/00
Inventor 王好谦郭震远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