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

An Image Gradient Method Based on Shape Interpolation

An interpolation and image technology, which is applied in the field of image gradient based on shape interpolation, can solve the problems of maintaining and not being able to directly apply complex and detailed images, achieve natural and smooth gradient effects, enhance practicability and convenience, and avoid local distortions Effect

Active Publication Date: 2019-04-23
ZHEJIANG GONGSHANG UNIVERSITY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the shape interpolation method can effectively avoid the distortion of the shape, thereby maintaining the geometric characteristics of the described object, the shape interpolation method is usually only suitable for vector graphics with simple outlines, and cannot be directly applied to images with more complex and rich details.

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
  • An Image Gradient Method Based on Shape Interpolation
  • An Image Gradient Method Based on Shape Interpolation
  • An Image Gradient Method Based on Shape Interpolation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Such as figure 1The illustrated embodiment is an image gradient method based on shape interpolation, including a source image and a target image. Given a source image and a target image, the user can place an open or closed curve (called " Characteristic curve"), specify and align the geometric features in the source image and the target image. Geometric features generally refer to internal features such as eyes, nose, eyebrows, hands and simple external contours.

[0036] The source image includes the set of source characteristic curves The target image includes the set of target characteristic curves The method comprises the steps of:

[0037] Step 100, Construct and The line appearance model of ;

[0038] Pick Each characteristic curve in The center of gravity of the curve acts as a proxy for the position of the curve in space; the The center of gravity of each characteristic curve is connected with the center of gravity of other characteristic curves ...

Embodiment 2

[0064] This embodiment contains all the content in Embodiment 1. For the source image and the target image, this embodiment uses a regular quadrilateral grid to approximate, and embeds the source image into the grid as a texture, and embeds the target image into the grid as a texture. In the grid, in the process of image gradient, the calculation is performed according to the position of each grid point, instead of calculating the deformation position of each pixel of the image, making full use of GPU resources, greatly reducing the amount of calculation of the program, saving computing costs, and realizing Real-time performance of image deformation.

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 an image gradient method based on shape interpolation, which includes a source image and a target image. The source image includes a source characteristic curve set. The invention uses the intermediate characteristic curve as a constraint to calculate the optimal point of any point in the source image and the target image. The deformation position realizes the geometric deformation of the source image and the target image relative to the intermediate feature curve, and realizes the alignment and fusion of the corresponding geometric features in the source image and the target image. The present invention has the characteristics of being able to generate more natural and smooth transition sequences and gradient effects, further enhancing the practicality and convenience of image gradient technology.

Description

technical field [0001] The invention relates to the technical field of two-dimensional image deformation, in particular to an image gradient method based on shape interpolation. Background technique [0002] With the development of digital media technology, many digital entertainment applications have emerged, such as movies, networks, games and so on. Image gradients are an important part of these applications. Therefore, in order to further promote and popularize these applications, it is necessary to design and provide corresponding tools to make the effect of image gradients more realistic and natural, and to allow ordinary users to intuitively and easily create image gradients. [0003] Image morphing technology (Image morphing) is developed on the basis of computer graphics and digital image processing. It mainly extracts the corresponding geometric features in two images, and then uses geometric transformation to fuse their features. Their colors are mixed and inter...

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): G06T3/00
CPCG06T3/18
Inventor 杨文武黄冠华
Owner ZHEJIANG GONGSHANG UNIVERSITY
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