Supercharge Your Innovation With Domain-Expert AI Agents!

Image vectorization system and method based on boundary segmentation algorithm

A segmentation algorithm and vectorization technology, used in image enhancement, image analysis, image data processing, etc., can solve the problem of insufficient fine-grained vectorization of raster images, and achieve the effect of easy construction of vector graphics and later evaluation.

Active Publication Date: 2020-07-28
SHANGHAI UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that the existing traditional method is not fine enough when vectorizing raster images, and to provide an image vectorization system and method based on boundary segmentation algorithm

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 vectorization system and method based on boundary segmentation algorithm
  • Image vectorization system and method based on boundary segmentation algorithm
  • Image vectorization system and method based on boundary segmentation algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] like figure 1 Shown, a kind of image vectorization system based on boundary segmentation algorithm, comprises area segmentation module, boundary detection module, boundary fitting module and SVG integration module; Described area segmentation module utilizes the method of statistical area fusion to divide image into areas, It is convenient for the following modules to process the image; the boundary detection module expands the pixels of the image and generates blank pixel blocks, boundary pixel blocks and intersecting pixel blocks, and finally inputs the sub-pixel image; the boundary fitting module converts the sub-pixel image The boundary is extracted and uses the Catmull-Rom spline to fit the cubic Bezier curve to represent the boundary C(u); the SVG integration module outputs the boundary C(u) output by the boundary fitting module and the sub Summarize processing of pixel images and segmented images with color attributes to generate vector graphics files in SVG form...

Embodiment 2

[0023] like figure 2 As shown, an image vectorization method based on the boundary segmentation algorithm, using the above-mentioned image vectorization system based on the boundary segmentation algorithm, the specific operation steps are as follows:

[0024] (1) The image M is processed by the region segmentation module. The main method is the statistical region fusion method. First, the image pixels are collected, and each pixel channel in the image is divided into a region, and the average value of each pixel channel is defined as M.

[0025] (2) Traverse each pixel channel, calculate and store the difference f(p, p') between the adjacent pixel channels p and p' (the difference value takes the difference f in the three channels of R, G, and B a (p, p′) max):

[0026] f(p,p')=max a∈R，G，B f a (p, p′) (1)

[0027] (3) According to the calculated difference value f, define the region whose difference is lower than the previously set average value as similar regions and mer...

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 vectorization system and method based on a boundary segmentation algorithm. The system comprises a region segmentation module, a boundary detection module, a boundaryfitting module and an SVG integration module. The operation method comprises the following steps that an image is divided into different areas; a sub-pixel image is generated by expanding a blank pixel block, a boundary pixel block and an intersection pixel block, the boundary of the sub-pixel image is extracted, a cubic Bezier curve is fitted by using a Catmull-Rom spline to represent a boundaryC(u), and finally an SVG format file is generated by integration. Compared with the prior art, the method has the advantages that the boundaries can be better divided, the boundaries of different areas can be accurately determined and extracted, and vector diagram construction and later evaluation are easy.

Description

technical field [0001] The invention belongs to the technical field of raster image vectorization processing, and specifically relates to an image vectorization system and method based on a boundary segmentation algorithm. Background technique [0002] The images displayed by the computer are divided into two categories: bitmap and vector graphics. Bitmap is also called bitmap image or raster image, which is composed of single pixels. Image vectorization is a hot topic in recent digital image processing. Vector images have many advantages: first, vector images are composed of simple geometric primitives, which represent compact representations and occupy less storage space; second, vector images are easy to edit and When editing a vector image, you only need to modify the parameter information of the corresponding geometric primitives when performing operations such as rotation, stretching, and translation; The display quality of the vector image can be scaled to maintain 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
IPC IPC(8): G06T7/11G06T7/90
CPCG06T7/11G06T7/90G06T2207/10024
Inventor 张新鹏李劲松冯国瑞
Owner SHANGHAI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com