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

Computer-aided disordered needlework manufacture method using genetic algorithms

A computer-aided and genetic algorithm technology, applied in the field of computer-aided random stitch embroidery, can solve the problems of complex dependencies, inconsistent brush stroke model definitions, and difficulty in establishing cross-stitch display function relationships, etc.

Inactive Publication Date: 2013-09-11
NANJING UNIV
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these attributes of cross needles are often related to multiple image features, and the dependencies between them are complex. It is difficult to establish the display function relationship between the cross needle attributes and image features. Therefore, it is necessary to define the drawn needle The evaluation function of the trace scheme image uses a random search method such as a genetic algorithm to solve this problem.
However, the method used in the existing work only involves a single image feature, and the evaluation method of the drawing result does not meet the evaluation requirements of random stitch embroidery, and its definition of the stroke model does not conform to the cross stitch as the basic method in random stitch embroidery. Embroidery Unit Requirements

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
  • Computer-aided disordered needlework manufacture method using genetic algorithms
  • Computer-aided disordered needlework manufacture method using genetic algorithms
  • Computer-aided disordered needlework manufacture method using genetic algorithms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The invention discloses a method for making computer-aided random stitch embroidery using a genetic algorithm, such as figure 1 As shown, the main flow of each embodiment part is introduced respectively below:

[0043] 1. Image feature extraction

[0044] The present invention extracts the corresponding image features as the basis for subsequent random stitch embroidery stitch sequence generation. As described in step 2, the image features extracted by the present invention mainly include object area, area vector field and image saliency feature The three are described step by step below.

[0045] 1.1 Object Region Extraction

[0046] In the embroidery process of chaotic stitch embroidery, the embroidery method is different for different object areas. In the foreground area, the stitch density is higher and the embroidery thread length is shorter. Therefore, in the process of making random stitch embroidery by computer, it is necessary to divide the image into differ...

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 computer-aided disordered needlework manufacture method using genetic algorithms. The method includes the steps of firstly, using an input color image as a reference image, and using imaging segmentation, area vector field extraction and image consistency line extraction to extract image features such as different object areas, area vector fields and image saliency; secondly, defining three-layer parameterized knitting models including each embroidery thread, each cross needle and cross needle arrangement according to features of disordered needlework, and describing a method for obtaining embroidery thread collection according to the parameterized knitting models; thirdly, using the genetic algorithms to obtain disordered needlework needle tracking sequence according to knitting model parameters determined according to image features; fourthly, converting needle tracking coordinates into coordinates required by a computerized embroidery machine, and inputting the coordinates into the computerized embroidery machine to obtain the corresponding disordered needlework. The method is significant to mechanical standardized production of the disordered needlework.

Description

technical field [0001] The invention relates to a method for making computer-aided random stitch embroidery, which belongs to the technical fields of computer image processing and computer graphics. Specifically, this method defines and constructs a stitch model suitable for random stitch embroidery, and extracts image features from color images, and uses genetic algorithm to automatically determine the stitch model parameters based on image features to complete the random stitch embroidery production process . Background technique [0002] Random stitch embroidery is an embroidery art created by Changzhou artist Professor Yang Shouyu in the 1930s. It reformed the traditional embroidery method and combined it with the brushstrokes and colors of Western paintings. Embroidery expression method. Random stitch embroidery is free in needle movement, flexible in color use, and has a large room for display. It changes the traditional embroidery stitch method of "closely connectin...

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): G06F17/50G06K9/46
Inventor 孙正兴杨克微周杰周俊昊
Owner NANJING UNIV
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