Fabric pattern matching method and system based on color diagram and vector diagram

A matching method and vector graphics technology, applied in the field of image processing, can solve the problems of matching result matching failure, low efficiency, slow speed, etc., and achieve the effect of improving matching accuracy, reducing labor costs, and improving matching efficiency.

Pending Publication Date: 2021-07-13
ZHEJIANG SCI-TECH UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the prior art, for the matching of textile images, manual segmentation is used to segment the parts of the textile images to be matched, which is very slow and inefficient. Therefore, the speed of textile image matching is greatly slowed down, and it cannot meet the needs of enterprises. Requirements for Rapid Textile Image Matching
In addition, in the current process of textile image matching, the image of the textile to be matched is prone to tilting. Therefore, even if the textile image to be matched belongs to a qualified product, the final matching result will probably fail to match. Accuracy cannot be guaranteed
Finally, in the current textile image matching process, it is often necessary to match all the pixels in the image one by one to obtain the final result of whether the matching is successful. It is impossible to end the matching in advance and output the matching result. The efficiency of such a matching process lower

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
  • Fabric pattern matching method and system based on color diagram and vector diagram
  • Fabric pattern matching method and system based on color diagram and vector diagram
  • Fabric pattern matching method and system based on color diagram and vector diagram

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] refer to figure 1 , the present embodiment provides a fabric pattern matching method based on a color map and a vector diagram, comprising steps:

[0060] S1, input template graph, and template graph is preprocessed, to obtain the preprocessing template graph A (refer to figure 2 As shown, it is a fabric diagram);

[0061] S2. Input the picture to be matched, and remove the number of color channels of the picture to be matched to convert the picture to be matched into grayscale picture B;

[0062] S3. Calculate the offset angle θ of the largest circumscribed ellipse of the grayscale picture B relative to the horizontal axis, and keep the grayscale picture B horizontal through the affine transformation matrix;

[0063] S4. Randomly select the ROI region S in the gray-scale image B, crop the region S and extract the contour to obtain the contour map L;

[0064] S5. Remove the interference features in the contour map L to obtain the template map M to be matched;

[00...

Embodiment 2

[0096] The difference between this embodiment and Embodiment 1 is that

[0097] Step S6 specifically includes the following steps:

[0098] S6.1, using the 5-layer image pyramid algorithm to locate the corresponding position of the template map M to be matched on the preprocessing template map A;

[0099] S6.2. Calculate the similarity measure Sk between the first k pixels in the template graph M to be matched and the preprocessed template graph A;

[0100] S6.3. Set the matching similarities of the remaining pixels in the template map M to be matched to 1, and set the threshold Smin;

[0101] S6.4, when When , the matching ends early and the output result is a matching failure. If Then execute step S6.5;

[0102] S6.5, when k

[0103] Among them, n represents the number of pixels in the template map M to be matched, λ=(1-g·s min ) / (1-g), g represents th...

Embodiment 3

[0106] refer to Figure 5 , the present embodiment provides a fabric pattern matching system based on a color image and a vector diagram, including: a preprocessing module, a grayscale module, a correction module, an outline extraction module, an interference removal module and a matching module, wherein the grayscale module, the correction module The module, the contour extraction module, the de-interference module and the matching module are connected in sequence, and the preprocessing module is connected with the matching module;

[0107] A preprocessing module, configured to preprocess the template graph to obtain a preprocessed template graph A suitable for the size of the picture to be matched;

[0108] The grayscale module is used to remove the number of color channels of the picture to be matched to convert the picture to be matched into a grayscale picture B;

[0109] The correction module is used to calculate the offset angle θ of the largest circumscribed ellipse o...

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 fabric pattern matching method and system based on a color graph and a vector diagram. The method comprises: S1, inputting a template graph, and preprocessing the template graph to obtain a preprocessed template graph A matched with a to-be-matched picture in size; S2, inputting a to-be-matched picture, and removing the number of color channels of the to-be-matched picture so as to convert the to-be-matched picture into a grayscale picture B; S3, calculating a deviation angle theta of a maximum circumscribed ellipse of the gray-scale picture B relative to a horizontal axis, and keeping the gray-scale picture B horizontal through an affine transformation matrix; S4, randomly selecting an ROI region S in the grayscale picture B, cutting the region S and extracting a contour to obtain a contour map L; S5, removing interference features in the contour map L to obtain a to-be-matched template map M; and S6, matching the to-be-matched template graph M with the pattern in the preprocessed template graph A to obtain a matching result. According to the invention, the accuracy and speed of textile fabric image matching are improved, and the labor cost of enterprises is greatly reduced.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a fabric pattern matching method and system based on a color map and a vector diagram. Background technique [0002] With the continuous advancement of modern textile printing technology, some patterns on the textile need to be matched with the printing template to verify its accuracy during the printing process. In this process, any area on the printed matter is required to have a corresponding area on the template map to match it. Therefore, high requirements are put forward for the timeliness and accuracy of the matching method. [0003] In the prior art, for the matching of textile images, manual segmentation is used to segment the parts of the textile images to be matched, which is very slow and inefficient. Therefore, the speed of textile image matching is greatly slowed down, and it cannot meet the needs of enterprises. Requirements for rapid textile ...

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): G06K9/62G06K9/46
CPCG06V10/44G06V10/56G06V10/751
Inventor 吕文涛刘志伟王成群骆淑云徐伟强
Owner ZHEJIANG SCI-TECH 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