A method for identifying the type of weave structure of woven fabrics
An identification method and a technology of tissue structure, applied in the field of image analysis, can solve the problems of difficulty in identifying the type of tissue structure of woven fabrics, inability to cope with illumination, and low recognition rate.
Inactive Publication Date: 2018-11-23
HEBEI UNIV OF TECH
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The technical problem to be solved by the present invention is to provide a method for identifying the types of weave structures of woven fabrics, which is a method for identifying the types of weave structures of woven fabrics based on yarn boundary features, which overcomes the shortcomings existing in the existing methods for identifying types of weave structures of woven fabrics. The recognition rate is low, and brightness and color changes have a great impact on the recognition results. It cannot cope with the types of woven fabric structures with uneven illumination, yarn thickness and color changes, and it is difficult to identify the woven fabric structure of yarn and fiber twisted and deformed woven fabrics. Different types of defects, and can identify the twill weave and its variation, satin weave and its variation
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0162] A method for identifying the type of weave structure of a woven fabric is a method for identifying the type of weave structure of a woven fabric based on yarn boundary features, and the steps are as follows:
[0163] The first step, woven fabric image preprocessing:
[0164] Input the magnified image of the woven fabric collected by the USB digital electron microscope into the computer, the resolution of the magnified image is 640×480 pixels, and use the formula (1) to convert the RGB color space image into the HSV color space to obtain the brightness information I V ,
[0165] I V =max{I R , I G , I B} (1), where I R , I G , I B Respectively represent the red, green and blue component values of each pixel in the RGB color space, and then the brightness information I V Carry out median filter processing to obtain woven fabric brightness image I V,MF , further to I V,MF Erosion treatment to obtain brightness image of woven fabric I V,Ero ;
[0166] In the s...
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
Login to View More Abstract
The invention discloses a method for identifying the type of the weave structure of a woven fabric, which relates to image analysis, and is a method for identifying the type of the weave structure of the woven fabric based on yarn boundary features. Image; local woven fabric point image normalization; computerized fabric point image yarn boundary features; woven fabric point image recognition of warp and weft attributes; calculation of weave cycle yarn number; correction of woven fabric point image warp and weft attributes; recognition machine The type of fabric structure and the output of the woven fabric structure map; the present invention overcomes the low recognition rate in the existing identification method of the type of woven fabric structure, the brightness and color changes have a great influence on the recognition result, and cannot cope with uneven illumination, yarn thickness and The weave structure of woven fabrics with changing colors is difficult to identify the defects of yarn and fiber twisted and deformed weave structures. At the same time, it has the recognition effect on twill and satin weaves and extremely changeable weaves.
Description
technical field [0001] The technical solution of the invention relates to image analysis, in particular to a method for identifying the type of woven fabric structure. Background technique [0002] Currently in the textile industry, the various parameters of the weave structure of woven fabrics mainly rely on professionals to manually identify the cloth with the help of a magnifying glass, an analysis needle or a cloth mirror, or manually identify and analyze the woven fabric pictures collected by the image collector with the naked eye. The recognition efficiency of the manual recognition method is low, and the accuracy and efficiency of the recognition are heavily dependent on the personal status, experience, technology and knowledge reserve of the relevant personnel, and after manual recognition, the parameters of the cloth organization structure are professionally recorded or re-input Computers require a lot of time and are prone to errors, which is not conducive to the f...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06T2207/20032G06T2207/10061G06T2207/30124G06T2207/20152G06V20/69G06V10/443G06V10/56G06V2201/122G06F18/2415G06T5/80
Inventor 郭迎春师硕于洋刘依阎刚葛鑫
Owner HEBEI UNIV OF TECH