A method for detecting fiber distribution in mixed fiber products

Abstract

The invention discloses a method for detecting the fiber distribution in a mixed fiber product. The method comprises the following steps: 1, collecting an original image of the mixed fiber product, and obtaining a low-noise gray scale image through denoising and gray scale transformation; 2, setting any fiber as target or non-target fibers; 3, cutting that image of the step '1' into small pixel maps, and selecting an appropriate threshold value to process the small pixel maps; 4, extracting that eigenvalue of the non-target fiber as noise, performing two-dimensional multi-level stochastic resonance on the image of the step '3', and extracting the target fiber accord to the result; 5, binarizing that image of the step '4', recombine the small images into the binarized images of the original size accord to the original cutting order, if the binarized images can display the target fiber outline, carrying out the next step, otherwise returning to the step '4'; 6, counting that number of target fib pixels of the restored image, and giving the fib distribution value of the mixed fiber product. By extracting the eigenvalues of the target and non-target fibers and by removing the non-target fibers to highlight the target fibers, the present invention has the advantages of simple operation and high processing accuracy.

Description

technical field [0001] The invention relates to the field of non-woven equipment, in particular to the detection of fiber distribution in mixed fiber products. Background technique [0002] Traditional fiber web detection methods such as sampling weighing method, thickness measurement method and radioisotope measurement method can accurately analyze the uniformity of fiber webs composed of single fibers, but cannot evaluate the uniformity of fiber webs composed of mixed fibers. In particular, it cannot intuitively reflect the distribution of each fiber in the mixed fiber web. With the continuous development of image processing technology, due to its advantages such as high processing precision, good reproducibility, and diverse processing, this technology It is widely used to characterize the structural characteristics of fiber webs, mainly including the study of fiber orientation distribution of nonwoven material webs, the detection of fiber web porosity, and the determinat...

AI Technical Summary

Problems solved by technology

[0002] Traditional fiber web detection methods such as sampling weighing method, thickness measurement method and radioisotope measurement method can accurately analyze the uniformity of fiber webs composed of single fibers, but cannot evaluate the uniformity of fiber webs composed of mixed fibers. In particular, it cannot intuitively reflect the distribution of each fiber in the mixed fiber web. With the continuous development of image processing technology, due to its advantages such as high processing precision, good reproducibility, and diverse processing, this technology It is widely used to characterize the structural characteristics of fiber webs, mainly including the study of fiber orientation distribution of nonwoven material webs, the detection of fiber web porosity, and the determination of fiber web uniformity, and has achieved good application results. However, the above image processing methods are more aimed at the detection of performance indicators of fiber webs composed of single fibers, and less research has been done on the detection of fiber distribution in fiber webs composed of mixed fibers. This patent combines multi-level stochastic resonance technology , the method of image processing can effectively solve the above problems, and has the advantages of fast, efficient and high accuracy

[0003] At present, the method of studying fiber distribution characteristics is generally to use image fusion to obtain fiber orientation, use morphological erosion and expansion to remove noise and noise, and use threshold segmentation to calculate porosity. Erosion can shrink the contour boundary; expansion can make the contour Boundary expansion. Erosion and expansion are to remove the gaps in the grid to highlight the fiber grid. Image threshold segmentation is to select a more appropriate threshold for the entire collected image to process, and then study the distribution of fibers. However, There is no image processing technology to study the fiber distribution in mixed fiber products. Therefore, this paper adopts the method of multi-level stochastic resonance to set the eigenvalue of any fiber in mixed fiber products as the target fiber, and the rest are non-target fibers; Then use image processing technology to qualitatively and quantitatively analyze the distribution of target fibers; finally, draw a histogram of target fiber pixel distribution according to the distribution of target fibers

Images