Cotton foreign fiber online classifying method and system

Abstract

The invention discloses cotton foreign fiber online classifying method and system, wherein the method comprises steps of collecting color images of cotton foreign fibers in real time; segmenting the color images of cotton foreign fibers with an image segmenting method based on three-component mean value and variance of pixels R, G and B to obtain an objective image formed by the objective pixel in the color images of cotton foreign fibers; removing small objects produced by noise and false foreign fibers in the objective image with an area threshold method to obtain objects of the cotton foreign fibers; extracting color features, shape features and texture features of each object of the cotton foreign fibers to generate feature vectors for describing the objects of the cotton foreign fibers; and classifying the objects of the cotton foreign fibers by using the feature vectors and a one-against-one-algorithm multi-class classification support vector machine based on a directed acyclicgraph. The invention realizes the online real-time classification of the cotton foreign fibers, and is beneficial to subsequently realizing the online computation of the foreign fibers.

Description

technical field [0001] The invention relates to the fields of machine vision and pattern recognition, in particular to an online classification method and system for foreign fibers of cotton. Background technique [0002] Cotton foreign fibers refer to non-cotton fibers and colored fibers that are mixed into cotton during the process of cotton picking, tanning, and purchase, which have a serious impact on the quality of cotton and its products, mainly including polypropylene yarn, plastic cloth, chicken feathers, and cloth strips. , twine and hair etc. Although the content of foreign fibers in lint is small, it has a serious impact on the quality of cotton textiles. Once mixed and involved in weaving, it will affect the strength of the yarn, and affect the coloring during dyeing, which will cause significant economic losses to the cotton textile industry. [0003] At present, it is possible to reduce the content of foreign fibers in cotton by picking foreign fibers, or take...

AI Technical Summary

Problems solved by technology

[0005] Since the theoretical basis of the existing cotton foreign fiber classification method is the law of large numbers, the number of samples is required to be close to infinity, which is almost impossible to achieve in practical applications.

Therefore, the adaptability of the classification method is poor, and the classification accuracy rate is low

However, if the foreign fiber cannot be quickly and accurately classified, it is impossible to quick

Images