System and method for real-time appearance digital analysis for yarn

Abstract

The invention relates to a system and a method for real-time appearance digital analysis for a yarn. The system comprises a camera obscura, an image acquisition system and a PC (personal computer) processing terminal, wherein the image acquisition system is electrically connected with the PC processing terminal; and at least two reflectors and an LED (light-emitting diode) backlight source are arranged in the camera obscura. The system disclosed by the invention can be used for dynamically and continuously acquiring yarn images, simultaneously performing related analysis processing on the yarn images of five side surfaces in the images respectively at the same detection position of each image during a characteristic extraction process, extracting characteristics, and finally fusing the yarn appearance characteristic information of all the images to form the appearance characteristic vector of the yarn, performing characteristic similarity DW (X, Y) calculation with a standard sample, and judging the performance and the quality of the yarn on the basis of the calculation result. According to the system and the method disclosed by the invention, the multi-angle three-dimensional appearance characteristic information of the yarn can be obtained in real time, so that the quality of the yarn can be rapidly and accurately determined; the influence of human factors on quality evaluation is effectively reduced, so that the accuracy of analysis is improved; and the system is reasonable in design and high in practicability.

Description

technical field [0001] The invention belongs to the field of intelligent digital information analysis of machine vision, and in particular relates to a real-time yarn appearance digital analysis system and method. Background technique [0002] Yarn quality is directly related to the appearance performance, physical performance and wearing performance of fabrics and clothing, and plays a pivotal role in textile production. The fineness, hairiness and evenness of the yarn directly affect the appearance of the fabric, and also affect the physical and mechanical properties such as strength, stretchability, elasticity, and wear resistance. Yarn appearance information (thickness variation, ellipticity, diameter unevenness, etc.) is of great significance for comprehensive evaluation of yarn quality, guidance of manufacturing process, and prediction of fabric appearance. [0003] Therefore, the detection of yarn quality has become a core issue of product quality monitoring since th...

AI Technical Summary

Problems solved by technology

However, due to the three-dimensional structure of the yarn body, there is information loss in single-angle field of view imaging detection, which may easily cause errors in feature extraction

Images