Cotton impurity detection method and system based on machine vision

Abstract

The invention discloses a cotton impurity detection system and method based on machine vision, and belongs to the technical field of cotton impurity image detection. And a machine vision and deep learning technology is utilized, a cotton miscellaneous data set is adopted to train a convolutional neural network, then a weight is output, an optimized convolutional neural network is obtained, and image information of actually detected noil is identified. The convolutional neural network has a complementary search technology and a searchable lightweight and efficient network architecture, has the characteristics of low parameter, high performance and high speed, and can meet the requirements of industrial application. On the basis, the parameter layer and the channel number can be adjusted, the parameter quantity is reduced, and the detection speed is improved, so that the method is more suitable for impurity image detection and classification. The method is high in automation degree, a previous manual sorting mode is replaced, the efficiency is improved, and the cost is reduced. Meanwhile, the cotton impurity detection efficiency and quality are improved, more technical supports are provided for subsequent impurity removal, the finished product quality of cotton textiles is improved, and the method has good application prospects.

Description

technical field [0001] The invention belongs to the technical field of cotton trash image detection, and in particular relates to a machine vision-based cotton trash detection method and system. Background technique [0002] Cotton plays a pivotal role in the textile industry. At present, more than 70% of the existing cotton is picked by machines. Therefore, cotton will be mixed with a large amount of impurities to be collected and processed. The lint is easily absorbed in the lint during production and processing, and is difficult to remove during spinning, and is often wrapped in the sliver, which results in uneven drying of the sliver, uneven dyeing, cotton yarn breakage, and excessive loss. At the same time, the defect rate of textiles caused by cotton dust is inversely proportional to the decontamination rate of cotton fibers, which will cause serious waste of textile products. Therefore, the detection and analysis of cotton dust is an essential process in industrial sp...

AI Technical Summary

Problems solved by technology

[0003] The problem of removing cotton impurities has been plagued by many textile companies in online production. In order to reduce the impact of cotton impurities on the quality of yarn and cloth, cotton spinning enterprises have to organize special personnel to observe the removal of impurities in cotton cleaning machines in real time on the cotton production line. The existing common practice On the cotton production line of cotton spinning enterprises, the operator stands on both sides of the cotton cleaning machine and frequently observes whether the valve device of the cotton cleaning machine is affected by a large amount of impurities. At this time, the efficiency of removing impurities is seriously reduced, and the cleaning machine must be suspended Manual control of the valve unit for internal purge work

This manual visual inspection method has great defects. On the one hand, the labor intensity of the operators is high, the working environment is harsh, and the health and safety of workers are difficult to guarantee. On the other hand, due to the large number of cotton cleaning machines, it is difficult to detect cotton accurately and quickly in real time. The amount of impurities in the cotton is located on multiple machines in the center of the production line. Even if a problem is found, it is difficult for the operator to control and clean it in time; at the same time, the cotton cleaning machine uses a traditional high-pressure jet separation device to remove cotton, resulting in existing Cotton cleaning machines have disadvantages such as high uncertainty, ambiguity, and low efficiency. Missing inspections often occur, and it is difficult to meet the high-speed, high-precision inspection requirements of modern industries.

[0004] The impurity content in cotton has different effects on subsequent production. There are no fixed standards and specifications for the detection and analysis of impurity content in cotton. In actual industrial spinning, the cotton cleaning machine mainly relies on the traditional physical method, that is, the high-pressure air jet separation device to clean the cotton. This method takes a long time due to manual participation, and the detection efficiency of the impurity separation method is low

Images