基于深度学习的棉花异性纤维检测  

Detection of Cotton Foreign Fibers Based on Deep Learning

作　　者：梁后军[1] 谢睿[2] 周万怀[1] 张雪东[1] 李庆旭 李浩[1] LIANG Houjun;XIE Rui;ZHOU Wanhuai;ZHANG Xuedong;LI Qingxu;LI Hao(School of Management Science and Engineering,Anhui University of Finance and Economics,Institute of Cotton Engineering,Anhui University of Finance and Economics,Bengbu,Anhui 233000,China;School of Accounting,Anhui University of Finance and Economics,Bengbu,Anhui 233000,China)

机构地区：[1]安徽财经大学管理科学与工程学院、安徽财经大学棉花工程研究所,安徽蚌埠233000 [2]安徽财经大学会计学院,安徽蚌埠233000

出　　处：《中国纤检》2024年第2期77-81,共5页China Fiber Inspection

基　　金：安徽省高校自然科学重点项目(KJ2021A0478)。

摘　　要：在棉花纤维生产过程中,棉花异性纤维直接影响着其成品质量优劣。通过人工进行视觉上的观察是常用的判定棉花异性纤维优劣的方法,但这种方法耗费大量人力和时间,且准确性不高。本文测试一种可根据深度学习对棉花异性纤维进行自动检测的方法。通过卷积神经网络,在对棉花图像不断训练的过程中,使棉花异性纤维质量检测过程自动化。结果表明,这一方法对于检测棉花异性纤维准确性高、效率高,对于高品质棉花自动化生产加工有重要意义。In the production process of cotton fiber,cotton heterosexual fiber directly affects the quality of its finished product.Visual observation by manual is a commonly used method to determine the quality of cotton heterosexual fiber,but this method consumes a lot of manpower and time,and the accuracy is not high.In this paper,we test a method for automatic detection of cotton heterosexual fibers based on deep learning.Through the convolutional neural network,the quality detection process of cotton heterosexual fibers is automated in the process of continuous training of cotton images.The results show that this method has high accuracy and high efficiency for the detection of cotton heterosexual fibers,and is of great significance for the automatic production and processing of high-quality cotton.

关 键 词：目标检测 深度学习 卷积神经网络 棉花异性纤维 

分 类 号：TS107.2[轻工技术与工程—纺织工程]