摘要
为了实现工厂的无人化生产,需要高效地对纺织品进行分类。针对传统纺织品生产厂的人工分类方法存在着效率低下、难以满足大规模生产需求的问题。将人工智能和计算机视觉先进技术应用到纺织品材质分类中,提出了一种基于DSCI-YOLOv8的纺织材质分类算法。在YOLOv8模型原有分类网络的基础上添加坐标信息注意力模块,增强模型对不同尺度纺织品材质特征的提取能力,提高了网络分类的准确率,同时减少了计算所需的一部分计算量和参数量;其次将分布偏移卷积加入到C2f网络模块,改进了分类神经部分的网络结构,从而存储器的使用得到降低,计算速度也得到提高。实验结果表明,在自制的纺织品材质分类数据集FMCD上进行测试,改进后的模型相较于YOLOv8模型准确率提高了2.09个百分点,每秒处理图片数提高13.5%。大幅减少计算成本的同时,有效提高了纺织品材质分类的精度和速度。可以满足纺织工业对产品类别分类和质量的检测需求。
In order to realize unmanned production in factories,textiles need to be sorted efficiently.The manual classification method for traditional textile production plants has the problem of low efficiency and difficulty in meeting the needs of large-scale production.Artificial intelligence and computer vision advanced technology were applied to textile material classification,and a textile material classification algorithm based on DSCI-YOLOv8 was proposed.On the basis of the original classification network of the YOLOv8 model,the coordinate information attention module is added to enhance the model′s ability to extract the features of textile materials at different scales,improve the accuracy of network classification,and reduce some of the calculations and parameters required for calculation.Secondly,the distributed offset convolution is added to the C2f network module,which improves the network structure of the classification neural part,so that the memory usage is reduced and the computation speed is improved.Experimental results show that the accuracy of the improved model is increased by 2.09 percentage points and 13.5%increase in image processing per second compared with the YOLOv8 model.While greatly reducing the calculation cost,it effectively improves the accuracy and speed of textile material classification.It can meet the testing needs of the textile industry for product category classification and quality.
作者
王敏
许永琪
曹小萌
曹冉
欧翔
Wang Min;Xu Yongqi;Cao Xiaomeng;Cao Ran;Ou Xiang(School of Electronics and Information Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China;Electronics and Information Engineering College,Anhui Jianzhu University,Hefei 230601,China)
出处
《电子测量技术》
北大核心
2024年第18期130-137,共8页
Electronic Measurement Technology
基金
国家自然科学基金(41775165,41775039)
安徽省高校杰出青年科研项目(2023AH020022)资助。
关键词
深度学习
纺织品分类
注意力机制
YOLOv8
分布偏移卷积
deep learning
textile classification
attention mechanisms
YOLOv8
distribution offset convolution
作者简介
王敏,博士,教授,主要研究方向为信号与信息处理、图像处理、深度学习。E-mail:yu0801@163.com;通信作者:许永琪,硕士研究生,主要研究方向为计算机视觉、深度学习等。E-mail:1250030670@qq.com;曹小萌,硕士研究生,主要研究方向为计算机视觉、深度学习等。E-mail:2069197782@qq.com;曹冉,硕士研究生,主要研究方向为计算机视觉、深度学习等。E-mail:413769629@qq.com;欧翔,硕士研究生,主要研究方向为计算机视觉、深度学习等。E-mail:1164088794@qq.com。
