Detection of foreign fiber in cotton based on improved YOLOv3

Ming-xiu WU; Jin WU; Chen ZHANG; Lei ZHU

doi:10.37188/YJYXS20203511.1195

您当前的位置：

首页 >

文章列表页 >

Detection of foreign fiber in cotton based on improved YOLOv3

Image Processing | 更新时间：2020-10-30

- Detection of foreign fiber in cotton based on improved YOLOv3
- Chinese Journal of Liquid Crystals and Displays Vol. 35, Issue 11, Pages: 1195-1203(2020)
- 作者机构：
  
  1.武汉科技大学信息科学与工程学院, 湖北武汉 430081
  2.冶金自动化与检测技术教育部工程中心, 湖北武汉 430081
- 作者简介：
- 基金信息：
  
  the Youth Fund Project of National Natural Science Foundation of China(61502358);the Youth Fund Project of National Natural Science Foundation of China(61702384)
- DOI：10.37188/YJYXS20203511.1195
  CLC： TP391
- Received：26 April 2020，
  
  Revised：25 May 2020，
  
  Accepted：25 May 2020，
  
  Published：05 November 2020
- 稿件说明：
移动端阅览
Ming-xiu WU, Jin WU, Chen ZHANG, et al. Detection of foreign fiber in cotton based on improved YOLOv3[J]. Chinese journal of liquid crystals and displays, 2020, 35(11): 1195-1203.
DOI：

Ming-xiu WU, Jin WU, Chen ZHANG, et al. Detection of foreign fiber in cotton based on improved YOLOv3[J]. Chinese journal of liquid crystals and displays, 2020, 35(11): 1195-1203. DOI： 10.37188/YJYXS20203511.1195.

摘要

针对棉花异性纤维检测准确率不高、实时性较差的问题，以棉花为研究对象，提出了一种基于改进YOLOv3的棉花异性纤维检测方法。引入轻量级MobileNets网络为特征提取网络，结合YOLOv3的多尺度特征融合检测网络，构建改进的MobileNets-YOLOv3模型。提出一种分段式学习率，以增强学习效果。将实际采集到的真实棉花异性纤维图像数据集按4:1的比例划分为训练集和测试集，并使用对比度增强、水平镜像等6种图像增广方法扩充数据集。对扩充前后的数据集、不同的学习率、改进前后的YOLOv3模型、本文模型与Faster R-CNN和SSD_300模型做了对比试验。实验结果表明，数据集的增广、改进后的分段式学习率均能改善训练模型的过拟合现象，在测试集上的平均正确率（mAP）分别提高了3.6%、5.64%；改进后的YOLOv3模型对测试集进行检测的平均正确率（mAP）为84.82%，帧速率为66.67 f·s

-1

，识别精度优于YOLOv3模型，提高了2.03%，帧速率是YOLOv3模型的3倍，总体性能也优于Faster R-CNN和SSD_300模型，能较好地满足棉花异纤检测的精度和实时性要求。

Abstract

In order to solve the problems of low identification efficiency and poor real-time performance to cotton foreign fiber detection

an improved method of cotton foreign fiber detection based on YOLOv3 was proposed. The constructed model of MobileNets-YOLOv3 was designed

in which a lightweight MobileNets network was selected as the feature extraction network

combined with YOLOv3's multi-scale feature fusion detection network. A segmented learning rate was proposed to enhance the learning effect. The cotton foreign fiber image data set collected from the equipment on real site was divided into a training set and a test set

according to a ratio of 4:1. Six image augmentation methods

such as contrast enhancement

brightness enhancement and so on

was induced

to expand the original data set. Based on the training set before and after expansion

different learning rates

the YOLOv3 model before and after improvement

the proposed model and Faster R-CNN along with SSD_300

different models were tested and compared. The experimental results showed that the data expansion and the segmented learning rate can improve the overfitting of the training model

and the mean average precison (mAP) on the test set was increased by 3.6% and 5.64% respectively. The improved YOLOv3 model can significantly reduce the mistake rate and miss rate of detection. The mAP of the test set was 84.82%

and the frame rate was 66.67 f·s

-1

. Compared with YOLOv3

the mAP of MobileNets-YOLOv3 was increased by 2.03%

the frame rate was raised to 3 times as it and the duration of training was shortened to 1/4 times as it. The overall performance of MobileNets-YOLOv3 was also better than that of Faster R-CNN and SSD_300. The proposed method can better satisfy the accuracy and real-time performance of cotton foreign fiber detection.

关键词

Keywords

references

G R GAMBLE , J A FOULK . Quantitative analysis of cotton ( Gossypium hirsutum ) lint trash by fluorescence spectroscopy . Journal of Agricultural and Food Chemistry , 2007 . 55 ( 13 ): 4940 - 4943 . DOI: 10.1021/jf063607t http://doi.org/10.1021/jf063607t .

A MUSTAFIC , C Y LI , M HAIDEKKER . Blue and UV LED-induced fluorescence in cotton foreign matter . Journal of Biological Engineering , 2014 . 8 29 DOI: 10.1186/1754-1611-8-29 http://doi.org/10.1186/1754-1611-8-29 .

郏东耀 , 丁天怀 . 棉花中异性纤维的多光谱检测 . 清华大学学报(自然科学版) , 2005 . 45 ( 2 ): 193 - 196 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qhdxxb200502014 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qhdxxb200502014 .

D Y JIA , T H DING . Detecting foreign fibers in cotton using a multi-spectral technique . Journal of Tsinghua University (Science and Technology) , 2005 . 45 ( 2 ): 193 - 196 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qhdxxb200502014 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qhdxxb200502014 .

杜玉红 , 王加富 , 蒋秀明 , 等 . 应用聚类统计分析的棉花异纤图形检测算法 . 纺织学报 , 2015 . 36 ( 3 ): 135 - 139 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxb201503026 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxb201503026 .

Y H DU , J F WANG , X M JIANG , 等 . Algorithm for pattern detection of cotton foreign fibers based on cluster statistic analysis . Journal of Textile Research , 2015 . 36 ( 3 ): 135 - 139 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxb201503026 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxb201503026 .

师红宇 , 管声启 , 吴宁 . 棉花中异性纤维的图像多分辨率差分检测方法 . 纺织学报 , 2014 . 35 ( 5 ): 13 - 18 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxb201405003 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxb201405003 .

H Y SHI , S Q GUAN , N WU . Detection of foreign fibers among cotton based on image multi-resolution difference method . Journal of Textile Research , 2014 . 35 ( 5 ): 13 - 18 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxb201405003 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxb201405003 .

师红宇 , 管声启 . 基于视觉注意计算模型的棉花异性纤维检测 . 东华大学学报(自然科学版) , 2016 . 42 ( 3 ): 400 - 405 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgfzdxxb201603016 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgfzdxxb201603016 .

H Y SHI , S Q GUAN . Cotton foreign fibers detection based on visual attention computational model . Journal of Donghua University (Natural Science Edition) , 2016 . 42 ( 3 ): 400 - 405 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgfzdxxb201603016 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgfzdxxb201603016 .

杨文柱 , 李道亮 , 魏新华 , 等 . 基于改进遗传算法的棉花异性纤维目标特征选择 . 农业机械学报 , 2010 . 41 ( 4 ): 173 - 178 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=nyjxxb201004035 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=nyjxxb201004035 .

W Z YANG , D L LI , X H WEI , 等 . Feature selection for cotton foreign fiber objects based on improved genetic algorithm . Transactions of the Chinese Society for Agricultural Machinery , 2010 . 41 ( 4 ): 173 - 178 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=nyjxxb201004035 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=nyjxxb201004035 .

杨文柱 , 卢素魁 , 王思乐 . 基于多类支持向量机的棉花异性纤维分类方法 . 计算机应用 , 2011 . 31 ( 12 ): 3446 - 3448, 3452 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjyy201112077 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjyy201112077 .

W Z YANG , S K LU , S L WANG . Classification of cotton foreign fibers based on multi-class support vector machine . Journal of Computer Applications , 2011 . 31 ( 12 ): 3446 - 3448, 3452 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjyy201112077 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjyy201112077 .

GIRSHICK R, DONAHUE J, DARRELL T, et al . Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Columbus, OH, USA: IEEE, 2014: 580-587.

郑欣 , 田博 , 李晶晶 . 基于YOLO模型的宫颈细胞簇团智能识别方法 . 液晶与显示 , 2018 . 33 ( 11 ): 965 - 971 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1462781&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1462781&Fpath=&index=-1&l=zh .

X ZHENG , B TIAN , J J LI . Intelligent recognition method of cervical cell cluster based on YOLO model . Chinese Journal of Liquid Crystals and Displays , 2018 . 33 ( 11 ): 965 - 971 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1462781&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1462781&Fpath=&index=-1&l=zh .

J LI , X MEI , D PROKHOROV , 等 . Deep neural network for structural prediction and lane detection in traffic scene . IEEE Transactions on Neural Networks and Learning Systems , 2017 . 28 ( 3 ): 690 - 703 . DOI: 10.1109/TNNLS.2016.2522428 http://doi.org/10.1109/TNNLS.2016.2522428 .

A G HOWARD , M L ZHU , B CHEN , 等 . MobileNets:efficient convolutional neural networks for mobile vision applications . arXiv:1704.04861v1 , 2017 . 1 - 9 . http://arxiv.org/abs/1704.04861 http://arxiv.org/abs/1704.04861 .

J REDMON , A FARHADI . YOLOv3:an incremental improvement . arXiv:1804.02767v1 , 2018 . 1 - 6 . http://arxiv.org/abs/1804.02767 http://arxiv.org/abs/1804.02767 .

REN S Q, HE K M, GIRSHICK R, et al . Faster R-CNN: towards real-time object detection with region proposal networks[C]// Proceedings of the 28 th International Conference on Neural Information Processing Systems . Montreal, Canada: ACM, 2015: 91-99.

LIU W, ANGUELOV D, ERHAN D, et al . SSD: single shot MultiBox detector[C]// Proceedings of the 14 th European Conference on Computer Vision . Amsterdam, The Netherlands: Springer, 2016: 21-37.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Infrared dim-small target detection under complex background based on attention mechanism

Research progress on absolute visual localization of unmanned aerial vehicles

3D hand reconstruction method based on adaptive occlusion recovery and topology-pose bidirectional perception

Reconstruction method of video snapshot compressive imaging based on Mamba-2

Related Author

LIU Ying

SUN Hai-jiang

ZHAO Yong-xian

MIAO Zongcheng

ZHOU Runxi

LIU Jie

YANG Haiyan

LIU Jia

Related Institution

Changchun Institute of Optics， Fine Mechanics and Physics， Chinese Academy of Sciences

University of Chinese Academy of Sciences

Technological Institute of Materials & Energy Science （TIMES）， School of Electronic Information， Xijing University

School of Artificial Intelligence， Optics and Electronics （iOPEN）， Northwestern Polytechnical University

School of Automation， Nanjing University of Information Science & Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰