基于改进YOLOv3的瞳孔屈光度检测方法

李岳毅; 丁红昌; 张雷; 赵长福; 张士博; 王艾嘉

基于改进YOLOv3的瞳孔屈光度检测方法

李岳毅^1,,
丁红昌^{1, 2, ,},
张雷^{3, 4},
赵长福¹,
张士博¹,
王艾嘉¹

1.
长春理工大学机电工程学院，吉林长春 130022
2.
长春理工大学重庆研究院，重庆 401135
3.
郑州轻工业大学电气信息工程学院，河南郑州 450002
4.
中国烟草总公司郑州烟草研究院，河南郑州 450001

基金项目:

吉林省科技发展计划重点研发项目 20200401117GX

河南省科技攻关计划 212102210155

详细信息

作者简介:
李岳毅（1994-），男，硕士研究生，主要从事图像处理、目标检测和计算机视觉方面的研究。E-mail: lyy642668743@163.com

通讯作者:
丁红昌（1980-），男，博士，副教授，博士生导师，吉林省第七批拔尖创新人才。主要从事在线检测、模式识别和机器视觉方面的研究。E-mail: custjdgc@163.com

中图分类号: TP391
计量
- 文章访问数: 126
- HTML全文浏览量: 35
- PDF下载量: 25
- 被引次数: 0
出版历程
- 收稿日期: 2021-08-27
- 修回日期: 2021-11-29
- 刊出日期: 2022-07-20

Pupil Diopter Detection Approach Based on Improved YOLOv3

LI Yueyi^1
,,
DING Hongchang^{1, 2
, ,},
ZHANG Lei^{3, 4},
ZHAO Changfu¹,
ZHANG Shibo¹,
WANG Aijia¹

1.
College of Mechanical and Electrical Engineering, Changchun University of Science and Technology, Changchun 130022, China
2.
Chongqing Research Institute, Changchun University of Science and Technology, Chongqing 401135, China
3.
School of Electrical Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
4.
Zhengzhou Tobacco Research Institute China National Tobacco Corporation, Zhengzhou 450001, China

摘要

摘要: 针对瞳孔区域屈光度识别准确率低、检测效率低等问题，本文提出一种基于改进YOLOv3深度神经网络的瞳孔图像检测算法。首先构建用于提取瞳孔主特征的二分类检测网络YOLOv3-base，强化对瞳孔特征的学习能力。然后通过迁移学习，将训练模型参数迁移至YOLOv3-DPDC（Deep Pupil Diopter Classify），降低样本数据分布不均衡造成的模型训练困难以及检测性能差的难题，最后采用Fine-tuning调参快速训练YOLOv3多分类网络，实现了对瞳孔屈光度快速检测。通过采集的1200张红外瞳孔图像进行实验测试，结果表明本文算法屈光度检测准确率达91.6%，检测速度可达45 fps，优于使用Faster R-CNN进行屈光度检测的方法。
- 瞳孔屈光度检测 /
- 深度学习 /
- YOLOv3网络 /
- 多尺度特征 /
- 机器视觉
Abstract: To address the problems of low diopter recognition accuracy and low detection efficiency in the pupil area, this paper proposes a pupil image detection algorithm based on an improved YOLOv3 deep neural network. First, a two-class detection network YOLOv3 base for extracting the main features of the pupil is constructed to strengthen the learning ability of the pupil characteristics. Subsequently, through migration learning, the training model parameters are migrated to YOLOv3-DPDC to reduce the difficulty of model training and poor detection performance caused by the uneven distribution of sample data. Finally, fine-tuning is used to quickly train the YOLOv3 multi-classification network to achieve accurate pupil diopter detection. An experimental test was performed using the 1200 collected infrared pupil images. The results show that the average accuracy of diopter detection using this algorithm is as high as 91.6%, and the detection speed can reach 45 fps; these values are significantly better than those obtained using Faster R-CNN for diopter detection.
- pupil diopter detection /
- deep learning /
- YOLOv3 /
- multi-scale features /
- machine vision

HTML全文

图 1 本文提出的瞳孔识别算法示意图

Figure 1. Schematic diagram of the infrared pupil recognition algorithm proposed in this article

下载: 全尺寸图片幻灯片

图 2 第一阶段迁移学习处理过程

Figure 2. The first stage transfer learning process

下载: 全尺寸图片幻灯片

图 3 本文所提算法的网络模型与参数说明

Figure 3. The network model and parameter description of the proposed algorithm in this article

下载: 全尺寸图片幻灯片

图 4 瞳孔图像数据集人工扩增示意图

Figure 4. Schematic diagram of artificial augmentation of pupil image data set

下载: 全尺寸图片幻灯片

图 5 Loss值变化示意图

Figure 5. Schematic diagram of Loss value change

下载: 全尺寸图片幻灯片

图 6 本文方法在部分图像上的检测结果

Figure 6. The detection results of the method in this paper on some images

下载: 全尺寸图片幻灯片

表 1 瞳孔数据集C的划分

Table 1. The division of pupil data set C

Diopter grade	Initial number of samples	Number of samples after amplification	Training samples	Validation samples
R₁	120	2000	1600	400
R₁	780	5000	4000	1000
R₃	300	4000	3200	800

下载: 导出CSV

表 2 实验参数设置

Table 2. Experimental parameter settings

Parameter	Parameter value
Training image size/pixel	416×416
Number of iterations	9000
GPU quantity	1
IOU	0.6
The initial learning rate of the previous stage	0.001
The initial learning rate of the latter stage	0.0001

下载: 导出CSV

表 3 不同算法数据对比

Table 3. Data of different algorithms

Algorithm model	Precision/%	Recall/%	Time/ms	F_1-score/%
SSD	82.5	84.7	20.3	84.7
RetinaNet	84.7	82.4	32.6	82.4
Faster R-CNN	86.8	88.9	109.6	88.9
Our algorithm	91.6	90.5	22.3	90.5

下载: 导出CSV

表 4 传统算法数据统计

Table 4. Statistics of traditional algorithms

Algorithm model	Accuracy/%	Time/ms
Traditional algorithm	71.5	130

下载: 导出CSV

表 5 本文算法得出的分类混淆矩阵

Table 5. The classification confusion matrix obtained by the algorithm in this paper

	R₁	R₂	R₃
R₁	19	1	0
R₂	1	17	2
R₃	0	1	19

下载: 导出CSV

参考文献(14)

[1]	薛烽, 李湘宁. 一种基于图像处理的屈光度测量方法[J]. 光电工程, 2009, 36(8): 62-66, 74. https://www.cnki.com.cn/Article/CJFDTOTAL-GDGC200908017.htm XUE Feng, LI Xiangning. A method of diopter measurement based on image processing[J]. Photoelectric Engineering, 2009, 36(8): 62-66, 74. https://www.cnki.com.cn/Article/CJFDTOTAL-GDGC200908017.htm
[2]	胡志轩. 基于红外图像的眼视力屈光度检测系统[D]. 武汉: 华中师范大学, 2018. HU Zhixuan. An Eye Vision Diopter Detection System Based On Infrared Image[D]. Wuhan: Center China Normal University, 2018.
[3]	谢娟英, 侯琦, 史颖欢, 等. 蝴蝶种类自动识别研究[J]. 计算机研究与发展, 2018, 55(8): 1609-1618. https://www.cnki.com.cn/Article/CJFDTOTAL-JFYZ201808003.htm XIE Juanying, HOU Qi, SHI Yinghuan, et al. Research on automatic recognition of butterfly species[J]. Computer Research and Development, 2018, 55(8): 1609-1618. https://www.cnki.com.cn/Article/CJFDTOTAL-JFYZ201808003.htm
[4]	Redmon J, Divvala S, Girshick R, et al. You only look once: unified real-time object detection[C]//Proceedings of the Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
[5]	Kaur P, Khehra B S, Pharwaha A. Deep transfer learning based multi way feature pyramid network for object detection in images[J]. Mathematical Problems in Engineering, 2021, 2021: 1-13.
[6]	Noh H, Hong S, Han B. Learning deconvolution network for semantic segmentation[C]//IEEE International Conference on Computer Vision, 2015: 5119-5127.
[7]	刘智, 黄江涛, 冯欣. 构建多尺度深度卷积神经网络行为识别模型[J]. 光学精密工程, 2017, 25(3): 799-805. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201703035.htm LIU Zhi, HUANG Jiangtao, FENG Xin. Building a multi-scale deep convolutional neural network behavior recognition model[J]. Optics and Precision Engineering, 2017, 25(3): 799-805. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201703035.htm
[8]	王娟, 刘嘉润, 李瑞瑞. 基于深度学习的红外相机视力检测算法[J]. 电子测量与仪器学报, 2019, 33(11): 36-43. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201911005.htm WANG Juan, LIU Jiarun, LI Ruirui. Infrared camera vision detection algorithm based on deep learning[J]. Journal of Electronic Measurement and Instrument, 2019, 33(11): 36-43. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201911005.htm
[9]	LIU Y P, JI X X, PEI S T, et al. Research on automatic location and recognition of insulators in substation based on YOLOv3[J]. High Voltage, 2020, 5(1): 62-68. doi: 10.1049/hve.2019.0091
[10]	Murugan A, Nair S, Kumar K. Detection of skin cancer using SVM, random forest and KNN classifiers[J]. Journal of Medical Systems, 2019, 43(8): 683-686.
[11]	ZHU S G, DU J P, REN N, et al. Hierarchical-Based object detection with improved locality sparse coding[J]. Chinese Journal of Electronics, 2016, 25(2): 290-295. doi: 10.1049/cje.2016.03.015
[12]	温江涛, 王涛, 孙洁娣, 等. 基于深度迁移学习的复杂环境下油气管道周界入侵事件识别[J]. 仪器仪表学报, 2019, 40(8): 12-19. https://www.cnki.com.cn/Article/CJFDTOTAL-YQXB201908002.htm WEN Jiangtao, WANG Tao, SUN Jiedi, et al. Intrusion event identification of oil and gas pipeline perimeter in complex environment based on deep migration learning[J]. Chinese Journal of Scientific Instrument, 2019, 40(8): 12-19. https://www.cnki.com.cn/Article/CJFDTOTAL-YQXB201908002.htm
[13]	REN S, HE K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[14]	LIU W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector[C]//Proceedings of European Conference on Computer Vision, 2016: 21-37.