Duck egg surface defect detection based on improved GoogLeNet

Authors

XIAO Wang, School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, Guangdong 510006, China
YANG Yu-jun, School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, Guangdong 510006, China
SHEN Qi-fang, School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, Guangdong 510006, China
SHAN Sen-sen, School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, Guangdong 510006, China
HUANG Yue, School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, Guangdong 510006, China

Abstract

A method of duck egg surface defect detection based on improved GoogLeNet （GoogLe Net-Mini） was proposed, and the other three neural networks include GoogLeNet, VGG16 and AlexNet were compared. The results showed that the accuracy of the four networks were 95.88%, 94.16%, 92.75% and 85.43% respectively. The detection accuracy of GoogLeNet-Mini for three kinds of duck eggs （normal, dirty and damaged） was 98.43%, 97.45% and 95.88% respectively. Compared with GoogLeNet, VGG16 and AlexNet, GoogLeNet-Mini had higher accuracy, better generalization and robustness, and the detection accuracy of three types of duck eggs can meet the production requirements. The detection range is applicable to duck eggs with more than 5% dirty area and more than 2% damaged area.

Publication Date

6-28-2021

First Page

162

Last Page

167

DOI

10.13652/j.issn.1003-5788.2021.06.027

Recommended Citation

Wang, XIAO; Yu-jun, YANG; Qi-fang, SHEN; Sen-sen, SHAN; and Yue, HUANG (2021) "Duck egg surface defect detection based on improved GoogLeNet," Food and Machinery: Vol. 37: Iss. 6, Article 27.
DOI: 10.13652/j.issn.1003-5788.2021.06.027
Available at: https://www.ifoodmm.cn/journal/vol37/iss6/27

References

[1] 俞玥, 张守丽, 李占明. 禽蛋品质无损检测及分级技术研究进展[J]. 食品安全质量检测学报, 2020, 11（23）: 8 740-8 745.
[2] 王栓巧, 郁志宏. 基于有限元法的禽蛋检测机构蛋壳破损率研究[J]. 食品与机械, 2017, 33（8）: 76-78, 84.
[3] 张魁, 彭佳伟, 李帅. 一种蛋品无损检测分拣装置及其蛋品声学信号采集单元: CN111642420A[P]. 2020-09-11.
[4] 吴林峰, 余怀鑫, 祝志慧. 基于机器视觉的孵化早期群体受精蛋鉴别[J]. 食品与机械, 2019, 35（4）: 152-156.
[5] 裴悦琨, 连明月, 姜艳超. 基于机器视觉的樱桃缺陷检测与识别[J]. 食品与机械, 2019, 35（12）: 137-140, 226.
[6] 高辉, 马国峰, 刘伟杰. 基于机器视觉的苹果缺陷快速检测方法研究[J]. 食品与机械, 2020, 36（10）: 125-129, 148.
[7] 程鸿芳, 张春友. 自然场景下基于改进LeNet卷积神经网络的苹果图像识别技术[J]. 食品与机械, 2019, 35（3）: 155-158.
[8] 杨志锐, 郑宏, 郭中原, 等. 基于网中网卷积神经网络的红枣缺陷检测[J]. 食品与机械, 2020, 36（2）: 140-145, 181.
[9] 王淑青, 黄剑锋, 张鹏飞, 等. 基于YOLOv4神经网络的小龙虾质量检测方法[J]. 食品与机械, 2021, 37（3）: 120-124, 194.
[10] 孙力, 蔡健荣, 林颢, 等. 基于声学特性的禽蛋裂纹实时在线检测系统[J]. 农业机械学报, 2011, 42（5）: 183-186.
[11] 陈诚, 强敏, 蔡健荣, 等. 禽蛋蛋壳裂纹在线检测系统设计[J]. 农业工程, 2020, 10（6）: 22-27.
[12] 魏萱, 何金成, 郑书河, 等. 基于图像纹理特征的土鸡蛋微裂纹无损检测[J]. 福建农林大学学报（自然科学版）, 2017, 46（6）: 716-720.
[13] 王巧华, 芦茜, 马美湖, 等. 基于机器视觉的产地脏污鸭蛋外形扁平度在线检测[J]. 中国食品学报, 2017, 17（5）: 200-207.
[14] NASIRI A, OMID M, TAHERI-GARAVAND A. An automatic sorting system for unwashed eggs using deep learning[J]. Journal of Food Engineering, 2020, 283（1）: 110036.
[15] 王伟男, 杨朝红. 基于图像处理技术的目标识别方法综述[J]. 电脑与信息技术, 2019, 27（6）: 9-15.
[16] 张继凯, 赵君, 张然, 等. 深度学习的图像实例分割方法综述[J]. 小型微型计算机系统, 2021, 42（1）: 161-171.
[17] 李德新. 基于Otsu阈值的MSI不连续破损边缘提取[J]. 计算机仿真, 2020, 37（9）: 358-362.
[18] 林成创, 单纯, 赵淦森, 等. 机器视觉应用中的图像数据增广综述[J]. 计算机科学与探索, 2021, 15（4）: 583-611.
[19] SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Boston: [s.n.], 2015: 1-9.
[20] 薛勇, 王立扬, 张瑜, 等. 基于GoogLeNet深度迁移学习的苹果缺陷检测方法[J]. 农业机械学报, 2020, 51（7）: 30-35.
[21] 薛晨兴, 张军, 邢家源. 基于GoogLeNet Inception V3的迁移学习研究[J]. 无线电工程, 2020, 50（2）: 118-122.
[22] 徐昭洪, 刘宇, 全吉成, 等. 基于VGG16预编码的遥感图像建筑物语义分割[J]. 科学技术与工程, 2019, 19（17）: 250-255.
[23] 陈立潮, 闫耀东, 张睿, 等. 融合迁移学习的AlexNet神经网络不锈钢焊缝缺陷分类[J/OL]. 智能系统学报. （2020-11-25）[2021-05-05]. http://kns.cnki.net/kcms/detail/23.1538.TP.20201125.1015.002.html.