食品与发酵工业 >

2024 , Vol. 50 >Issue 24: 313 - 320

DOI: https://doi.org/10.13995/j.cnki.11-1802/ts.039633

分析与检测

基于电子鼻和机器视觉的鱼肉新鲜度检测研究

  • 袁也 ,
  • 周博 ,
  • 吴泽玮
展开
  • (盐城工学院 机械工程学院,江苏 盐城,224002)
第一作者:硕士研究生(周博副教授为通信作者,E-mail:zjzhobo@126.com)

收稿日期: 2024-04-19

  修回日期: 2024-05-28

  网络出版日期: 2024-12-30

基金资助

国家自然科学基金项目(22171239,31671583)

收起

Fish freshness detection based on an electronic nose and machine vision

  • YUAN Ye ,
  • ZHOU Bo ,
  • WU Zewei
Expand
  • (Department of Mechanical Engineering,Yancheng Institute of Technology, Yancheng 224002, China)

Received date: 2024-04-19

  Revised date: 2024-05-28

  Online published: 2024-12-30

Fold

摘要

为了提升鱼肉新鲜度检测的准确率,该研究采用了电子鼻、机器视觉和多数据融合技术快速地检测冷藏鱼肉的新鲜度。挥发性盐基氮含量与新鲜度密切相关且易于测量,因此被选定作为鱼肉新鲜度的指标;用机器视觉和电子鼻获取样品的图像和气味信息。应用反向传播神经网络、卷积神经网络(convolutional neural network,CNN)和卷积神经网络-门控循环单元-注意力(CNN-GRU-Attention)3种模型对鱼肉新鲜度进行3分类和7分类预测。结果表明,3分类和7分类实验中,3种模型利用电子鼻数据进行分类的效果均优于机器视觉方法。此外,对原始数据进行融合后,3个模型的分类准确率均有提升。特别是基于CNN-GRU-Attention模型的多感官数据融合方法在本次研究中效果最优,其在测试集上的准确率分别达97.61%和90.48%。研究结果表明,采用多感知检测技术结合CNN-GRU-Attention预测模型能够有效地提高鱼肉新鲜度检测的准确性。

关键词： 鱼肉新鲜度; 电子鼻; 机器视觉; 数据融合; 神经网络

本文引用格式

袁也 , 周博 , 吴泽玮 . 基于电子鼻和机器视觉的鱼肉新鲜度检测研究[J]. 食品与发酵工业, 2024 , 50(24) : 313 -320 . DOI: 10.13995/j.cnki.11-1802/ts.039633

Abstract

To improve the accuracy of fish freshness detection, electronic nose, machine vision, and multi-data fusion techniques were used to rapidly detect the freshness of refrigerated fish.Total volatile base nitrogen (TVB-N), which is closely related to freshness and is easy to measure, was selected as an indicator of fish freshness.Machine vision and electronic nose-acquired images as well as odor information were collected from samples.Three models, namely, the backpropagation neural network (BPNN), convolutional neural network (CNN), and convolutional neural network-gated recurrent unit-attention (CNN-GRU-Attention), were applied to fish freshness for 3-classification and 7-classification prediction.Results showed that the classification effect of the three models using the electronic nose data was better than that of the machine vision method, regardless of whether the application was 3-classification or 7-classification.In addition, the classification accuracy of the three models improved after the fusion of the original data.In particular, the multisensory data fusion method based on the CNN-GRU-Attention model performed the best in this study, with its accuracies on the test set reaching 97.61% and 90.48%, respectively.The results showed that multi-perception detection technology combined with the CNN-GRU-Attention prediction model could effectively improve the accuracy of fish freshness detection.

Key words： fish freshness; electronic nose; machine vision; data fusion; neural network

参考文献

[1] TACON A G J, LEMOS D, METIAN M.Fish for health:Improved nutritional quality of cultured fish for human consumption[J].Reviews in Fisheries Science & Aquaculture, 2020, 28(4):449-458.
[2] XIONG Y W, LI Y H, WANG C Y, et al.Non-destructive detection of chicken freshness based on electronic nose technology and transfer learning[J].Agriculture, 2023, 13(2):496-515.
[3] 王蓓, 沈飞, 何学明, 等.电子鼻同步检测花生霉菌及霉菌毒素[J].食品科学, 2022, 43(12):310-316.
WANG B, SHEN F, HE X M, et al.Simultaneous detection of harmful fungi and mycotoxin contamination in peanuts by electronic nose[J].Food Science, 2022, 43(12):310-316.
[4] LYU Y, YANG L, BU F Y, et al.Optimization of sensor array for detection of abalone freshness based on electronic tongue[J].Journal of New Materials for Electrochemical Systems, 2023, 26(1):94-100.
[5] DONG K, GUAN Y F, WANG Q, et al.Non-destructive prediction of yak meat freshness indicator by hyperspectral techniques in the oxidation process[J].Food Chemistry: X, 2023, 17:100541.
[6] 董鑫鑫, 杨方威, 于航, 等. 基于拉曼光谱技术的猪瘦肉新鲜度快速无损检测方法研究[J]. 光谱学与光谱分析, 2023, 43(2):484-488.
DONG X X, YANG F W, YU H, et al. Study on rapid nondestructive detection of pork lean freshness based on Raman spectroscopy[J]. Spectroscopy and Spectral Analysis, 2023, 43(2):484-488.
[7] CHEN J M, LU Y, YAN F, et al.A fluorescent biosensor based on catalytic activity of platinum nanoparticles for freshness evaluation of aquatic products[J].Food Chemistry, 2020, 310:125922.
[8] MUNEKATA P E S, FINARDI S, DE SOUZA C K, et al.Applications of electronic nose, electronic eye and electronic tongue in quality, safety and shelf life of meat and meat products:A review[J].Sensors, 2023, 23(2):672.
[9] 孙哲华, 孟庆浩, 靳荔成.基于小波变换的白酒检测电子鼻降噪方法研究[J].仪表技术与传感器, 2021(11):114-120.
SUN Z H, MENG Q H, JIN L C.Research on denoising of method electronic nose for liquor detection based on wavelet transform[J].Instrument Technique and Sensor, 2021(11):114-120.
[10] CHEN J, LIN B, ZHENG F J, et al.Characterization of the pure black tea wine fermentation process by electronic nose and tongue-based techniques with nutritional characteristics[J].ACS Omega, 2023, 8(13):12538-12547.
[11] 盛秀丽, 马刘峰, 方志刚, 等.基于电子鼻和HS-SPME-GC-MS技术分析9种新疆石榴果实挥发性成分[J].食品工业科技, 2023, 44(6):325-334.
SHENG X L, MA L F, FANG Z G, et al.Analysis of volatile components of nine Punica grcanatum L.cultivars grown in Xinjiang based on electronic nose and HS-SPME-GC-MS[J].Science and Technology of Food Industry, 2023, 44(6):325-334.
[12] 孙梦梦, 鞠皓, 姜洪喆, 等.水果成熟度无损检测技术研究进展[J].食品与发酵工业, 2023, 49(17):354-362.
SUN M M, JU H, JIANG H Z, et al.Research progress of nondestructive detection technology in fruit maturity[J].Food and Fermentation Industries, 2023, 49(17):354-362.
[13] 李思懿, 粘颖群, 谭建庄, 等.基于电子鼻快速检测生鲜猪肉的异味[J].食品工业科技, 2023, 44(20):338-348.
LI S Y, ZHAN Y Q, TAN J Z, et al.Application of electronic nose for rapid detection of off-flavour of raw pork[J].Science and Technology of Food Industry, 2023, 44(20):338-348.
[14] 李丽霞, 张浩, 林宇浩, 等.电子鼻结合GC-MS鉴别不同部位的三七粉[J].食品科学, 2023, 44(20):321-329.
LI L X, ZHANG H, LIN Y H, et al.Identification of Panax notoginseng powders from different root parts using electronic nose and GC-MS[J].Food Science, 2023, 44(20):321-329.
[15] 蔡雪梅, 何莲, 易宇文, 等.GC-MS结合电子鼻分析啤酒对啤酒鸭风味的影响[J].中国调味品, 2020, 45(7):158-163.
CAI X M, HE L, YI Y W, et al.Effect of beer on the volatile compounds of beer duck by electronic nose and GC-MS[J].China Condiment, 2020, 45(7):158-163.
[16] RAUDIENÉ E, GAILIUS D, VINAUSKIENÉ R, et al.Rapid evaluation of fresh chicken meat quality by electronic nose[J].Czech Journal of Food Sciences, 2018, 36(5):420-426.
[17] 丁楠. 电子鼻对自制灌肠制品货架期进行预测[J].食品工业, 2020, 41(8):288-290.
DING N.Prediction of shelf life of self-made enema products by electronic nose[J].The Food Industry, 2020, 41(8):288-290.
[18] CHEN J, GU J H, ZHANG R, et al.Freshness evaluation of three kinds of meats based on the electronic nose[J].Sensors, 2019, 19(3):605-616.
[19] 张茹, 张奋楠, 周星宇, 等.基于机器视觉的生鲜牛肉冷藏时间识别研究[J].食品与发酵工业, 2022, 48(18):75-80.
ZHANG R, ZHANG F G, ZHOU X Y, et al.Identification of the refrigerated time for chilled beef based on machine vision[J].Food and Fermentation Industries, 2022, 48(18):75-80.
[20] SHI Y Y, WANG X C, BORHAN M S, et al.A review on meat quality evaluation methods based on non-destructive computer vision and artificial intelligence technologies[J].Food Science of Animal Resources, 2021, 41(4):563-588.
[21] TAHERI-GARAVAND A, FATAHI S, OMID M, et al.Meat quality evaluation based on computer vision technique:A review[J].Meat Science, 2019, 156:183-195.
[22] ZHANG C J, ZHANG D Q, SU Y Y, et al.Research on the authenticity of mutton based on machine vision technology[J].Foods, 2022, 11(22):3732.
[23] 李振波, 李萌, 赵远洋, 等.基于改进VGG-19卷积神经网络的冰鲜鲳鱼新鲜度评估方法[J].农业工程学报, 2021, 37(22):286-294.
LI Z B, LI M, ZHAO Y Y, et al.Iced pomfret freshness evaluation method based on improved VGG-19 convolutional neural networks[J].Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(22):286-294.
[24] 李玉花, 史翰卿, 熊赟葳, 等.融合电子鼻和视觉技术的鸡肉新鲜度检测装置研究[J].农业机械学报, 2022, 53(11):433-440.
LI Y H, SHI H Q, XIONG Y W, et al.Research of chicken freshness detection device based on electeonic nose and vision technology[J].Transactions of the Chinese Society for Agricultural, 2022, 53(11):433-440.
[25] ZHAO C T, MA J, JIA W S, et al.An apple fungal infection detection model based on BPNN optimized by sparrow search algorithm[J].Biosensors, 2022, 12(9):692.
Options
文章导航

/

〈 〉

技术支持：北京玛格泰克科技发展有限公司