Rapid Detection of Astaxanthin in Antarctic Krill Meal by Computer Vision Combined with Convolutional Neural Network

ZHANG Quantong; ZHENG Yao; YANG Liu; ZHANG Shuaishuai; GUO Quanyou

doi:10.13386/j.issn1002-0306.2024030200

Volume 46 Issue 3

Jan. 2025

Turn off MathJax

Article Contents

Abstract

References

Supplements

Science and Technology of Food Industry > 2025 > 46(3): 11-18. > DOI: 10.13386/j.issn1002-0306.2024030200

ZHANG Quantong, ZHENG Yao, YANG Liu, et al. Rapid Detection of Astaxanthin in Antarctic Krill Meal by Computer Vision Combined with Convolutional Neural Network[J]. Science and Technology of Food Industry, 2025, 46(3): 11−18. (in Chinese with English abstract). doi: 10.13386/j.issn1002-0306.2024030200.

Citation:

PDF (4428 KB)

Rapid Detection of Astaxanthin in Antarctic Krill Meal by Computer Vision Combined with Convolutional Neural Network

ZHANG Quantong^{1, 2, 3,},
ZHENG Yao^{2, 3},
YANG Liu^{2, 3},
ZHANG Shuaishuai^{2, 3},
GUO Quanyou^{1, 2, 3, ,}

1.
College of Food Science and Technology, Shanghai Ocean University, Shanghai 201306, China
2.
Key Laboratory of Oceanic and Polar Fisheries, Ministry of Agriculture and Rural Affairs, East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, China
3.
Laoshan Laboratory, Qingdao 266061, China

More Information

Received Date: March 13, 2024
Available Online: November 28, 2024

Graphical Abstract

Abstract

Abstract

To achieve rapid detection of astaxanthin content in Antarctic krill meal, a determination method for astaxanthin content in krill meal was established using computer vision and convolutional neural networks. A total of 70 Antarctic krill meal samples were analyzed using high-performance liquid chromatography to determine their astaxanthin contents as label, and corresponding images of the samples were acquired using a computer vision system to form the dataset and the dataset was augmented. The model was built using the TensorFlow learning framework. The 5-fold cross-validation was used to tune and evaluate the model and select the optimal parameter model. The optimal parameter model was evaluated by randomly dividing the dataset, and 30 images from the dataset were randomly selected for model validation. The results showed that the optimal hyperparameters model with a root mean square error (RMSE) of 3.59 was preserved through a five-fold cross-validation. For model evaluation, the model was repeated three times. The mean values of the coefficient of determination (R²), mean absolute error (MAE), mean square error (MSE), and RMSE for the test set were 0.9626, 1.49, 4.22, and 2.05, respectively. For model validation, the relative errors ranged from 0.10% to 6.46%, indicating small deviations between the predictions and the observations. The astaxanthin content prediction model demonstrated high accuracy, enabling quick and nondestructive detection of astaxanthin content in krill meal samples.
- computer vision,
- convolutional neural network,
- Antarctic krill,
- astaxanthin,
- rapid detection

FullText(HTML)

References (40)

References

[1]	SHI J, SUN X, WANG Y, et al. Foodomics reveals altered lipid and protein profiles of Antarctic krill (Euphausia superba) under different processing[J]. Food Bioscience, 2023, 53:102565.
[2]	杨柳, 王鲁民, 周国燕, 等. 南极磷虾粉的加工工艺、品质特性与应用研究进展[J]. 海洋渔业,2022,44(4):501−512. [YANG L, WANG L M, ZHOU G Y, et al. Processing technology, quality characteristics and application status of Antarctic krill powder[J]. Marine Fisheries,2022,44(4):501−512.] doi: 10.3969/j.issn.1004-2490.2022.04.011 YANG L, WANG L M, ZHOU G Y, et al. Processing technology, quality characteristics and application status of Antarctic krill powder[J]. Marine Fisheries, 2022, 44（4）: 501−512. doi: 10.3969/j.issn.1004-2490.2022.04.011
[3]	邵晨. 船上加工处理对南极磷虾保藏的初步研究[D]. 上海:上海海洋大学, 2022. [SHAO C. Preliminary study on preservation of Antarctic krill by shipboard processing[D]. Shanghai:Shanghai Ocean University, 2022.] SHAO C. Preliminary study on preservation of Antarctic krill by shipboard processing[D]. Shanghai: Shanghai Ocean University, 2022.
[4]	LANDYMORE C, DURANCE T D, SINGH A, et al. Comparing different dehydration methods on protein quality of krill (Euphausia pacifica)[J]. Food Research International,2018,119:276−282.
[5]	赵昕源. 南极磷虾粉加工过程中主要营养活性物质的流向与结构分析[D]. 上海:上海海洋大学, 2022. [ZHAO X Y. Flow direction and structure analysis of main nutrient active substances during processing of Euphausia superba meal[D]. Shanghai:Shanghai Ocean University, 2022.] ZHAO X Y. Flow direction and structure analysis of main nutrient active substances during processing of Euphausia superba meal[D]. Shanghai: Shanghai Ocean University, 2022.
[6]	XIE D, GONG M Y, WEI W, et al. Antarctic krill (Euphausia superba) oil:A comprehensive review of chemical composition, extraction technologies, health benefits, and current applications[J]. Comprehensive Reviews in Food Science and Food Safety,2019,18(2):514−534. doi: 10.1111/1541-4337.12427
[7]	LIU Y, CONG P, LI B, et al. Effect of thermal processing towards lipid oxidation and non-enzymatic browning reactions of Antarctic krill (Euphausia superba) meal[J]. Journal of the Science of Food and Agriculture,2018,98(14):5257−5268. doi: 10.1002/jsfa.9064
[8]	MARTíNEZ-DELGADO A A, KHANDUAL S, VILLANUEVA–RODRíGUEZ S J. Chemical stability of astaxanthin integrated into a food matrix:Effects of food processing and methods for preservation[J]. Food Chemistry,2017,225:23−30. doi: 10.1016/j.foodchem.2016.11.092
[9]	孙伟红, 邢丽红, 冷凯良, 等. 高效液相色谱法测定南极磷虾及其制品中虾青素的含量[J]. 食品安全质量检测学报,2017,8(4):1248−1253. [SUN W H, XING L H, LENG K L, et al. Determination of astaxanthin in Antarctic krill and its products by high performance liquid chromatography[J]. Journal of Food Safety and Quality,2017,8(4):1248−1253.] SUN W H, XING L H, LENG K L, et al. Determination of astaxanthin in Antarctic krill and its products by high performance liquid chromatography[J]. Journal of Food Safety and Quality, 2017, 8（4）: 1248−1253.
[10]	LIU Y, PU H, SUN D-W. Efficient extraction of deep image features using convolutional neural network (CNN) for applications in detecting and analysing complex food matrices[J]. Trends in Food Science & Technology,2021,113:193−204.
[11]	CONG X Y, MIAO J K, ZHANG H Z, et al. Effects of drying methods on the content, structural isomers, and composition of astaxanthin in Antarctic krill[J]. Acs Omega,2019,4(19):17972−17980. doi: 10.1021/acsomega.9b01294
[12]	魏荣男, 沈建, 谈佳玉, 等. 热处理对南极磷虾品质特性及虾粉得率的影响[J]. 海洋渔业,2018,40(2):235−241. [WEI R N, SHEN J, TAN J Y, et al. The effect of heat treatment on the Antarctic krill quality and yield rate of krill powder[J]. Marine Fisheries,2018,40(2):235−241.] doi: 10.3969/j.issn.1004-2490.2018.02.013 WEI R N, SHEN J, TAN J Y, et al. The effect of heat treatment on the Antarctic krill quality and yield rate of krill powder[J]. Marine Fisheries, 2018, 40（2）: 235−241. doi: 10.3969/j.issn.1004-2490.2018.02.013
[13]	LU F S H, BRUHEIM I, ALE M T, et al. The effect of thermal treatment on the quality changes of Antartic krill meal during the manufacturing process:High processing temperatures decrease product quality[J]. European Journal of Lipid Science and Technology,2014,117(4):411−420.
[14]	ZHANG Y, TAKAHAMA K, OSAWA Y, et al. Characteristics of LED light-induced geometrical isomerization and degradation of astaxanthin and improvement of the color value and crystallinity of astaxanthin utilizing the photoisomerization[J]. Food Research International,2023,174:113553. doi: 10.1016/j.foodres.2023.113553
[15]	SANTOS PEREIRA L F, BARBON S, JR. , VALOUS N A, et al. Predicting the ripening of papaya fruit with digital imaging and random forests[J]. Computers and Electronics in Agriculture,2018,145:76−82. doi: 10.1016/j.compag.2017.12.029
[16]	李聪, 李玉洁, 李小占, 等. 基于机器视觉的红枣外部品质检测技术研究进展[J]. 食品工业科技,2022,43(20):447−453. [LI C, LI Y J, LI X Z, et al. Research progress on external quality detection and classification technology of jujube based on machine vision[J]. Science and Technology of Food Industry,2022,43(20):447−453.] LI C, LI Y J, LI X Z, et al. Research progress on external quality detection and classification technology of jujube based on machine vision[J]. Science and Technology of Food Industry, 2022, 43（20）: 447−453.
[17]	SU Q, KONDO N, RIZA D F A, et al. Potato quality grading based on depth imaging and convolutional neural network[J]. Journal of Food Quality,2020,2020:8815896.
[18]	WANG C, LIU Y, XIA Z, et al. Convolutional neural network‐based portable computer vision system for freshness assessment of crayfish (Prokaryophyllus clarkii)[J]. Journal of Food Science,2022,87(12):5330−5339. doi: 10.1111/1750-3841.16377
[19]	GILA A, BEJAOUI M A, BELTRAN G, et al. Rapid method based on computer vision to determine the moisture and insoluble impurities content in virgin olive oils[J]. Food Control,2020,113:107210. doi: 10.1016/j.foodcont.2020.107210
[20]	FERNANDES D D D S, ROMEO F, KREPPER G, et al. Quantification and identification of adulteration in the fat content of chicken hamburgers using digital images and chemometric tools[J]. LWT-Food Science and Technology, 2019, 100:20−27.
[21]	PAULINE O, SUMING C, CHAO-YIN T, et al. A non-destructive methodology for determination of cantaloupe sugar content using machine vision and deep learning[J]. Journal of the Science of Food and Agriculture,2022,102(14):6586−6595. doi: 10.1002/jsfa.12024
[22]	中华人民共和国农业农村部. 水产品及其制品中虾青素含量的测定高效液相色谱法:SC/T 3053-2019[S]. 北京:中国农业出版社, 2019:1. [Ministry of Agriculture and Rural Affairs of the People's Republic of China. Determination of astaxanthin in fish and fishery products by high performance liquid chromatography method:SC/T 3053-2019[S]. Beijing:China Agriculture Press, 2019:1.] Ministry of Agriculture and Rural Affairs of the People's Republic of China. Determination of astaxanthin in fish and fishery products by high performance liquid chromatography method: SC/T 3053-2019[S]. Beijing: China Agriculture Press, 2019: 1.
[23]	VIDAL M, GARCIA-ARRONA R, BORDAGARAY A, et al. Simultaneous determination of color additives tartrazine and allura red in food products by digital image analysis[J]. Talanta,2018,184:58−64. doi: 10.1016/j.talanta.2018.02.111
[24]	WANG C, LIU S, WANG Y, et al. Application of convolutional neural network-based detection methods in fresh fruit production:A comprehensive review[J]. Frontiers in Plant Science, 2022, 13.
[25]	杜紫燕, 徐杰, 熊菁晶, 等. 南极磷虾粉贮藏过程中品质变化研究[J]. 食品工业科技,2018,39(9):267−271,277. [DU Z Y, XU J, XIONG J J, et al. Effect of storage conditions on the quality of Antarctic krill meal[J]. Science and Technology of Food Industry,2018,39(9):267−271,277.] DU Z Y, XU J, XIONG J J, et al. Effect of storage conditions on the quality of Antarctic krill meal[J]. Science and Technology of Food Industry, 2018, 39（9）: 267−271,277.
[26]	BAI Y, XIONG Y, HUANG J, et al. Accurate prediction of soluble solid content of apples from multiple geographical regions by combining deep learning with spectral fingerprint features[J]. Postharvest Biology and Technology,2019,156:110943. doi: 10.1016/j.postharvbio.2019.110943
[27]	LI J, ZHU Z, LIU H, et al. Strawberry R-CNN:Recognition and counting model of strawberry based on improved faster R-CNN[J]. Ecological Informatics, 2023:102210.
[28]	GU J, WANG Z, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern Recognition,2018,77:354−377. doi: 10.1016/j.patcog.2017.10.013
[29]	ZHANG Q, ZHUO L, LI J, et al. Vehicle color recognition using multiple-layer feature representations of lightweight convolutional neural network[J]. Signal Processing,2018,147:146−153. doi: 10.1016/j.sigpro.2018.01.021
[30]	COTRIM W D S, MINIM V P R, FELIX L B, et al. Short convolutional neural networks applied to the recognition of the browning stages of bread crust[J]. Journal of Food Engineering,2020,277:109916. doi: 10.1016/j.jfoodeng.2020.109916
[31]	LI Z, LIU F, YANG W, et al. A survey of convolutional neural networks:Analysis, applications, and prospects[J]. Ieee Transactions on Neural Networks and Learning Systems,2022,33(12):6999−7019. doi: 10.1109/TNNLS.2021.3084827
[32]	NASIRI A, OMID M, TAHERI-GARAVAND A. An automatic sorting system for unwashed eggs using deep learning[J]. Journal of Food Engineering,2020,283:110036. doi: 10.1016/j.jfoodeng.2020.110036
[33]	张润泽, 冯国红, 付晟宏, 等. 基于CNN-GRU-AE的蓝莓货架期预测模型研究[J]. 食品科学,2024,45(13):229−238. [ZHANG R Z, FENG G H, FU S H, et al. Research on blueberry shelf-life prediction model based on CNN-GRU-AE[J]. Food Science,2024,45(13):229−238.] doi: 10.7506/spkx1002-6630-20231208-071 ZHANG R Z, FENG G H, FU S H, et al. Research on blueberry shelf-life prediction model based on CNN-GRU-AE[J]. Food Science, 2024, 45（13）: 229−238. doi: 10.7506/spkx1002-6630-20231208-071
[34]	占可, 陈季旺, 徐言, 等. 基于近红外光谱特征的冷冻小龙虾鲜度快速检测方法[J]. 食品科学,2024,45(2):299−307. [ZHAN K, CHEN JW, XU Y, et al. Rapid detection method for freshness of crayfish during freezing storage:Based on near-infrared spectroscopy[J]. Food Science,2024,45(2):299−307.] doi: 10.7506/spkx1002-6630-20230418-177 ZHAN K, CHEN JW, XU Y, et al. Rapid detection method for freshness of crayfish during freezing storage: Based on near-infrared spectroscopy[J]. Food Science, 2024, 45（2）: 299−307. doi: 10.7506/spkx1002-6630-20230418-177
[35]	YU S, LAN H, LI X, et al. Prediction method of shelf life of damaged Korla fragrant pears[J]. Journal of Food Process Engineering,2021,44:e13902. doi: 10.1111/jfpe.13902
[36]	GAO Q, WANG P, NIU T, et al. Soluble solid content and firmness index assessment and maturity discrimination of Malus micromalus Makino based on near-infrared hyperspectral imaging[J]. Food Chemistry,2021,370:131013.
[37]	KARUNASINGHA D S K. Root mean square error or mean absolute error? Use their ratio as well[J]. Information Sciences,2022,585:609−629. doi: 10.1016/j.ins.2021.11.036
[38]	QI J, DU J, SINISCALCHI S M, et al. On mean absolute error for deep neural network based vector-to-vector regression[J]. IEEE Signal Processing Letters,2020,27:1485−1489. doi: 10.1109/LSP.2020.3016837
[39]	耿金峰, 张惠敏, 杨建强, 等. 雨生红球藻中虾青素含量的快速测定方法[J]. 食品研究与开发,2016,37(12):125−128. [GENG J F, ZHANG H M, YANG J Q, et al. A method for rapid determination of astaxanthin from Haematococcus pluvialis[J]. Food Research and Development,2016,37(12):125−128.] doi: 10.3969/j.issn.1005-6521.2016.12.029 GENG J F, ZHANG H M, YANG J Q, et al. A method for rapid determination of astaxanthin from Haematococcus pluvialis[J]. Food Research and Development, 2016, 37（12）: 125−128. doi: 10.3969/j.issn.1005-6521.2016.12.029
[40]	LIU J, BI J, LIU X, et al. Modelling and optimization of high-pressure homogenization of not-from-concentrate juice:Achieving better juice quality using sustainable production[J]. Food Chemistry,2021,370:131058.

Supplements (1)

Supplements
Other Related Supplements

Get Citation

PDF

XML

Article Metrics

Article views (45) PDF downloads (4)

Science and Technology of Food Industry

Rapid Detection of Astaxanthin in Antarctic Krill Meal by Computer Vision Combined with Convolutional Neural Network

Abstract

References

Supplements

Other Related Supplements

Catalog

Article Metrics

Export File

Citation

Format

Content