食品与发酵工业 >

2026 , Vol. 52 >Issue 11: 416 - 427

DOI: https://doi.org/10.13995/j.cnki.11-1802/ts.043999

综述与专题评论

基于机器视觉的鱼体质量检测研究进展

  • 刘稼轩 ,
  • 高佳斌 ,
  • 吴文锦 ,
  • 陈胜 ,
  • 石柳 ,
  • 褚上 ,
  • 郭晓嘉 ,
  • 林家豪 ,
  • 汪兰 ,
  • 乔宇 ,
  • 熊光权 ,
  • 刘斌 ,
  • 陈朗
展开
  • 1(湖北工业大学 生命科学与健康工程学院, 湖北 武汉, 430068)
    2(湖北省农业科学院农产品加工与核农技术研究所, 湖北 武汉, 430072)
    3(宣恩县万寨乡农业技术服务中心, 湖北 恩施, 445503)
第一作者:第一作者:硕士研究生(陈朗助理研究员为通信作者,E-mail:chenlang@hbaas.ac.cn)

收稿日期: 2025-07-22

  修回日期: 2025-10-22

  网络出版日期: 2026-06-24

基金资助

湖北省重点研发计划项目(2023BBB115);湖北省农业科学院青年科学基金项目(2024NKYJJ28);湖北省农机装备补短板核心技术应用攻关项目(HBSNYT202221);武汉都市圈协同创新科技项目(2024070904020441)

收起

Research progress on fish quality inspection based on machine vision

  • LIU Jiaxuan ,
  • GAO Jiabin ,
  • WU Wenjin ,
  • CHEN Sheng ,
  • SHI Liu ,
  • CHU Shang ,
  • GUO Xiaojia ,
  • LIN Jiahao ,
  • WANG Lan ,
  • QIAO Yu ,
  • XIONG Guangquan ,
  • LIU Bin ,
  • CHEN Lang
Expand
  • 1(School of Life Science and Health Engineering, Hubei University of Technology, Wuhan 430068, China)
    2(Institute of Agro-products Processing and Nuclear-Agricultural Technology, Hubei Academy of Agricultural Sciences, Wuhan 430072, China)
    3(Wanzhai Township Agricultural Technology Service Center, Xuan’en County, Enshi 445503, China)

Received date: 2025-07-22

  Revised date: 2025-10-22

  Online published: 2026-06-24

Fold

摘要

质量作为鱼类主要可测量属性之一,是标准化分级、精深加工及市场价值评估的直接决定因素。随着计算机硬件技术和优化算法的高速发展,基于机器视觉的鱼体质量无损检测技术取得突破性进展,凭借精准高效的特点成为鱼体质量检测的有力工具。该文重点检索学术文献库包括中国知网、Web of Science、Food Science、IEEE Access、Computers and Electronics in Agriculture、Fisheries Research等,覆盖2015—2025年内的中英文期刊、会议以及学位论文,并通过文献整理和分析,系统构建了基于机器视觉的鱼体质量检测技术体系框架,针对该技术体系所涉及的图像采集、特征提取、质量预测等关键步骤进行了系统性总结,并对比分析了常见质量预测方法的优缺点及应用场景。最后,对鱼体质量预测方法的发展趋势进行了展望。

关键词： 机器视觉; 质量检测; 图像采集; 特征提取; 深度学习

本文引用格式

刘稼轩 , 高佳斌 , 吴文锦 , 陈胜 , 石柳 , 褚上 , 郭晓嘉 , 林家豪 , 汪兰 , 乔宇 , 熊光权 , 刘斌 , 陈朗 . 基于机器视觉的鱼体质量检测研究进展[J]. 食品与发酵工业, 2026 , 52(11) : 416 -427 . DOI: 10.13995/j.cnki.11-1802/ts.043999

Abstract

Body weight stands as a pivotal measurable attribute of fish, recognized as a decisive factor in standardized size grading systems, precision processing parameterization frameworks, and market value evaluation mechanisms.The rapid advancement of computer hardware and intelligent optimization algorithms demonstrates the potential to drive revolutionary progress in non-destructive weight detection technologies based on machine vision, establishing these systems as robust tools for aquatic product inspection due to their exceptional accuracy and operational efficiency.The study primarily searched multiple academic literature databases, including CNKI,Web of Science,Food Science,IEEE Access Computers and Electronics in Agriculture and Fisheries Research The comprehensive search covered Chinese and English journals,conference proceedings, and dissertations published from 2015 to 2025.Through a systematic review and synthesis of existing domestic and international literature, a complete technical architecture for machine vision-based fish weight assessment was constructed, comprising three core modules:image acquisition devices, feature extraction algorithms, and weight prediction models.High quality image acquisition and high-resolution image data are identified as fundamental prerequisites and critical guarantees for achieving precise weight measurements, leading researchers to compare the advantages, disadvantages, and application scenarios of various acquisition devices.Subsequently, the optimal application ranges of diverse feature extraction algorithms were analyzed, followed by a comparative evaluation of machine vision and deep learning technologies under current environmental conditions.Finally, the study presents concrete prospects and assessments regarding future development trends and research directions for fish weight prediction methodologies.

Key words： machine vision; weight detection; image acquisition; feature extraction; deep learning

参考文献

[1] 农业农村部渔业渔政管理局. 中国渔业统计年鉴-2024[M].北京:中国农业出版社, 2024.
Bureau of Fishery and Fisheries Administration, Ministry of Agriculture and Rural Affairs.2024 China Fisheries Statistical Yearbook[M].Beijing:China Agriculture Press, 2024.
[2] 王慧, 何鸿举, 刘璐, 等.高光谱成像在鱼肉品质无损检测中的研究进展[J].食品科学, 2019, 40(5):329-338.
WANG H, HE H J, LIU L, et al.Recent progress in hyperspectral imaging for nondestructive evaluation of fish quality[J].Food Science, 2019, 40(5):329-338.
[3] 黄晓琛, 张凯利, 刘元杰, 等.机器学习与计算机视觉技术在食品质量评价中的研究进展[J].食品科学, 2024, 45(12):1-10.
HUANG X C, ZHANG K L, LIU Y J, et al.Research progress on machine learning and computer vision technology in food quality evaluation[J].Food Science, 2024, 45(12):1-10.
[4] 杨泽青, 张明轩, 陈英姝, 等.基于机器视觉的表面缺陷检测方法研究进展[J].现代制造工程, 2023(4):143-156.
YANG Z Q, ZHANG M X, CHEN Y S, et al.Review of surface defect detection methods based on machine vision[J].Modern Manufacturing Engineering, 2023(4):143-156.
[5] KONOVALOV D A, SALEH A, EFREMOVA D B, et al.Automatic weight estimation of harvested fish from images[C].2019 Digital Image Computing:Techniques and Applications (DICTA).IEEE, 2020:1-7.
[6] MENG L, HIRAYAMA T, OYANAGI S.Underwater-drone with panoramic camera for automatic fish recognition based on deep learning[J].IEEE Access, 2018, 6:17880-17886.
[7] STURE Ø, ØYE E R, SKAVHAUG A, et al.A 3D machine vision system for quality grading of Atlantic salmon[J].Computers and Electronics in Agriculture, 2016, 123:142-148.
[8] 李文静. 多相机标定及三维重建技术研究[D].西安:西安理工大学, 2022.
LI W J.Research on multi-camera calibration and 3D reconstruction technology[D].Xi’an:Xi’an University of Technology, 2022.
[9] COOK D, MIDDLEMISS K, JAKSONS P, et al.Validation of fish length estimations from a high frequency multi-beam sonar (ARIS) and its utilisation as a field-based measurement technique[J].Fisheries Research, 2019, 218:59-68.
[10] ZHANG P, QIAO Y, JIN Y, et al.Upstream migration of fishes downstream of an under-construction hydroelectric dam and implications for the operation of fish passage facilities[J].Global Ecology and Conservation, 2020, 23:e01143.
[11] 马骏骁, 龚泽, 康家铭, 等.基于线激光扫描的鱼类定量切段方法[J].食品与机械, 2022, 38(10):87-92.
MA J X, GONG Z, KANG J M, et al.Research on quantitative fish segmentation method based on line laser scanning[J].Food & Machinery, 2022, 38(10):87-92.
[12] 叶东东, 徐霞, 丁玉庭.深度学习与机器视觉在鱼类加工与品质监测中的研究进展[J].食品与发酵工业, 2024, 50(22):389-398.
YE D D, XU X, DING Y T.Research progress on deep learning and machine vision for fish processing and quality monitoring[J].Food and Fermentation Industries, 2024, 50(22):389-398.
[13] 李莲, 郭晓亚.基于计算机视觉的鱼类分级方法的研究[J].内蒙古农业大学学报(自然科学版), 2015, 36(5):120-124.
LI L, GUO X Y.Research on fish classification method based on image processing[J].Journal of Inner Mongolia Agricultural University (Natural Science Edition), 2015, 36(5):120-124.
[14] 赵树昌. 基于机器视觉的苹果分级及表面损伤技术研究[D].杭州:浙江科技学院, 2023.
ZHAO S C.Apple grading and appearance damage detection based on vision[D].Hangzhou:Zhejiang University of Science and Technolog, 2023.
[15] 马常昊, 胡文惠, 钟海超, 等.融合Sobel算子的SAR图像结构优化方法[J].探测与控制学报, 2024, 46(2):119-124.
MA C H, HU W H, ZHONG H C, et al.SAR image structure optimization method using sobel operator fusion[J].Journal of Detection & Control, 2024, 46(2):119-124.
[16] 许四祥, 李天甲, 翟健健, 等.基于Prewitt算子的自适应弱小目标检测[J].红外技术, 2019, 41(2):189-193.
XU S X, LI T J, ZHAI J J, et al.Adaptive dim small target detection based on prewitt operator[J].Infrared Technology, 2019, 41(2):189-193.
[17] 李星军, 邵志伟, 梁嘉怡.基于Roberts算子的激光夜视图像自动分割方法[J].激光杂志, 2024, 45(5):110-114.
LI X J, SHAO Z W, LIANG J Y.Automatic segmentation method of laser night vision image based on Roberts operator[J].Laser Journal, 2024, 45(5):110-114.
[18] 李强, 赵峰, 许中平, 等.基于改进Canny算子的电气设备红外图像边缘检测算法[J].武汉大学学报(工学版), 2024, 57(12):1759-1765.
LI Q, ZHAO F, XU Z P, et al.Edge detection algorithm of infrared image of electrical equipment based on improved Canny operator[J].Engineering Journal of Wuhan University, 2024, 57(12):1759-1765.
[19] 周俊杰, 余建波.基于机器视觉的加工刀具磨损量在线测量[J].上海交通大学学报, 2021, 55(6):741-749.
ZHOU J J, YU J B.Online measurement of machining tool wear based on machine vision[J].Journal of Shanghai Jiao Tong University, 2021, 55(6):741-749.
[20] 朱明, 李梦珂, 万鹏, 等.基于鱼体特征点检测的淡水鱼种类识别[J].农业工程学报, 2023, 39(11):155-164.
ZHU M, LI M K, WAN P, et al.Identification of freshwater fish species based on fish feature point detection[J].Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(11):155-164.
[21] 李晓蒙. 基于语义部件模型的条斑鲨鱼体姿态估计方法研究[D].秦皇岛:燕山大学, 2021.
LI X M.Research on body pose estimation of White-spotted Bamboo Shark based on semantic component model[D].Qinhuangdao:Yanshan University, 2021.
[22] 康煜东. 基于单目相机的实时三维重建技术研究[D].西安:西安电子科技大学, 2024.
KANG Y D.Research on real-time 3D reconstruction technology based on monocular cameras[D].Xi’an:Xidian University, 2024.
[23] 李艳君, 黄康为, 项基.基于立体视觉的动态鱼体尺寸测量[J].农业工程学报, 2020, 36(21):220-226.
LI Y J, HUANG K W, XIANG J.Measurement of dynamic fish dimension based on stereoscopic vision[J].Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(21):220-226.
[24] ZHANG Z Y.Flexible camera calibration by viewing a plane from unknown orientations[C].Proceedings of the Seventh IEEE International Conference on Computer Vision.IEEE, 2002:666-673.
[25] 于跃龙, 魏修亭, 马泽, 等.基于图像识别的鱿鱼胴体三维重建方法研究[J].渔业现代化, 2025, 52(2):109-117.
YU Y L, WEI X T, MA Z, et al.Research on 3D reconstruction of squid carcass based on image recognition[J].Fishery Modernization, 2025, 52(2):109-117.
[26] 曾猛杰, 汪晨曦, 赖俊杰, 等.亚像素边缘检测算法综述[J].光学 精密工程, 2024, 32(23):3513-3524.
ZENG M J, WANG C X, LAI J J, et al.Review of sub-pixel edge detection algorithms[J].Optics and Precision Engineering, 2024, 32(23):3513-3524.
[27] 郑锦, 王森, 李航, 等.多关键点约束与深度估计辅助的单目3D目标检测算法[J].计算机学报, 2024, 47(12):2803-2818.
ZHENG J, WANG S, LI H, et al.A monocular 3D object detection algorithm with multi-keypoint constraints and depth estimation assistance[J].Chinese Journal of Computers, 2024, 47(12):2803-2818.
[28] 马启栋, 孔月萍, 李博宇, 等.水处理过程中的絮体图像纹理特征分析及应用[J].给水排水, 2023, 59(3):15-20.
MA Q D, KONG Y P, LI B Y, et al.Analysis and application of flocs image texture features in water treatment process[J].Water & Wastewater Engineering, 2023, 59(3):15-20.
[29] 杨航, 陈瑞, 安仕鹏, 等.深度学习背景下的图像三维重建技术进展综述[J].中国图象图形学报, 2023, 28(8):2396-2409.
YANG H, CHEN R, AN S P, et al.The growth of image-related three dimensional reconstruction techniques in deep learning-driven era:A critical summary[J].Journal of Image and Graphics, 2023, 28(8):2396-2409.
[30] 唐彦嵩, 徐锐豪, 王夙加.机器视觉在食品无损检测中的应用研究进展[J].中国食品学报, 2024, 24(12):13-27.
TANG Y S, XU R H, WANG S J.Research progress in the application of machine vision in food nondestructive detection[J].Journal of Chinese Institute of Food Science and Technology, 2024, 24(12):13-27.
[31] CONCHA-MEYER A, EIFERT J, WANG H J, et al.Volume estimation of strawberries, mushrooms, and tomatoes with a machine vision system[J].International Journal of Food Properties, 2018, 21(1):1867-1874.
[32] JEON Y, CHO H.Model based hybrid decision tree[J].Journal of the Korean Data and Information Science Society, 2019, 30(3):515-524.
[33] CHAUHAN V K, DAHIYA K, SHARMA A.Problem formulations and solvers in linear SVM:A review[J].Artificial Intelligence Review, 2019, 52(2):803-855.
[34] NISHIMURA J, KURODA T.Multiaxial haar-like feature and compact cascaded classifier for versatile recognition[J].IEEE Sensors Journal, 2010, 10(11):1786-1795.
[35] WU Y, MA W P, GONG M G, et al.A novel point-matching algorithm based on fast sample consensus for image registration[J].IEEE Geoscience and Remote Sensing Letters, 2015, 12(1):43-47.
[36] 马国强, 田云臣, 李晓岚.基于不规则图像面积测量的窄体舌鳎个体重量估计[J].微型机与应用, 2016, 35(16):67-71.
MA G Q, TIAN Y C, LI X L.Individual weight estimation of Cynoglossus gracilis based on measurement of irregular image area[J].Microcomputer & Its Applications, 2016, 35(16):67-71.
[37] 单佳楠, 郑晓伟.基于机器视觉技术的金鲳鱼质量预测研究[J].渔业现代化, 2023, 50(2):58-66.
SHAN J N, ZHENG X W.Weight prediction of golden pomfret based on machine vision technology[J].Fishery Modernization, 2023, 50(2):58-66.
[38] 刘清. 基于机器视觉的活体鳗鱼重量检测方法及试验研究[D].广州:华南农业大学, 2020.
LIU Q.The weight of live eel based on machine vision testing methods and experimental research[D].Guangzhou:South China Agricultural University, 2020.
[39] VARRÀ M O, HUSÁKOVÁ L, PATOČKA J, et al.Classification of transformed anchovy products based on the use of element patterns and decision trees to assess traceability and country of origin labelling[J].Food Chemistry, 2021, 360:129790.
[40] SABERIOON M, CÍSAŘ P.Automated within tank fish mass estimation using infrared reflection system[J].Computers and Electronics in Agriculture, 2018, 150:484-492.
[41] LOPEZ-TEJEIDA S, SOTO-ZARAZUA G M, TOLEDANO-AYALA M, et al.An improved method to obtain fish weight using machine learning and NIR camera with haar cascade classifier[J].Applied Sciences, 2022, 13(1):69.
[42] JANG Y, SEO Y S.Machine vision based fish cutting point prediction for target weight[J].Computers, Materials & Continua, 2023, 75(1):2247-2263.
[43] GANAIE M A, HU M H, MALIK A K, et al.Ensemble deep learning:A review[J].Engineering Applications of Artificial Intelligence, 2022, 115:105151.
[44] ZHU L L, SPACHOS P, PENSINI E, et al.Deep learning and machine vision for food processing:A survey[J].Current Research in Food Science, 2021, 4:233-249.
[45] MEI S H, JI J Y, HOU J H, et al.Learning sensor-specific spatial-spectral features of hyperspectral images via convolutional neural networks[J].IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(8):4520-4533.
[46] GEWERS F L, FERREIRA G R, DE ARRUDA H F, et al.Principal component analysis:A natural approach to data exploration[J].ACM Computing Surveys, 2022, 54(4):1-34.
[47] 江小辉, 孙翼飞, 郭维诚, 等.基于改进鸡群优化算法运动学与改进鸡群优化-Elman神经网络非运动学的机器人误差标定[J].信息与控制, 2024, 53(3):315-328.
JIANG X H, SUN Y F, GUO W C, et al.Robot error calibration based on improved CSO algorithm kinematics and improved CSO-Elman neural network non-kinematics[J].Information and Control, 2024, 53(3):315-328.
[48] 刘小刚, 李荣梅, 范诚, 等.基于语义分割的芒果表皮缺陷识别[J].华南农业大学学报, 2023, 44(1):134-141.
LIU X G, LI R M, FAN C, et al.Recognition of mango skin defect based on semantic segmentation[J].Journal of South China Agricultural University, 2023, 44(1):134-141.
[49] FERNANDES A F A, TURRA E M, DE ALVARENGA É R, et al.Deep Learning image segmentation for extraction of fish body measurements and prediction of body weight and carcass traits in Nile tilapia[J].Computers and Electronics in Agriculture, 2020, 170:105274.
[50] ZHANG L, WANG J P, DUAN Q L.Estimation for fish mass using image analysis and neural network[J].Computers and Electronics in Agriculture, 2020, 173:105439.
[51] 唐亚娅. 基于图像处理的鳙鱼分类及重量估计模型研究与系统开发[D].重庆:重庆大学, 2022.
TANG Y Y.Research and system development of bighead carp classification and weight estimation model based on image processing[D].Chongqing:Chongqing University, 2022.
[52] 赵丽清, 段东瑶, 殷元元, 等.基于PSO-Elman算法的茶叶烘干含水率预测[J].农业工程学报, 2021, 37(19):284-292.
ZHAO L Q, DUAN D Y, YIN Y Y, et al.Prediction of tea drying moisture content based on PSO Elman algorithm[J].Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(19):284-292.
[53] DE OLIVEIRA JUNIOR L A, MEDEIROS H R, MACÊDO D, et al.SegNetRes-CRF:A deep convolutional encoder-decoder architecture for semantic image segmentation[C].2018 International Joint Conference on Neural Networks (IJCNN).IEEE, 2018:1-6.
[54] CONG X Q, TIAN Y C, QUAN J N, et al.Machine vision-based estimation of body size and weight of pearl gentian grouper[J].Aquaculture International, 2024, 32(4):5325-5351.
[55] 王禹莎, 王家迎, 辛瑞, 等.基于计算机视觉的大黄鱼体尺、体重性状表型测量装置开发和应用[J].水产学报, 2023, 47(1):205-214.
WANG Y S, WANG J Y, XIN R, et al.Application of computer vision in morphological and body weight measurements of large yellow croaker(Larimichthys crocea)[J].Journal of Fisheries of China, 2023, 47(1):205-214.
[56] KARAKATSOULI N, MAVROMMATI M, KARELLOU E I, et al.Weight prediction of intensively reared gilthead seabream Sparus aurata from morphometric traits measured in images[J].Aquaculture International, 2024, 32(3):3675-3687.
[57] 段青玲, 张宇航, 孔铭瑞, 等.基于旋转目标检测和双目视觉的大闸蟹质量估算方法[J].农业机械学报, 2025, 56(6):575-584;672.
DUAN Q L, ZHANG Y H, KONG M R, et al.Weight estimation method for Chinese mitten crab based on oriented object detection and binocular vision[J].Transactions of the Chinese Society for Agricultural Machinery, 2025, 56(6):575-584;672.
[58] 周晓林, 马超, 王兆平, 等.基于机器视觉的鲤、鲫鱼性状测量系统的设计与实现[J].渔业现代化, 2022, 49(6):108-117.
ZHOU X L, MA C, WANG Z P, et al.Design and implementation of trait measurement system for common carp(Cyprinus carpio)and crucian carp(Carassius auratus)based on machine vision[J].Fishery Modernization, 2022, 49(6):108-117.
[59] 毕云峰, 周洪光, 修丽欣.一种水下鱼体质量测量方法及系统, 中国:CN114821118A[P].2022-07-29.
BI Y F, ZHOU H G, XIU L X.A method and system for measuring the mass of underwater fish bodies, China:CN114821118A[P].2022-07-29.
[60] 石晨, 刘越越, 吕婧, 等.一种水下鱼类无损测量方法与系统, 中国:CN117635689A[P].2024-03-01.
SHI C, LIU Y Y, LYU J, et al.An underwater fish non-destructive measurement method and system, China:CN117635689A[P].2024-03-01.
[61] 张璐, 郑亚澎, 刘尊续, 等.一种水下游动鱼体质量估算方法及系统, 中国:CN119205870A[P].2024-12-27.
ZHANG L, ZHENG Y P, LIU Z X, et al.A method and system for estimating the body mass of a swimming fish, China:CN119205870A[P].2024-12-27.
[62] 汪小旵, 武尧, 肖茂华, 等.水产养殖中智能识别技术的研究进展[J].华南农业大学学报, 2023, 44(1):24-33.
WANG X C, WU Y, XIAO M H, et al.Research progress of intelligent identification technology in aquaculture[J].Journal of South China Agricultural University, 2023, 44(1):24-33.
[63] 曾立华, 许春燕, 董心如, 等.基于深度学习多模态融合模型的鱼类生物量估算方法及系统, 中国:CN119271987A[P].2025-01-07.
ZENG L H, XU C Y, DONG X R, et al.Fish biomass estimation method and system based on deep learning multimodal fusion model, China:CN119271987A[P].2025-01-07.
[64] 王博彦. 基于Transformer的鱼体关键点检测算法研究[D].杭州:浙江大学, 2023.
WANG B Y.Research on transformer-based detection algorithm of key point of fish body[D].Hangzhou:Zhejiang University, 2023.
[65] DONG Y H, JIANG X, JIN Z, et al.Self-collaboration code generation via ChatGPT[J].ACM Transactions on Software Engineering and Methodology, 2024, 33(7):1-38.
Options
文章导航

/

〈 〉

技术支持：北京玛格泰克科技发展有限公司