摘要
机器视觉技术是一种无损、快速、经济的检测技术。结合国内外的相关研究现状,本文介绍了机器视觉系统的优点和对颜色、形状、尺寸等的检测方法,在此基础上,分别对机器视觉技术在包括鱼、虾、扇贝和牡蛎等水产食品感官检测方面的应用进行了详细阐述和讨论,此外,探究了机器视觉技术目前在水产食品感官检测领域应用的局限性及在深度学习方面的发展前景。本文旨在为水产食品的感官检测提供技术支撑,保障消费者的食用安全。
Machine vision technique is a non-destructive,fast and economical inspection technology.Based on a review of the current status of research on machine vision technique,the advantages of a machine vision system and the ways in which it is used to detect color,shape and size are presented in the present paper.On this basis,the application of machine vision technique is discussed and analyzed carefully in aquatic products such as fish,shrimp,scallops and oysters.In addition,the limitations of machine vision technique in the sensory detection of aquatic foods are pointed out and future development prospects in deep learning are discussed.The purpose of this paper is to provide technical support for sensory testing of aquatic foods to ensure consumer safety.
引文
[1]BALABAN M O.Quantifying nonhomogeneous colors in agricultural materials part I:method development[J].Journal of Food Science,2008,73(9):S431-S437.DOI:10.1111/j.1750-3841.2008.00807.x.
[2]GüMüS B,BALABAN M O.Prediction of the weight of aquacultured rainbow trout(Oncorhynchus mykiss)by image analysis[J].Journal of Aquatic Food Product Technology,2010,19(3/4):227-237.DOI:10.1080/10498850.2010.508869.
[3]SUN D W.Computer vision technology for food quality evaluation[M].Boston:Elsevier/Academic Press,2008:57-80.DOI:10.1016/B978-0-12-373642-0.X5001-7.
[4]RONNIE SARKAR N.Machine vision for quality control in the food industry[M]//FUNG D Y C.Instrumental methods for quality assurance in foods.New York:CRC Press,1991:166-188.DOI:10.1201/9780203750711.
[5]GUNASEKARAN S.Computer vision technology for food quality assurance[J].Trends in Food Science and Technology,1996,7(8):245-256.DOI:10.1016/0924-2244(96)10028-5.
[6]ANDREADIS I.Modelling and evaluating colour information for robot vision[J].Mechatronics,1999,9(4):429-446.DOI:10.1016/S0957-4158(99)00002-1.
[7]BALABAN M O,üNAL?ENGOR G F,SORIANO M G,et al.Quantification of gaping,bruising,and blood Spots in salmon fillets using image analysis[J].Journal of Food Science,2011,76(3):E291-E297.DOI:0.1111/j.1750-3841.2011.02060.x.
[8]HEIA K,SIVERTSEN A H,STORMO S K,et al.Detection of nematodes in cod(Gadus morhua)fillets by imaging spectroscopy[J].Journal of Food Science,2007,72(1):E011-E015.DOI:10.1111/j.1750-3841.2006.00212.x.
[9]YANG C C,CHAO K L,CHEN Y R.Development of multispectral image processing algorithms for identification of wholesome,septicemic,and inflammatory process chickens[J].Journal of Food Engineering,2005,69(2):225-234.DOI:10.1016/j.jfoodeng.2004.07.021.
[10]SUN D W.Computer vision:an objective,rapid and non-contact quality evaluation tool for the food industry[J].Journal of Food Engineering,2004,61(1):1-2.DOI:10.1016/S0260-8774(03)00182-1.
[11]BALABAN M O,KRISTINSSON H G,OTWELL W S.Evaluation of color parameters in a machine vision analysis of carbon monoxidetreated fish:part 1[J].Journal of Aquatic Food Product Technology,2005,14(2):5-24.DOI:10.1300/j030v14n02_02.
[12]BALABANM O,ODABASIA Z.Measuringcolor with machine vision[J].Food Technology,2006,60(12):32-36.DOI:10.1177/1082013206073046.
[13]GUMUS B,BALABAN M O,üNLUSAYIN M.Machine vision applications to aquatic foods:a review[J].Turkish Journal of Fisheries and Aquatic Sciences,2011,11(1):171-181.DOI:10.4194/trjfas.2010.0124.
[14]ZION B.The use of computer vision technologies in aquaculture:a review[J].Computers and Electronics in Agriculture,2012,88:125-132.DOI:10.1016/j.compag.2012.07.010.
[15]MATHIASSEN J R,JANSSON S,VELIYULIN E,et al.Automatic weight and quality grading of whole pelagic fish[C]//Nor-Fishing Technology Conference(NFTC)2006,Trondheim,Norway,2006:101-107.
[16]AGUIRRE H,AMEZCUA F,MADRID-VERA J,et al.Lengthweight relationship for 21 fish species from a coastal lagoon in the southwestern Gulf of California[J].Journal of Applied Ichthyology,2008,24(1):91-92.DOI:10.1111/j.1439-0426.2007.01043.x.
[17]NIETO-NAVA J T,ZETINA-REJóN M,ARREGUíN-SáNCHEZF,et al.Length-weight relationship of demersal fish from the eastern coast of the mouth of the gulf of California[J].Journal of Fisheries and Aquatic Science,2010,5(6):494-502.DOI:10.3923/jfas.2010.494.502.
[18]STURE?,?YE E R,SKAYHAUG A,et al.A 3D machine vision system for quality grading of Atlantic salmon[J].Computers&Electronics in Agriculture,2016,123:142-148.DOI:10.1016/j.compag.2016.02.020.
[19]SHI Ce,QIAN Jianping,HAN Shuai,et al.Developing a machine vision system for simultaneous prediction of freshness indicators based on tilapia(Oreochromis niloticus)pupil and gill color during storage at 4℃[J].Food Chemistry,2018,243:134-140.DOI:10.1016/j.foodchem.2017.09.047.
[20]ZHENG Hongyuan,ZHANG Rong,YANG Chunwei,et al.A method for real-time medaka(Oryzias latipes)detection base on machine vision technology[J].Applied Mechanics&Materials,2014,442:494-500.DOI:10.4028/www.scientific.net/amm.442.494
[21]RERKRATN A,KAEWPOONSUK A.System development for quality evaluation of fish fillet using image processing[C]//International Conference on Computer,Communications and Information Technology:CCIT 2014,Beijing,2014:196-199.
[22]DOWLATI M,MOHTASEBI S S,OMID M,et al.Freshness assessment of gilthead sea bream(Sparus aurata)by machine vision based on gill and eye color changes[J].Journal of Food Engineering,2013,119(2):277-287.DOI:0.1016/j.jfoodeng.2013.05.023.
[23]DOWLATI M,DE LA GUARDIA M,DOWLATI M,et al.Application of machine-vision techniques to fish-quality assessment[J].Trends in Analytical Chemistry,2012,40:168-179.DOI:10.1016/j.trac.2012.07.011.
[24]BALABAN M O.Quantifying nonhomogeneous colors in agricultural materials part I:method development[J].Journal of Food Science,2008,73(9):S431-S437.DOI:10.1111/j.1750-3841.2008.00807.x.
[25]LEóN K,MERY D,PEDRESCHI F,et al.Color measurement in L*a*b*from RGB digital images[J].Food Research International,2006,39(10):1084-1091.DOI:10.1016/j.foodres.2006.03.006.
[26]ROTARU C,GRAF T.Color image segmentation in HSI space for automotive applications[J].Journal of Real-Time Image Processing,2008,3(4):311-322.DOI:10.1007/s11554-008-0078-9.
[27]COSTA C,ANTONUCCI F,MENESATTI P,et al.An advanced colour calibration method for fish freshness assessment:a comparison between standard and passive refrigeration modalities[J].Food and Bioprocess Technology,2012,6(8):2190-2195.DOI:10.1007/s11947-011-0773-6.
[28]PAN P M,LI J P,LV G L,et al.Prediction of shelled shrimp weight by machine vision[J].Journal of Zhejiang University Science B,2009,10(8):589-594.DOI:10.1631/jzus.b0820364.
[29]ZHANG Dong,LILLYWHITE K D,LEE D J,et al.Automatic shrimp shape grading using evolution constructed features[J].Computers&Electronics in Agriculture,2014,100(2):116-122.DOI:10.1016/j.compag.2013.11.009.
[30]OSTERLOFF J,NILSSEN I,NATTKEMPER T W.A computer vision approach for monitoring the spatial and temporal shrimp distribution at the LoVe observatory[J].Methods in Oceanography,2016,15/16:114-128.DOI:10.1016/j.mio.2016.03.002.
[31]LUO Yan,ZHANG Anhong,CHENG Fang.Distilling the main skeleton line of shrimp based on machine vision technology[J].Science&Technology of Food Industry,2013,34(8):68-73.
[32]POONNOY P,CHUM-IN T.Estimation of sushi shrimp weight using image analysis technique and non-linear regression models[C]//Valencai:International Conference of Agricultural Engineering,2012:48-53.
[33]HOSSEINPOUR S,RAFIEE S,MOHTASEBI S S,et al.Application of computer vision technique for on-line monitoring of shrimp color changes during drying[J].Journal of Food Engineering,2013,115(1):99-114.DOI:10.1016/j.jfoodeng.2012.10.003.
[34]HE H,ADAMS R M,FARKAS D F,et al.Use of high-pressure processing for oyster shucking and shelf-life extension[J].Journal of Food Science,2002,67(2):640-645.DOI:10.1111/j.1365-2621.2002.tb10652.x.
[35]LEE D J,LANE R M,CHANG G H.Three-dimensional reconstruction for high-speed volume measurement[J].Proceedings of SPIE,2001,4189:258-267.DOI:10.1117/12.417201.
[36]MATHIASSEN J R,MISIMI E,TOLDNES B,et al.High speed weight estimation of whole herring(Clupea harengus)using 3Dmachine vision[J].Journal of Food Science,2011,76(6):E458-E464.DOI:10.1111/j.1750-3841.2011.02226.x.
[37]XIONG Guangming,LEE D J,MOON K R,et al.Shape similarity measure using turn angle cross-correlation for oyster quality evaluation[J].Journal of Food Engineering,2010,100(1):178-186.DOI:10.1016/j.jfoodeng.2010.03.043.
[38]LEE D J,XU X Q,RUBERT M L,et al.Shape analysis for an automatic oyster grading system[J].Proceedings of SPIE,2004,5606:27-36.DOI:10.1117/12.571783.
[39]LIN Aiguang,SUN Baoyuan,MA Xianying,et al.Study on detecting method of scallop direction guiding[J].Journal of Dalian University of Technology,2008,48(1):79-83.
[40]郭常有,曹广斌,韩世成,等.基于图像处理技术的扇贝尺寸及位置自动识别[J].大连海洋大学学报,2012,27(6):578-582.DOI:10.3969/j.issn.2095-1388.2012.06.017.
[41]王帅.视频中扇贝图像的检测与定位研究[D].大连:大连海洋大学,2015:30-34.DOI:10.7666/d.D675290.
[42]BROSNAN T,SUN D W.Improving quality inspection of food products by computer vision:a review[J].Journal of Food Engineering,2004,61(1):3-16.DOI:10.1016/S0260-8774(03)00183-3.
[43]GUNASEKARAN S.Computer vision technology for food quality assurance[J].Trends in Food Science and Technology,1996,7(8):245-256.DOI:10.1016/0924-2244(96)10028-5.
[44]STOCKMAN G,SHAPIRO L G.Computer vision[M].New Jersey:Prentice Hall PTR Upper Saddle River,2001:7-8.DOI:10.1006/cviu.1993.1034.
[45]QUEVEDO R A,AGUILERA J M,PEDRESCHI F.Color of salmon fillets by computer vision and sensory panel[J].Food and Bioprocess Technology,2010,3(5):637-643.DOI:10.1007/s11947-008-0106-6.