[1]陈士进,丁冬,李泊,等.基于机器视觉的牛肉结缔组织特征和嫩度关系研究[J].南京农业大学学报,2016,39(5):865-871.[doi:10.7685/jnau.201511016]
 CHEN Shijin,DING Dong,LI Bo,et al.Research on relationship between beef connective tissue features and tenderness by computer vision technology[J].Journal of Nanjing Agricultural University,2016,39(5):865-871.[doi:10.7685/jnau.201511016]
点击复制

基于机器视觉的牛肉结缔组织特征和嫩度关系研究()
分享到:

《南京农业大学学报》[ISSN:1000-2030/CN:32-1148/S]

卷:
39卷
期数:
2016年5期
页码:
865-871
栏目:
出版日期:
2016-09-16

文章信息/Info

Title:
Research on relationship between beef connective tissue features and tenderness by computer vision technology
作者:
陈士进 丁冬 李泊 沈明霞 林盛业
南京农业大学工学院/江苏省现代设施农业技术与装备工程实验室, 江苏 南京 210031
Author(s):
CHEN Shijin DING Dong LI Bo SHEN Mingxia LIN Shengye
College of Engineering/Jiangsu Province Engineering Laboratory for Modern Facility Agriculture Technology & Equipment, Nanjing Agricultural University, Nanjing 210031, China
关键词:
牛肉嫩度结缔组织机器视觉图像处理Stepwise多元线性回归留一法交叉验证
Keywords:
beef tendernessconnective tissuecomputer visionimage processingStepwise-multiple linear regressions(Stepwise-MLR)Leave-one-out cross validation
分类号:
S818.9
DOI:
10.7685/jnau.201511016
摘要:
[目的] 嫩度是肉品质量的首要指标,其影响牛肉的消费和商业价值;寻找合适的嫩度指标,快速、无损、客观地预测牛肉嫩度一直是肉品学研究的热点之一。[方法] 本文基于机器视觉技术和图像处理方法,分割牛肉图像的肌间结缔组织区域,提取肌间结缔组织的特征参数,运用统计学方法关联该特征参数和熟肉剪切力值,结合经过专门训练的评级小组的分级,采用Stepwise多元线性回归(Stepwise-MLR)建模,对牛肉嫩度进行预测和分级。[结果] 70个样本图像的结缔组织特征数据全部用于训练模型,采用留一法交叉验证(Leave-one-out cross validation)测试模型,验证模型的牛肉嫩度判别系数(R2)为0.857,剩余标准误差(residual standard error,RSEC)为6.453;将牛肉分为嫩、中等、老3个等级,全部预测集的总体等级预测正确率为88.57%。[结论] 肌间结缔组织特征是预测牛肉嫩度的重要指标,本文所用的软硬件方法对牛肉嫩度的快速、无损、客观预测和分级具有一定的实用价值及指导意义。
Abstract:
[Objectives] Tenderness is the primary indicator of the meat quality. It influences the consumption and commercial value of the beef. Looking for suitable indicators of tenderness and predicting the tenderness with a rapid,non-destructive,and objective method has always been one of research focuses. [Methods] In this paper,the area of connective tissue between the muscles was segmented based on computer vision technology and image processing methods to extract features. Then statistical methods were used to find the relationship between characteristic parameters and cooked-beef shear force value. And combining with rating by a trained panel,the beef tenderness model was established by Stepwise-multiple linear regressions to predict cooked-beef tenderness and grading. [Results] The connective tissue feature data for 70 sample images were used to train and test sample tenderness model in a rotational leave-one-out scheme. Beef tenderness discrimination coefficient of the model R2 was 0.857,and RSEC was 6.453. Through cross validation,the beef was classified into tender,medium and tough groups with 88.57% classification accuracy. [Conclusions] Experimental results showed that image features of connective tissue between muscles were important indicators of beef tenderness. The hardware and software which was able to predict beef tenderness levels quickly and non-destructively had good practical value and guiding significance.

参考文献/References:

[1] Verbeke W,Wezemael L V,de Barcellos M D,et al. European beef consumers’ interest in a beef eating-quality guarantee:insights from a qualitative study in four EU countries[J]. Appetite,2010,54(2):289-296.
[2] Banovi Dc’ M,Grunert K G,Barreira M M,et al. Beef quality perception at the point of purchase:a study from Portugal[J]. Food Quality and Preference,2009,20(4):335-342.
[3] Robbins K,Jensen J,Ryan K J,et al. Consumer attitudes towards beef and acceptability of enhanced beef[J]. Meat Science,2003,65:721-729.
[4] van Wezemael L,de Smet S,Ueland ?,et al. Relationships between sensory evaluations of beef tenderness,shear force measurements and consumer characteristics[J]. Meat Science,2014,97:310-315.
[5] Grunert K G,Verbeke W,Kügler J O,et al. Use of consumer insight in the new product development process in the meat sector[J]. Meat Science,2011,89:251-258.
[6] Rodas-González A,Huerta-Leidenz N,Jerez-Timaure N,et al. Establishing tenderness thresholds of Venezuelan beef steaks using consumer and trained sensory panels[J]. Meat Science,2009,83:218-223.
[7] Jackman P,Sun D W,Allen P. Recent advances in the use of computer vision technology in the quality assessment of fresh meats[J]. Trends in Food Science & Technology,2011,22:185-197.
[8] McDonald T P,Chen Y R. Visual characterization of marbling in beef ribeyes and its relationship to taste parameters[J]. Trans ASAE,1991,34(6):2499-2504.
[9] Wulf D M,Connor S F O’,Tatum J D,et al. Using objective measures of muscle color to predict beef longissimus tenderness[J]. Journal of Animal Science,1997,75:684-692.
[10] Li J,Tan J,Shatadal P. Classification of tough and tender beef by image texture analysis[J]. Meat Science,2001,57:341-346.
[11] Li J,Tan J,Martz F A,et al. Image texture features as indicators of beef tenderness[J]. Meat Science,1999,53:17-22.
[12] Tan J L. Meat quality evaluation by computer vision[J]. Journal of Food Engineering,2004,61:27-35.
[13] Naganathan G K,Grimes L M,Subbiah J,et al. Visible/near-infrared hyperspectral imaging for beef tenderness prediction[J]. Computers and Electronics in Agriculture,2008,64:225-233.
[14] Sun X,Chen K J,Maddock-Carlin K R,et al. Predicting beef tenderness using color and multispectral image texture features[J]. Meat Science,2012,92:386-393.
[15] Purslow P P. The structure and functional significance of variations in the connective tissue within muscle[J]. Comparative Biochemistry and Physiology Part A,2002,133:947-966.
[16] Purslow P P. Intramuscular connective tissue and its role in meat quality[J]. Meat Science,2005,70:435-447.
[17] Girard I,Bruce H L,Basarab J A,et al. Contribution of myofibrillar and connective tissue components to the Warner-Bratzler-shear force of cooked beef[J]. Meat Science,2012,92:775-782.
[18] Dubost A,Micol D,Meunier B,et al. Relationships between structural characteristics of bovine intramuscular connective tissue assessed by image analysis and collagen and proteoglycan content[J]. Meat Science,2013,93:378-386.
[19] Dubost A,Micol D,Picard B,et al. Structural and biochemical characteristics of bovine intramuscular connective tissue and beef quality[J]. Meat Science,2013,95:555-561.
[20] Jabri M E,Abouelkaram S,Damez J L,et al. Image analysis study of the perimysial connective network,and its relationship with tenderness and composition of bovine meat[J]. Journal of Food Engineering,2010,96:316-322.
[21] Boles J A,Kohlbeck K S,Meyers M C,et al. The use of blood lactate concentration as an indicator of temperament and its impact on growth rate and tenderness of steaks from Simmental×Angus steers[J]. Meat Science,2015,103:68-74.
[22] 赵杰文,翟剑妹,刘木华,等. 牛肉嫩度的近红外光谱检测技术研究[J]. 光谱学与光谱分析,2006,26(4):640-642. Zhao J W,Zhai J M,Liu M H,et al. The determination of beef tenderness using near-infrared spectroscopy[J]. Spectroscopy and Spectral Analysis,2006,26(4):640-642(in Chinese with English abstract).
[23] Ohta Y,Kanade T,Sakai T. Color information for region segmentation[J]. Computer Graphics and Image Processing,1980,13(3):222-241.
[24] Kittler J,Devijver P A. An efficient estimator of pattern recognition system error probability[J]. Pattern Recognition,1981,13(3):245-249.

备注/Memo

备注/Memo:
收稿日期:2015-11-05
基金项目:国家现代农业(肉牛)产业技术体系项目(nycytx-38);农业科技成果转化资金项目(SQ2011ECC100043);国家自然科学基金项目(61503187)
作者简介:陈士进,博士研究生。
通信作者:沈明霞,教授,博导,主要从事计算机视觉与图像处理研究,E-mail:mingxia@njau.edu.cn。
更新日期/Last Update: 1900-01-01