基于卷积神经网络的熟化鱼肉纤维程度评价方法研究  

Evaluation of Fiber Degree for Cooked Fish Muscle Based on the Convolutional Neural Network

作　　者：俞军华 朱金林 闫博文[1,3] 焦熙栋 黄建联[2,4,5] 范大明 Yu Junhua;Zhu Jinlin;Yan Bowen;Jiao Xidong;Huang Jianlian;Fan Daming(State Key Laboratory of Food Science and Resources,Jiangnan University,Wuxi 214122,Jiangsu;Key Laboratory of Refrigeration and Conditioning Aquatic Products Processing,Ministry of Agriculture and Rural Affairs,Xiamen 361022,Fujian;School of Food Science and Technology,Jiangnan University,Wuxi 214122,Jiangsu;Fujian Provincial Key Laboratory of Refrigeration and Conditioning Aquatic Products Processing,Xiamen 361022,Fujian;Anjoy Foods Group Co.,Ltd.,Xiamen 361022,Fujian)

机构地区：[1]江南大学食品科学与资源挖掘全国重点实验室,江苏无锡214122 [2]农业农村部水产加工冷藏与调理重点实验室,福建厦门361022 [3]江南大学食品学院,江苏无锡214122 [4]福建省冷冻调理水产品加工重点实验室,福建厦门361022 [5]安井食品集团股份有限公司,福建厦门361022

出　　处：《中国食品学报》2023年第9期252-260,共9页Journal of Chinese Institute Of Food Science and Technology

基　　金：“十三五”国家重点研发计划“蓝色粮仓”重点专项(2019YFD0902000):江苏省农业科技自主创新基金项目(CX(21)2040)。

摘　　要：为了打破熟化鱼肉纤维口感无系统性评价方法的局面,基于卷积神经网络构建熟化鱼肉纤维程度的评价方法。通过对不同纤维程度的熟化鱼肉样品进行微观图片采集,建立数据集。数据集按8∶2的比例随机分为训练集和测试集。构建的模型在训练集上训练,然后用测试集评估其识别性能。结果表明,在网络深度的选择时,34层的ResNet模型在收敛速度和准确率上均胜出;4种不同深度的ResNet模型在最佳识别准确率上都优于AlexNet、VGG-16和GoogLeNet模型;ResNet-34的准确性、精度、灵敏度、特异性和AUC的平均值分别为96.94%,91.26%,91.00%,98.13%和99.19%,表明基于ResNet-34模型搭建的评价方法能够客观、准确地识别熟化鱼肉纤维程度。An evaluation method for cooked fish fiber degree was constructed based on the convolutional neural network in order to break the situation that there was no systematic evaluation method for cooked fish fiber taste.A dataset was established by collecting microscopic images of cooked fish samples with different fiber degrees.The dataset was randomly divided into training dataset and testing dataset in the ratio of 8∶2.The constructed models were trained on the training dataset and their recognition performance were evaluated by the testing dataset.The result showed that the 34-layer ResNet model win in convergence speed and accuracy when choosing network depth.Four ResNet models with different depths were better than AlexNet,VGG-16 and GoogLeNet models in the best recognition accuracy.The average accuracy,precision,sensitivity and specificity and AUC of ResNet-34 were 96.94%,91.26%,91.00%,98.13%and 99.19%,respectively,which proved that the evaluation method based on ResNet-34 model could objectively and accurately identify the degree of cooked fish fiber.

关 键 词：熟化鱼肉 纤维程度 卷积神经网络 ResNet 

分 类 号：TS254.1[轻工技术与工程—水产品加工及贮藏工程] TP183[轻工技术与工程—食品科学与工程]