基于EfficientNet网络模型的猪肉新鲜度智能识别方法  

An Intelligent Method for Pork Freshness Identification Based on EfficientNet Model

作　　者：刘超 张家瑜 戚超 黄继超 陈坤杰[1] LIU Chao;ZHANG Jiayu;QI Chao;HUANG Jichao;CHEN Kunjie(College of Engineering,Nanjing Agricultural University,Nanjing 210031,China;College of Intelligent Manufacturing,Taizhou Institute of Science and Technology,Nanjing University of Science and Technology,Taizhou 225300,China)

机构地区：[1]南京农业大学工学院,江苏南京210031 [2]南京理工大学泰州科技学院智能制造学院,江苏泰州225300

出　　处：《食品科学》2023年第24期369-376,共8页Food Science

基　　金：泰州市科技支撑计划(社会发展)项目指令计划项目(TS201918);江苏省苏北科技专项(SZ-HA2021035);江苏省“青蓝工程”优秀青年骨干教师项目(苏教师函[2022]51号)。

摘　　要：建立基于图像和EfficientNet框架的猪肉新鲜度测定方法。采集2 500张不同新鲜度的猪肉图片作为原始数据集,通过图像增强方式,构建总数为60 000张的猪肉新鲜度数据集。先用CIFAR-10数据集对EfficientNet进行训练,确定模型的基本结构及初始权值,然后用所构建的猪肉新鲜度数据集对模型进行训练和改进,使模型适用五分类问题。最后对所建立的模型进行测试和验证,并与Alexnet、VGG16和ResNet50目前主流的卷积神经网络模型进行比较。结果显示,在猪肉新鲜度识别方面,EfficientNet模型的平均正确识别率高达98.62%,明显优于Alexnet、VGG16和ResNet50模型,其中,EfficientNetB2模型的正确识别率达到99.22%,训练时间仅需157 min,综合性能最佳,是一种最适合猪肉新鲜度识别的方法。为提升模型泛化性,改进EfficientNetB2模型优化器算法,比较随机梯度下降、自适应矩估计)、均方根传播、校正自适应矩估计(rectified adaptive moment estimation,RAdam)4种优化器的性能。结果显示,采用RAdam优化器虽然没能进一步提高模型的准确率,但对提升模型的泛化能力有一定帮助,在工程应用上具有实际意义。A method for measuring pork freshness based on images and the EfficientNet framework was established.A total of 2500 images of pork with different freshness were collected as original dataset and processed by image enhancement to construct a new dataset of 60000 images.First,EfficientNet was trained with the CIFAR-10 dataset to determine the basic structure and initial weights of the model.Then,the model was trained and improved using the constructed dataset to make the model suitable forfive classification problems.Finally,the established model was tested,verified,and compared with the current mainstream convolutional neural network(CNN)models of Alexnet,VGG16 and ResNet50.The results showed that the average correct recognition rate of the EfficientNet model was as high as 98.62%,which was significantly better than that of the Alexnet,VGG16 and ResNet50 models.The correct recognition rate of the EfficientNetB2 model was 99.22%,and the training time was only 157 min.The comprehensive performance of the EfficientNetB2 model was the best,making it the most suitable method for pork freshness identification.In order to improve its generalization ability,the optimizer algorithm of the EfficientNetB2 model was improved,and the performances of stochastic gradient descent(SGD),adaptive moment estimation(Adam),root mean square propagation(RMSProp)and rectified adaptive moment estimation(RAdam)were compared.The results showed that the RAdam optimizer failed to further improve the accuracy of the model but instead helped to improve its generalization capability,which will of practical significance for engineering applications.

关 键 词：猪肉新鲜度 无损检测 深度学习 EfficientNet网络 

分 类 号：TS207.3[轻工技术与工程—食品科学]