基于CNN-DBN的小麦不完善粒识别技术研究  

Research on unsound wheat kernels recognition technology based on CNN-DBN

作　　者：张庆辉[1] 田欣欣 吕鹏涛 杨彬[2] ZHANG Qinghui;TIAN Xinxin;LYU Pengtao;YANG Bin(College of Information Science and Engineering,Henan University of Technology,Zhengzhou 450001,China;Zhengzhou Institute of Science and Technology Information,Zhengzhou 450000,China)

机构地区：[1]河南工业大学信息科学与工程学院,河南郑州450001 [2]郑州市科学技术情报研究所,河南郑州450000

出　　处：《河南工业大学学报（自然科学版）》2022年第3期118-124,共7页Journal of Henan University of Technology：Natural Science Edition

基　　金：教育部粮食信息处理与控制重点实验室开放项目(KFJJ-2020-109)。

摘　　要：针对在实际应用场景下,小麦不完善粒识别数据较少所产生识别率不佳的问题,提出并实现了基于迁移学习的CNN-DBN小麦不完善粒识别方法。利用基于大型公开数据集ImageNet的预训练深度卷积神经网络(CNN)中的VGG-16、VGG-19和ResNet50进行小麦特征提取,将获取的特征加以融合并输送至深度信念网络(DBN)进行分类。结果表明:CNN和DBN结合的方法用于小麦不完善粒识别,其中迁移学习VGG-16+VGG-19+ResNet50-DBN模型性能最好,其测试准确率可达91.86%;CNN-DBN模型既避免了小麦复杂的特征提取步骤,又使不完善粒识别因数据集规模小而导致识别率不理想的问题得到了改善;特征融合的方法使提取到的小麦图像信息更加丰富、全面。CNN-DBN模型结合了有监督网络和无监督网络的优点,对高维数据有更好的分类能力,为小麦不完善粒识别提供了理论支持。The recognition of unsound wheat kernels is an important part of wheat quality inspection,and it is also a key indicator to measure wheat quality.Research on the recognition of unsound wheat kernels is of great significance to the correct evaluation of wheat quality.In recent years,researches on the recognition of unsound wheat kernels were mainly to directly optimize classical classification networks,and the problem of unsatisfactory recognition effect was often caused by insufficient wheat training dataset.Aiming at the problem of poor recognition rate due to insufficient recognition data of unsound wheat kernels in practical application scenarios,we designed and implemented a method for identifying unsound wheat kernels based on transfer learning CNN-DBN model.We used a jitter-type automatic feeding tray,a transparent carrier plate and a pair of high-definition industrial cameras to form an automatic wheat image acquisition device to obtain high-definition RGB images of wheat.Using the deep convolutional neural networks VGG-16,VGG-19 and ResNet50 pre-trained on the ImageNet dataset as feature extractors,the extracted wheat features were fused,and then classified by the deep belief network(DBN).We conducted experiments of single model,two-model fusion and three-model fusion,based on the performance of the three types of fusion models on the dataset,and finally chose the three-model fusion scheme with the best performance on the dataset.Meanwhile,the recognition results of each model using the softmax classifier and DBN as the classifier were compared.Finally,the transfer learning VGG-16+VGG-19+ResNet50-DBN model was selected as the model for this task.Experiments showed that the transfer learning VGG-16+VGG-19+ResNet50-DBN model was used to identify unsound wheat kernels,and its accuracy can reach 91.86%.The pre-trained models we use were trained on the large-scale dataset ImageNet.Because the scale of the ImageNet dataset was very large,these pre-trained models also had good generalization performance for imag

关 键 词：迁移学习 特征融合 卷积神经网络 深度信念网络 小麦不完善粒识别 

分 类 号：TS210[轻工技术与工程—粮食、油脂及植物蛋白工程]