基于Enhanced VGG16的油茶品种分类

被引：8

作者：

孟志超 ^{[1
]}

贺磊盈 ^{[1
,2
]}

杜小强 ^{[1
,2
]}

张国凤 ^{[1
,2
]}

姚小华 ^{[3
]}

吴顺凯 ^{[1
]}

郭豪鉴 ^{[1
]}

机构：

[1] 浙江理工大学机械与自动控制学院

[2] 中国林业科学研究院亚热带林业研究所

[3] 浙江省种植装备技术重点实验室

来源：

农业工程学报 | 2022年 / 10期

基金：

国家重点研发计划;

关键词：

深度学习; 油茶叶; 分类; Enhanced VGG16; hard-Swish; ReLU6;

D O I：

暂无

中图分类号：

S794.4 [油茶];

学科分类号：

0829 ; 0907 ;

摘要：

随着油茶产业不断壮大，市场上也出现了油茶幼苗品系混乱、以假乱真、以次充好的现象，因此急需开发一种专门的分类识别算法实现不同油茶品种的准确识别。农业领域常用VGG、ResNet网络模型进行分类工作，但存在权重空间过大和准确率不高等问题。该研究对VGG16网络模型进行层间删减以及结构调整，提出了Enhanced VGG16网络模型，在油茶叶数据集上完成模型训练与测试，并与现有经典卷积神经网络（AlexNet、VGG16、Resnet50、InceptionV3、Xception）进行对比。结果表明，Enhanced VGG16网络模型的训练集准确率和测试集准确率分别为98.98%和98.44%，权重空间为90.6 MB。与原始VGG16模型相比，训练集准确率和测试集准确率分别提高3.08和2.05个百分点，权重空间下降165.4 MB，模型性能显著提升。Enhanced VGG16网络模型与经典卷积神经网络相对比，模型综合性能更优。该研究为通过油茶叶进行品种分类识别提供了依据，同时可为其他农作物品种识别提供参考。

引用

页码：176 / 181

页数：6

共 27 条

[11] Improved crossover based monarch butterfly optimization for tomato leaf disease classification using convolutional neural network
Nandhini, S.
Ashokkumar, K.
[J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (12) : 18583 - 18610
[12] Leaf image-based classification of some common bean cultivars using discriminative convolutional neural networks[J] . Tavakoli H.,Alirezazadeh P.,Hedayatipour A.,Banijamali Nasib A.H.,Landwehr N..Computers and Electronics in Agriculture . 2021
[13] Defect Classification of Green Plums Based on Deep Learning
Zhou, Haiyan
Zhuang, Zilong
Liu, Ying
Liu, Yang
Zhang, Xiao
[J]. SENSORS, 2020, 20 (23) : 1 - 15
[14] Classification of ladies finger plant leaf using deep learning[J] . L. Selvam,P. Kavitha.Journal of Ambient Intelligence and Humanized Computing . 2020 (prep)
[15] Detection and segmentation of overlapped fruits based on optimized mask R-CNN application in apple harvesting robot[J] . Weikuan Jia,Yuyu Tian,Rong Luo,Zhonghua Zhang,Jian Lian,Yuanjie Zheng.Computers and Electronics in Agriculture . 2020 (C)
[16] Deep learning based segmentation for automated training of apple trees on trellis wires[J] . Yaqoob Majeed,Jing Zhang,Xin Zhang,Longsheng Fu,Manoj Karkee,Qin Zhang,Matthew D. Whiting.Computers and Electronics in Agriculture . 2020 (C)
[17] A visual detection method for nighttime litchi fruits and fruiting stems[J] . Cuixiao Liang,Juntao Xiong,Zhenhui Zheng,Zhuo Zhong,Zhonghang Li,Shumian Chen,Zhengang Yang.Computers and Electronics in Agriculture . 2020 (C)
[18] An optimized dense convolutional neural network model for disease recognition and classification in corn leaf[J] . Abdul Waheed,Muskan Goyal,Deepak Gupta,Ashish Khanna,Aboul Ella Hassanien,Hari Mohan Pandey.Computers and Electronics in Agriculture . 2020
[19] Very Deep Convolutional Networks for Large-Scale Image Recognition[J] . Karen Simonyan,Andrew Zisserman.CoRR . 2014
[20] Searching for mobilenetv3 .2 Howard A,Sandler M,Chu G,et al. Proceedings of the IEEE/CVF International Conference on Computer Vision(ICCV) . 2019

← 1 2 3 →