|本期目录/Table of Contents|

[1]崔艳荣,卞珍怡,高英宁.基于生成对抗网络的花卉识别方法[J].江苏农业科学,2022,50(22):200-208.
 Cui Yanrong,et al.Flower recognition method based on generative adversarial networks[J].Jiangsu Agricultural Sciences,2022,50(22):200-208.
点击复制

基于生成对抗网络的花卉识别方法(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第50卷
期数:
2022年第22期
页码:
200-208
栏目:
农业工程与信息技术
出版日期:
2022-11-20

文章信息/Info

Title:
Flower recognition method based on generative adversarial networks
作者:
崔艳荣卞珍怡高英宁
长江大学计算机科学学院,湖北荆州 434023
Author(s):
Cui Yanronget al
关键词:
花卉识别生成对抗网络数据增强深度学习注意力机制
Keywords:
-
分类号:
S126;TP391.41
DOI:
-
文献标志码:
A
摘要:
为解决现有花卉识别准确度低的问题,提出一种基于生成对抗网络的花卉识别方法。使用残差网络构建生成器和判别器,充分提取深层次花卉样本特征,大幅度减小模型参数量,加快模型收敛;融入注意力机制,快速有效提取花卉显著区域特征,并改进模型损失函数,进一步提高对抗网络生成样本的质量。同时利用生成器生成高清晰度、纹理特征明显且具有多样性的高质量花卉样本进行数据增强,迁移判别器参数到花卉识别网络,加快模型收敛速度,进一步提高花卉识别准确度。Oxford 102花卉数据集试验结果显示,相较于其他方法,该方法网络训练稳定、收敛速度快,花卉识别准确度显著提高。
Abstract:
-

参考文献/References:

[1]吴笑鑫,高良,闫民,等. 基于多特征融合的花卉种类识别研究[J]. 北京林业大学学报,2017,39(4):86-93.
[2]Dhar P. A new flower classification system using LBP and SURF features[J]. International Journal of Image,Graphics and Signal Processing,2019,11(5):13-20.
[3]Mohanty A K,Bag A. Image mining for flower classification by genetic association rule mining using GLCM features[J]. International Journal of Advanced Engineering,Management and Science,2017,3(5):516-521.
[4]Al-Saffar A A M,Tao H,Talab M A.Review of deep convolution neural network in image classification[C]//2017 International Conference on Radar,Antenna,Microwave,Electronics,and Telecommunications.Jakarta,Indonesia:IEEE,2017:26-31.
[5]林君宇,李奕萱,郑聪尉,等. 应用卷积神经网络识别花卉及其病症[J]. 小型微型计算机系统,2019,40(6):1330-1335.
[6]吴丽娜,王林山. 改进的LeNet-5模型在花卉识别中的应用[J]. 计算机工程与设计,2020,41(3):850-855.
[7]刘嘉政. 基于深度迁移学习模型的花卉种类识别[J]. 江苏农业科学,2019,47(20):231-236.
[8]关胤. 基于残差网络迁移学习的花卉识别系统[J]. 计算机工程与应用,2019,55(1):174-179.
[9]Cao S,Song B.Visual attentional-driven deep learning method for flower recognition[J]. Mathematical Biosciences and Engineering,2021,18(3):1981-1991.
[10]裴晓芳,张杨. 基于改进残差网络的花卉图像分类算法[J]. 电子器件,2020,43(3):698-704.
[11]Mikoajczyk A,Grochowski M. Data augmentation for improving deep learning in image classification problem[C]//2018 International Interdisciplinary PhD Workshop. S'winous'cie,Poland:IEEE,2018:117-122.
[12]刘建伟,谢浩杰,罗雄麟. 生成对抗网络在各领域应用研究进展[J]. 自动化学报,2020,46(12):2500-2536.
[13]Jin Q M,Lin R H,Yang F C. E-WACGAN:enhanced generative model of signaling data based on WGAN-GP and ACGAN[J]. IEEE Systems Journal,2020,14(3):3289-3300.
[14]Li Y,Zeng J B,Shan S G,et al. Occlusion aware facial expression recognition using CNN with attention mechanism[J]. IEEE Transactions on Image Processing,2019,28(5):2439-2450.
[15]王怡斐,韩俊刚,樊良辉. 基于WGAN的语音增强算法研究[J]. 重庆邮电大学学报(自然科学版),2019,31(1):136-142.
[16]Liu W B,Duan L X,Tang Y,et al. Data augmentation method for fault diagnosis of mechanical equipment based on improved wasserstein GAN[C]//2020 11th International Conference on Prognostics and System Health Management (PHM—2020 Jinan). Jinan:IEEE,2020:103-111.
[17]Wu Y,Qin X,Pan Y H,et al. Convolution neural network based transfer learning for classification of flowers[C]//2018 IEEE 3rd International Conference on Signal and Image Processing.Shenzhen:IEEE,2018:562-566.
[18]Qin M,Xi Y H,Jiang F. A new improved convolutional neural network flower image recognition model[C]//2019 IEEE Symposium Series on Computational Intelligence.Xiamen:IEEE,2019:3110-3117.
[19]曹晓杰,么娆,严雨灵. 应用迁移学习的卷积神经网络花卉图像识别[J]. 计算机应用与软件,2020,37(8):142-148.

相似文献/References:

[1]康飞龙,李佳,刘涛,等.多类农作物病虫害的图像识别应用技术研究综述[J].江苏农业科学,2020,48(22):22.
 Kang Feilong,et al.Application technology of image recognition for various crop diseases and insect pests: a review[J].Jiangsu Agricultural Sciences,2020,48(22):22.

备注/Memo

备注/Memo:
收稿日期:2022-01-23
基金项目:国家自然科学基金面上项目(编号:62077018)。
作者简介:崔艳荣(1968—),女,湖北仙桃人,博士,教授,主要从事网络安全、信息处理研究。E-mail:704974555@qq.com。
通信作者:卞珍怡,硕士研究生,主要从事图形图像及信息处理研究。E-mail:1191313778@qq.com。
更新日期/Last Update: 2022-11-20