首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于注意力机制非对称残差网络和迁移学习的玉米病害图像识别
引用本文:李庆盛,缪楠,张鑫,于雪莹,王首程,高继勇,王志强.基于注意力机制非对称残差网络和迁移学习的玉米病害图像识别[J].科学技术与工程,2021,21(15):6249-6256.
作者姓名:李庆盛  缪楠  张鑫  于雪莹  王首程  高继勇  王志强
作者单位:山东理工大学计算机科学与技术学院,淄博255000
基金项目:山东省自然科学基金(编号:ZR2019MF024);国家自然科学基金(编号:61701286);教育部科技发展中心产学研创新基金(编号:2018A02010);赛尔网络下一代互联网技术创新项目(编号:NGII20170314)第一作者:李庆盛(1995-),男,汉族,山东省烟台市,硕士研究生。研究方向:图像识别。E-mail:378140341@qq.com。* 通信作者:王志强(1977-),男,汉族,山东省淄博市,博士,教授。研究方向:人工智能。E-mail: wzq@sdut.edu.cn。 ?,缪 楠1,张 鑫1,于雪莹1,王首程1,高继勇1,王志强*
摘    要:为实现玉米病害图像快速、准确识别,提出了一种基于非对称注意力机制残差网络(asymmetric convolution attention resnet,ACA-Resnet)的图像检测模型.在残差网络的基础上,通过引入非对称卷积结构减少参数量,加快模型训练速度,同时引入注意力机制,改善模型的表达能力,提高检测准确率.为减小由于病害图片数量不足而造成的过拟合现象,采用迁移学习的方法提高模型的稳定性和泛化能力.结果 表明,ACA-Resnet经过ImageNet数据集预训练后对玉米病害图像的平均识别准确率可达到97.25%,较VGG-16、Inception-V3和ResNet50等网络分类效果更好,相较于Resnet50训练速度明显提升.可见本文方法训练速度快,识别精度高,可为玉米病害检测提供借鉴.

关 键 词:玉米病害  图像识别  残差网络  注意力机制  非对称卷积  迁移学习
收稿时间:2020/10/28 0:00:00
修稿时间:2021/3/4 0:00:00

Image Recognition of Maize Disease based on Asymmetric Convolutional Attention Residual Network and Transfer Learning
Li Qingsheng,Miao Nan,Zhang Xin,Yu Xueying,Wang Shoucheng,Gao Jiyong,Wang Zhiqiang.Image Recognition of Maize Disease based on Asymmetric Convolutional Attention Residual Network and Transfer Learning[J].Science Technology and Engineering,2021,21(15):6249-6256.
Authors:Li Qingsheng  Miao Nan  Zhang Xin  Yu Xueying  Wang Shoucheng  Gao Jiyong  Wang Zhiqiang
Institution:School of Computer Science and Technology,Shandong University of Technology;China
Abstract:For realizing the fast and accurate identification of corn disease images, an image detection model based on the Asymmetric Convolutional Attention Resnet (ACA-Resnet) is proposed. Based on the residual network, the asymmetric convolutional structure is introduced to reduce the number of parameters and accelerate the training speed of the model. Meanwhile, the attention mechanism is employed to improve the expressing ability of the model and the detection accuracy. In order to circumvent the overfitting problem caused by the insufficient disease images, the transfer learning algorithm is adopted to enhance the stability and generalization ability of the model. The average recognition accuracy of ACA-Resnet after pre-training with ImageNet data set reached 97.25%, which was better than that of VGG-16, Inception-V3, and Resnet50, and the training speed was significantly improved compared with Resnet50. The method presented in this paper has fast training speed and high identification accuracy, which can provide reference for the detection of maize disease.
Keywords:
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《科学技术与工程》浏览原始摘要信息
点击此处可从《科学技术与工程》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号