基于弹性动量深度学习神经网络的果体病理图像识别

被引:48
作者
谭文学 [1 ,2 ]
赵春江 [3 ]
吴华瑞 [3 ]
高荣华 [3 ]
机构
[1] 北京工业大学计算机学院
[2] 湖南文理学院计算机科学与技术学院
[3] 不详
关键词
果蔬病害; 病理图像; 深度学习神经网络; 弹性动量; 图像识别;
D O I
暂无
中图分类号
TP183 [人工神经网络与计算]; TP391.41 [];
学科分类号
080203 ;
摘要
为了实时预警果蔬病害和辅助诊断果蔬疾病,实现无人值守的病虫害智能监控,设计了深度学习神经网络的果蔬果体病理图像识别方法,基于对网络误差的传播分析,提出弹性动量的参数学习方法,以苹果为例进行果体病理图像的识别试验。结果表明,该方法召回率为98.4%;同其他同源更新机制相比,弹性动量方案能显著改善学习网络的果蔬病害识别准确率;其收敛曲线平滑,5 h时耗能实现收敛,对不同数据集也有良好泛化性能。
引用
收藏
页码:20 / 25
页数:6
相关论文
共 15 条
  • [11] Predicting the spread of postharvest disease in stored fruit, with application to apples[J] . M. Dutot,L.M. Nelson,R.C. Tyson.Postharvest Biology and Technology . 2013
  • [12] Computational and space complexity analysis of SubXPCA
    Kadappa, Vijayakumar
    Negi, Atul
    [J]. PATTERN RECOGNITION, 2013, 46 (08) : 2169 - 2174
  • [13] Modeling and Prediction of Material Removal Rate and Surface Roughness in Surface-Electrical Discharge Diamond Grinding Process of Metal Matrix Composites
    Agrawal, Shyam Sunder
    Yadava, Vinod
    [J]. MATERIALS AND MANUFACTURING PROCESSES, 2013, 28 (04) : 381 - 389
  • [14] Artificial neural networks for predicting indoor temperature using roof passive cooling techniques in buildings in different climatic conditions[J] . Shrikant Pandey,D.A. Hindoliya,Ritu Mod.Applied Soft Computing Journal . 2011 (3)
  • [15] Environmental emergency decision support system based on Artificial Neural Network[J] . Zhenliang Liao,Bo Wang,Xiaowei Xia,Phillip M. Hannam.Safety Science . 2011 (1)