欢迎访问《图学学报》 分享到：
图学学报

图学学报 ›› 2022, Vol. 43 ›› Issue (1): 28-35.DOI: 10.11996/JG.j.2095-302X.2022010028

• 图像处理与计算机视觉 • 上一篇    下一篇

基于胶囊 SE-Inception 的茄科病害识别方法研究

  

  1. 1. 中国农业大学信息与电气工程学院，北京 100083；  2. 中国农业大学国家渔业创新中心，北京 100083
  • 出版日期:2022-02-28 发布日期:2022-02-16
  • 基金资助:
    国家重点研发计划蓝色粮仓科技创新重点专项(2020YFD0900204)；广东省重点领域研发计划项目(2020B0202010009)

Solanaceae disease recognition method based on capsule SE-Inception

  1. 1. College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China;  2. National Fisheries Innovation Center of China Agricultural University, Beijing 100083, China
  • Online:2022-02-28 Published:2022-02-16
  • Supported by:
    National Key R&D Program Blue Granary Technology Innovation Key Special Project (2020YFD0900204); Guangdong Province Key Field R&D Program Project (2020B0202010009) 

PDF (PC)

101

摘要： 针对番茄和茄子 2 类茄科蔬菜的病害，基于 SE-Inception 和胶囊网络构建了一个具有抗噪性的 茄科病害识别网络，称为胶囊 SE-Inception。该网络主要分为特征提取和胶囊网络 2 部分。其特征提取部分采 用了批处理归一化层(BN)加速网络收敛；利用 SE-Inception 结构和多尺度特征提取模块来提高模型的精度。胶 囊网络部分采用了路由迭代次数为 2，维度为 16 的胶囊进行处理。基于自建的茄科病害数据集开展实验，其 包含白粉虱、白粉病、黄曲病和棉疫病 4 种病害类别和健康叶片；为减少过拟合，对数据进行了增广处理。实 验结果表明胶囊 SE-Inception 网络针对常见的高斯、椒盐和模糊噪声具有较好的抗噪性；其仅需较少的数据就 可以达到较高的识别精度，在相同数据量下，胶囊 SE-Inception 网络的识别精度高于常见轻量级模型。 

关键词: 茄科蔬菜, 病害识别, 抗噪性, SE-Inception 结构, 胶囊网络

Abstract: Aiming at the diseases of two types of Solanaceae vegetables, tomato and eggplant, a noise-resistant Solanaceae disease identification network was constructed based on SE-Inception and capsule network, called capsule SE-Inception. The network is mainly divided into two parts: the feature extraction part and the capsule network part. The feature extraction part of the network employed a batch normalization layer (BN) to accelerate the convergence of the network; the SE-Inception structure and multi-scale feature extraction module were used to improve the accuracy of the model. The capsule network part utilized a capsule with a routing iteration number of two and a dimension of sixteen for processing. The experiments were undertaken based on a self-built data set of Solanaceae diseases. Our sample data contains four disease categories: whitefly, powdery mildew, yellow smut, and cotton blight, as well as healthy leaves. Besides, in order to reduce over-fitting, the data was augmented. The experimental results show that the capsule SE-Inception network displays good noise immunity against common Gaussian, salt and pepper, and fuzzy noise; it only needs a limited amount of data to achieve higher recognition accuracy. Based on the same amount of data, the recognition accuracy of capsule SE-Inception network outperforms that of common lightweight models. 

Key words: Solanaceous vegetables, disease recognition, noise immunity, SE-Inception structure, capsule network 

中图分类号: