计算机应用 ›› 2020, Vol. 40 ›› Issue (5): 1301-1308.DOI: 10.11772/j.issn.1001-9081.2019091646

• 人工智能 • 上一篇    下一篇

基于深度学习的小样本中药材粉末显微图像识别

王一丁1, 郝晨宇1, 李耀利2, 蔡少青2, 袁媛3   

  1. 1.北方工业大学 信息学院,北京 100144
    2.北京大学 药学院,北京 100191
    3.中国中医科学院 中药资源中心,北京 100700
  • 收稿日期:2019-09-26 修回日期:2019-11-01 出版日期:2020-05-10 发布日期:2020-05-15
  • 通讯作者: 蔡少青(1960—)
  • 作者简介:王一丁(1967—),男,北京人,教授,博士,CCF会员,主要研究方向:生物特征识别、机器视觉; 郝晨宇(1996—),男,北京人,硕士研究生,主要研究方向:计算机视觉、深度学习; 李耀利(1977—),女,陕西宝鸡人,讲师,博士,主要研究方向:中药鉴定和质量评价; 蔡少青(1960—),男,宁夏银川人,教授,博士,主要研究方向:生药品种鉴定和品质评价; 袁媛(1978—),女,河北保定人,研究员,博士,主要研究方向:中药鉴定、分子生药学。
  • 基金资助:

    中医药行业科研专项(201407003);中央本级重大增减支项目(2060302)。

Microscopic image identification for small-sample Chinese medicinal materials powder based on deep learning

WANG Yiding1, HAO Chenyu1, LI Yaoli2, CAI Shaoqing2, YUAN Yuan3   

  1. 1.School of Information, North China University of Technology, Beijing 100144, China
    2.School of Pharmaceutical Sciences, Peking University, Beijing 100191, China
    3.National Resource Center for Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, China
  • Received:2019-09-26 Revised:2019-11-01 Online:2020-05-10 Published:2020-05-15
  • Contact: CAI Shaoqing, born in 1960, Ph. D., professor. His research interests include identification and quality evaluation of crude drugs.
  • About author:WANG Yiding, born in 1967, Ph. D., professor. His research interests include biometrics recognition, machine vision.HAO Chenyu, born in 1996, M. S. candidate. His research interests include computer vision, deep learning.LI Yaoli, born in 1977, Ph. D., lecturer. Her research interests include identification and quality control of traditional Chinese medicines.CAI Shaoqing, born in 1960, Ph. D., professor. His research interests include identification and quality evaluation of crude drugs.YUAN Yuan, born in 1978, Ph. D., research fellow. Her research interests include identification of traditional Chinese medicines, molecular pharmacognosy.
  • Supported by:

    This work is partially supported by the Specific Fund of Traditional Chinese Medicine Industry(201407003),the Key Project of Increase and Decrease of Expenditure at the Central Government Level(2060302).

摘要:

针对中药材种类繁多、数据量稀少以及难以对其导管进行分类的问题,提出一种基于多通道颜色空间与注意力机制模型的卷积神经网络改进方法。首先,采用多通道颜色空间将RGB颜色空间与其他颜色空间合并为6通道作为网络输入,使网络学习亮度、色调和饱和度等特征信息,弥补数据量的不足;其次,在网络中加入注意力机制模型,其中通道注意力模型将两个池化层紧密连接到一起,空间注意力模型将多尺度空洞卷积结合到一起,使网络将注意力聚焦于小样本中关键的特征信息。实验结果表明,针对34种中药材样本的8 774张导管图像,采用多通道颜色空间和注意力机制模型的方法,与原始ResNet网络相比,准确率分别提升了1.8个百分点和3.1个百分点,将二者结合后准确率提升了4.1个百分点,说明所提方法对小样本分类的准确率有着大幅度的提升。

关键词: 小样本数据, 注意力机制, 颜色空间, 卷积神经网络, 中药材粉末

Abstract:

Aiming at the problems that a wide variety of Chinese medicinal materials have small samples, and it is difficult to classify the vessels of them, an improved convolutional neural network method was proposed based on multi-channel color space and attention mechanism model. Firstly, the multi-channel color space was used to merge the RGB color space with other color spaces into 6 channels as the network input, so that the network was able to learn the characteristic information such as brightness, hue and saturation to make up for the insufficient samples. Secondly, the attention mechanism model was added to the network, in which the two pooling layers were connected tightly by the channel attention model, and the multi-scale cavity convolutions were combined by the spatial attention model, so that the network focused on the key feature information in the small samples. Aiming at 8 774 vessel images of 34 samples collected from Chinese medicinal materials, the experimental results show that by using the multi-channel color space and attention mechanism model method, compared with the original ResNet network, the accuracy is increased by 1.8 percentage points and 3.1 percentage points respectively, and the combination of the two methods increases accuracy by 4.1 percentage points. It can be seen that the proposed method greatly improves the accuracy of small-sample classification.

Key words: small-sample data, attention mechanism, color space, Convolutional Neural Network (CNN), Chinese medicinal materials powder

中图分类号: