《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (10): 3224-3234.DOI: 10.11772/j.issn.1001-9081.2021081498
张谊, 万华, 涂淑琴
收稿日期:
2021-08-23
修回日期:
2021-11-24
接受日期:
2021-11-25
发布日期:
2022-01-07
出版日期:
2022-10-10
通讯作者:
万华
作者简介:
第一联系人:张谊(1997—),女,福建三明人,硕士研究生,CCF会员,主要研究方向:计算机视觉基金资助:
Received:
2021-08-23
Revised:
2021-11-24
Accepted:
2021-11-25
Online:
2022-01-07
Published:
2022-10-10
Contact:
Hua WAN
About author:
ZHANG Yi, born in 1997, M. S. candidate. Her research interests include computer vision.Supported by:
摘要:
中药饮片相似品、真伪、变质等方面的分类对临床中药应用有着至关重要的影响。传统的人工鉴别方法主观性强、误判率高,而基于计算机视觉的中药饮片分类具有快速、准确等特点,使饮片筛选智能化。首先,介绍了基于计算机视觉的中药识别算法的一般步骤,并分类综述了对中药图像的预处理、特征提取和识别模型的技术发展现状;然后,选取12类相似易混中药饮片分类作为案例研究。通过构建包含9 156张图片的中药饮片数据集,分析对比了传统识别算法和多种深度学习模型的识别性能差异;最后,对计算机视觉在中药饮片应用研究中存在的难点和未来发展趋势进行了总结和展望。
中图分类号:
张谊, 万华, 涂淑琴. 基于计算机视觉的中药饮片分类技术综述与案例研究[J]. 计算机应用, 2022, 42(10): 3224-3234.
Yi ZHANG, Hua WAN, Shuqin TU. Technical review and case study on classification of Chinese herbal slices based on computer vision[J]. Journal of Computer Applications, 2022, 42(10): 3224-3234.
预处理方法 | 作用 | 应用场景 |
---|---|---|
图像归一化[ | 统一饮片主体位置和朝向 | 统一叶类植物角度 |
图像增强[ | 平滑、锐化 | 去除饮片图像噪声 |
图像增广[ | 旋转、平移、裁剪、镜像等几何变换 | 对数据集数量进行扩增 |
图像灰度化[ | 避免条带失真,减少计算量 | 将彩色图像转化为黑白图像 |
图像分割[ | 分离,去除背景 | 分割算法与手工分割相结合。去除背景,保留中草药图像主体 |
形态学图像处理[ | 提取边缘 | 对叶片轮廓进行边界提取 |
表1 常用的中药饮片图像预处理方法
Tab. 1 Common image preprocessing methods of Chinese herbal slices
预处理方法 | 作用 | 应用场景 |
---|---|---|
图像归一化[ | 统一饮片主体位置和朝向 | 统一叶类植物角度 |
图像增强[ | 平滑、锐化 | 去除饮片图像噪声 |
图像增广[ | 旋转、平移、裁剪、镜像等几何变换 | 对数据集数量进行扩增 |
图像灰度化[ | 避免条带失真,减少计算量 | 将彩色图像转化为黑白图像 |
图像分割[ | 分离,去除背景 | 分割算法与手工分割相结合。去除背景,保留中草药图像主体 |
形态学图像处理[ | 提取边缘 | 对叶片轮廓进行边界提取 |
类别 | 算法 | 年份 | 特点 |
---|---|---|---|
传统算法 | SVM[ | 1964 | SVM的决策边界是对学习样本求解的最大边距超平面,可以解决小样本、非线性、高维的回归等问题 |
KNN[ | 1968 | 核心思想是在训练样本中找到与某一个测试样本最近的K个实例 | |
BP[ | 1974 | 误差反向传播(error Back Propagation, BP)算法为一种局部搜索的优化方法,其学习过程由信号的正向传播与误差的反向传播两个过程组成 | |
深度学习 | AlexNet[ | 2012 | 8层网络,使用ReLU替换Sigmoid的作为激活函数,使用dropout抑制过拟合 |
VGGNet[ | 2014 | 使用简单的3×3卷积核,但将深度提升到16~19层 | |
GoogleNet[ | 2014 | 使用Inception Module,提高参数的利用率;使用1×1的卷积核进行降维以及映射处理 | |
ResNet[ | 2015 | 利用一种称为快捷连接的结构来跳过网络的某些层 | |
DenseNet[ | 2017 | 通过特征的重复使用和旁路设置(Bypass)设置,该网络大幅减少了网络的参数量 | |
EfficientNet[ | 2019 | 多维度混合的模型放缩方法,同时增加网络的width、深度以及输入网络的分辨率来提升网络的性能 |
表2 中草药识别常用算法举例
Tab. 2 Examples of common algorithms for Chinese herbal medicine recognition algorithms
类别 | 算法 | 年份 | 特点 |
---|---|---|---|
传统算法 | SVM[ | 1964 | SVM的决策边界是对学习样本求解的最大边距超平面,可以解决小样本、非线性、高维的回归等问题 |
KNN[ | 1968 | 核心思想是在训练样本中找到与某一个测试样本最近的K个实例 | |
BP[ | 1974 | 误差反向传播(error Back Propagation, BP)算法为一种局部搜索的优化方法,其学习过程由信号的正向传播与误差的反向传播两个过程组成 | |
深度学习 | AlexNet[ | 2012 | 8层网络,使用ReLU替换Sigmoid的作为激活函数,使用dropout抑制过拟合 |
VGGNet[ | 2014 | 使用简单的3×3卷积核,但将深度提升到16~19层 | |
GoogleNet[ | 2014 | 使用Inception Module,提高参数的利用率;使用1×1的卷积核进行降维以及映射处理 | |
ResNet[ | 2015 | 利用一种称为快捷连接的结构来跳过网络的某些层 | |
DenseNet[ | 2017 | 通过特征的重复使用和旁路设置(Bypass)设置,该网络大幅减少了网络的参数量 | |
EfficientNet[ | 2019 | 多维度混合的模型放缩方法,同时增加网络的width、深度以及输入网络的分辨率来提升网络的性能 |
网络 | 年份 | 亮点 |
---|---|---|
SqueezeNet[ | 2017 | 提出了新的网络架构Fire Module,通过减少参数来进行模型压缩 |
ShuffleNet系列[ | 2017 | v1:提出了channel shuffle操作,使得网络可以尽情地使用分组卷积来加速 |
2018 | v2:引入了channel split操作 | |
MobileNet系列[ | 2017 | v1:使用深度可分离卷积构建轻量级网络 |
2018 | v2:提出创新的inverted residual with linear bottleneck单元 | |
2019 | v3:结合AutoML技术与人工微调进行更轻量级的网络构建 | |
ESPNet系列[ | 2018 | |
2019 | ||
FBNet系列[ | 2019 | v1:结合了DNAS(Differentiable Neural Architecture Search)和资源约束 |
2020 | v2:加入了channel和输入分辨率的搜索 | |
2021 | v3:使用准确率预测来进行快速的网络结构搜索 | |
EfficientNet系列[ | 2019 | v1:同时增加网络的宽度、深度以及输入网络的分辨率来提升网络的性能 |
2021 | v2:通过神经架构搜索(Neural Architecture Search, NAS),配合混合缩放方法 | |
SkipNet[ | 2021 | 通过一种动态跳过冗余卷积层的方法来提高推断速度而且不损失准确度 |
表3 常用的轻量级CNN
Tab. 3 Common lightweight CNN
网络 | 年份 | 亮点 |
---|---|---|
SqueezeNet[ | 2017 | 提出了新的网络架构Fire Module,通过减少参数来进行模型压缩 |
ShuffleNet系列[ | 2017 | v1:提出了channel shuffle操作,使得网络可以尽情地使用分组卷积来加速 |
2018 | v2:引入了channel split操作 | |
MobileNet系列[ | 2017 | v1:使用深度可分离卷积构建轻量级网络 |
2018 | v2:提出创新的inverted residual with linear bottleneck单元 | |
2019 | v3:结合AutoML技术与人工微调进行更轻量级的网络构建 | |
ESPNet系列[ | 2018 | |
2019 | ||
FBNet系列[ | 2019 | v1:结合了DNAS(Differentiable Neural Architecture Search)和资源约束 |
2020 | v2:加入了channel和输入分辨率的搜索 | |
2021 | v3:使用准确率预测来进行快速的网络结构搜索 | |
EfficientNet系列[ | 2019 | v1:同时增加网络的宽度、深度以及输入网络的分辨率来提升网络的性能 |
2021 | v2:通过神经架构搜索(Neural Architecture Search, NAS),配合混合缩放方法 | |
SkipNet[ | 2021 | 通过一种动态跳过冗余卷积层的方法来提高推断速度而且不损失准确度 |
算法 | 精确度/% | 召回率/% | 特异性/% | 准确率/% | 单张图片测试平均耗时/ms | 模型大小/MB |
---|---|---|---|---|---|---|
HOG+SVM | 23.1 | 21.3 | 92.9 | 87.2 | 79.385 | 10.99 |
VGGNet-16 | 83.4 | 80.1 | 98.6 | 97.5 | 14.028 | 512.36 |
ResNet-34 | 88.5 | 86.2 | 98.9 | 98.1 | 7.497 | 81.32 |
ResNet-50 | 85.9 | 83.8 | 98.7 | 97.6 | 10.920 | 90.03 |
ResNet-101 | 87.4 | 85.0 | 98.8 | 97.8 | 17.133 | 162.73 |
ResNeXt-50 | 88.5 | 87.3 | 99.0 | 98.2 | 16.006 | 88.07 |
ResNeXt-101 | 88.7 | 85.8 | 98.9 | 98.0 | 33.816 | 331.87 |
MobileNet v2 | 79.2 | 74.2 | 98.0 | 96.4 | 6.779 | 8.73 |
ShuffleNet v2 1x | 91.4 | 90.0 | 99.2 | 98.6 | 5.966 | 4.95 |
表4 各算法分类结果
Tab. 4 Classification results of different algorithms
算法 | 精确度/% | 召回率/% | 特异性/% | 准确率/% | 单张图片测试平均耗时/ms | 模型大小/MB |
---|---|---|---|---|---|---|
HOG+SVM | 23.1 | 21.3 | 92.9 | 87.2 | 79.385 | 10.99 |
VGGNet-16 | 83.4 | 80.1 | 98.6 | 97.5 | 14.028 | 512.36 |
ResNet-34 | 88.5 | 86.2 | 98.9 | 98.1 | 7.497 | 81.32 |
ResNet-50 | 85.9 | 83.8 | 98.7 | 97.6 | 10.920 | 90.03 |
ResNet-101 | 87.4 | 85.0 | 98.8 | 97.8 | 17.133 | 162.73 |
ResNeXt-50 | 88.5 | 87.3 | 99.0 | 98.2 | 16.006 | 88.07 |
ResNeXt-101 | 88.7 | 85.8 | 98.9 | 98.0 | 33.816 | 331.87 |
MobileNet v2 | 79.2 | 74.2 | 98.0 | 96.4 | 6.779 | 8.73 |
ShuffleNet v2 1x | 91.4 | 90.0 | 99.2 | 98.6 | 5.966 | 4.95 |
1 | 王传娟. 常见中药饮片伪品和易混淆品的鉴别[J]. 心理月刊, 2019, 14(8):182. |
WANG C J. Identification of counterfeit and confusing products in common Chinese herbal slices[J]. Psychologies Magazine, 2019, 14(8): 182. | |
2 | 谢宗万. 中药品种传统经验鉴别"辨状论质"论[J]. 时珍国医国药, 1994, 5(3):19-21. |
XIE Z W. “Differentiation of symptoms and discussion of quality” in traditional experience identification of traditional Chinese medicine varieties[J]. Lishizhen Medicine and Materia Medica Research, 1994, 5(3): 19-21. | |
3 | 师飘,郑祥明. 计算机视觉在中药饮片领域中的应用与展望[J]. 德州学院学报, 2020, 36(6):34-38, 50. 10.3969/j.issn.1004-9444.2020.06.009 |
SHI P, ZHENG X M. Application and prospect of computer vision in Chinese herbal pieces[J]. Journal of Dezhou University, 2020, 36(6): 34-38, 50. 10.3969/j.issn.1004-9444.2020.06.009 | |
4 | CUI J S, LI Y H, HUO J, et al. A measurement method of motion parameters in aircraft ground tests using computer vision[J]. Measurement, 2021, 174: No.108985. 10.1016/j.measurement.2021.108985 |
5 | LI T, ZHU C, XIANG G Q, et al. LLCNN: a convolutional neural network for low-light image enhancement[C]// Proceedings of the 2017 IEEE Visual Communications and Image Processing. Piscataway: IEEE, 2017: 1-4. 10.1109/vcip.2017.8305143 |
6 | DELP E, MITCHELL O. Image compression using block truncation coding[J]. IEEE Transactions on Communications, 1979, 27(9): 1335-1342. 10.1109/tcom.1979.1094560 |
7 | LEU J G. Edge sharpening through ramp width reduction[J]. Image and Vision Computing, 2000, 18(6/7): 501-514. 10.1016/s0262-8856(99)00041-4 |
8 | FANG C W, LIAO Z C, YU Y Z. Piecewise flat embedding for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(6): 1470-1485. 10.1109/tpami.2018.2839733 |
9 | 张宁,刘文萍. 基于克隆选择算法和K近邻的植物叶片识别方法[J]. 计算机应用, 2013, 33(7):2009-2013. 10.3724/sp.j.1087.2013.02009 |
ZHANG N, LIU W P. Plant leaf recognition method based on clonal selection algorithm and K nearest neighbor[J]. Journal of Computer Applications, 2013, 33(7): 2009-2013. 10.3724/sp.j.1087.2013.02009 | |
10 | 翟传敏,汪青萍,杜吉祥. 基于叶缘与叶脉分数维特征的植物叶识别方法研究[J]. 计算机科学, 2014, 41(2):170-173. 10.3969/j.issn.1002-137X.2014.02.038 |
ZHAI C M, WANG Q P, DU J X. Plant leaf recognition method based on fractal dimension feature of outline and venation[J]. Computer Science, 2014, 41(2): 170-173. 10.3969/j.issn.1002-137X.2014.02.038 | |
11 | 王丽君,淮永建,彭月橙. 基于叶片图像多特征融合的观叶植物种类识别[J]. 北京林业大学学报, 2015, 37(1):55-61. 10.13332/j.cnki.jbfu.2015.01.006 |
WANG L J, HUAI Y J, PENG Y C. Method of identification of foliage from plants based on extraction of multiple features of leaf images[J]. Journal of Beijing Forestry University, 2015, 37(1): 55-61. 10.13332/j.cnki.jbfu.2015.01.006 | |
12 | 王晓峰,黄德双,杜吉祥,等. 叶片图像特征提取与识别技术的研究[J]. 计算机工程与应用, 2006, 42(3):190-193. 10.3321/j.issn:1002-8331.2006.03.056 |
WANG X F, HUANG D S, DU J X, et al. Feature extraction and recognition for leaf images[J]. Computer Engineering and Applications, 2006, 42(3): 190-193. 10.3321/j.issn:1002-8331.2006.03.056 | |
13 | 张万义,张千,潘继波,等. 基于深度学习的中草药分类识别[J]. 智慧健康, 2020, 6(35):1-4, 13. 10.19335/j.cnki.2096-1219.2020.35.001 |
ZHANG W Y, ZHANG Q, PAN J B, et al. Chinese herbal medicine classification and recognition based on deep learning[J]. Smart Healthcare, 2020, 6(35): 1-4, 13. 10.19335/j.cnki.2096-1219.2020.35.001 | |
14 | 恩德,忽胜强. 基于集成神经网络的植物叶片识别方法[J]. 浙江农业学报, 2015, 27(12):2225-2233. 10.3969/j.issn.1004-1524.2015.12.28 |
EN D, HU S Q. Plant leaf recognition based on artificial neural network ensemble[J]. Acta Agriculturae Zhejiangensis, 2015, 27(12): 2225-2233. 10.3969/j.issn.1004-1524.2015.12.28 | |
15 | 周法律,张璐瑶,汤岚凤,等. 中草药原植物叶片图像在线识别系统设计与实现[J]. 电脑知识与技术, 2014, 10(13):3114-3116. |
ZHOU F L, ZHANG L Y, TANG L F, et al. Design and implementation of online image recognition system of Chinese herbal medicine leaf[J]. Computer Knowledge and Technology, 2014, 10(13): 3114-3116. | |
16 | 谢树莹,周明,周金海. 基于OpenCV的中药饮片"辨色"识别研究[J]. 时珍国医国药, 2018, 29(2):510-512. 10.3969/j.issn.1008-0805.2018.02.092 |
XIE S Y, ZHOU M, ZHOU J H. Research of OpenCV-based recognition system of herbal decoction pieces[J]. Lishizhen Medicine and Materia Medica Research, 2018, 29(2): 510-512. 10.3969/j.issn.1008-0805.2018.02.092 | |
17 | 张宁,王志明,郑健. 基于标记分水岭的植物重叠叶片改进分割算法[J]. 计算机与现代化, 2019(1):21-26. 10.3969/j.issn.1006-2475.2019.01.005 |
ZHANG N, WANG Z M, ZHENG J. An improved segmentation algorithm for overlapping leaves of plants based on marked watershed[J]. Computer and Modernization, 2019(1): 21-26. 10.3969/j.issn.1006-2475.2019.01.005 | |
18 | 张宝文,陶佳,李亮. 中草药石楠叶片图像识别的研究[J]. 河北农业科学, 2018, 22(1):106-108. 10.16318/j.cnki.hbnykx.2018.01.028 |
ZHANG B W, TAO J, LI L. Study on image recognition of Chinese photinia leaves[J]. Journal of Hebei Agricultural Sciences, 2018, 22(1): 106-108. 10.16318/j.cnki.hbnykx.2018.01.028 | |
19 | 孙俊,谭文军,毛罕平,等. 基于改进卷积神经网络的多种植物叶片病害识别[J]. 农业工程学报, 2017, 33(19):209-215. 10.11975/j.issn.1002-6819.2017.19.027 |
SUN J, TAN W J, MAO H P, et al. Recognition of multiple plant leaf diseases based on improved convolutional neural network[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(19): 209-215. 10.11975/j.issn.1002-6819.2017.19.027 | |
20 | 梁丽金,卢文彪,王凤梅. 基于边缘检测的防风显微图像的分割与表征[J]. 中国实验方剂学杂志, 2018, 24(6):37-41. 10.13422/j.cnki.syfjx.20180608 |
LIANG L J, LU W B, WANG F M. Segmentation and characterization of Saposhnikoviae Radix micrograph based on edge detection[J]. Chinese Journal of Experimental Traditional Medical Formulae, 2018, 24(6): 37-41. 10.13422/j.cnki.syfjx.20180608 | |
21 | 黄方亮,俞磊,沈同平,等. 基于AlexNet深度学习模型的中草药植物图像分类研究与实现[J]. 齐鲁工业大学学报, 2020, 34(2): 44-49. |
HUANG F L, YU L, SHEN T P, et al. Research and implementation of Chinese herbal medicine plant image classification based on AlexNet deep learning model[J]. Journal of Qilu University of Technology, 2020, 34(2): 44-49. | |
22 | 王一丁,郝晨宇,李耀利,等. 基于深度学习的小样本中药材粉末显微图像识别[J]. 计算机应用, 2020, 40(5):1301-1308. 10.11772/j.issn.1001-9081.2019091646 |
WANG Y D, HAO C Y, LI Y L, et al. Microscopic image identification for small-sample Chinese medicinal materials powder based on deep learning[J]. Journal of Computer Applications, 2020, 40(5): 1301-1308. 10.11772/j.issn.1001-9081.2019091646 | |
23 | 刘晶晶,侯凌燕,杨大利. 牡丹花特征提取及识别技术研究[J]. 北京信息科技大学学报(自然科学版), 2017, 32(1):65-71. |
LIU J J, HOU L Y, YANG D L. Research on Peony feature extraction and identification technology[J]. Journal of Beijing Information Science & Technology University, 2017, 32(1): 65-71. | |
24 | YANG Z Q, DONG J W, KOU W L, et al. Mapping Panax Notoginseng plantations by using an Integrated Pixel- and Object-Based (IPOB) approach and ZY-3 imagery[J]. Remote Sensing, 2021, 13(11): No.2148. 10.3390/rs13112184 |
25 | 杨涛,雷进,朱皓睿,等. 基于图像特征融合的麦冬叶部病害识别[J]. 湖北农业科学, 2021, 60(7):135-138, 144. 10.14088/j.cnki.issn0439-8114.2021.07.027 |
YANG T, LEI J, ZHU H R, et al. Recognition of ophiopogon japonicus disease based on image feature fusion[J]. Hubei Agricultural Sciences, 2021, 60(7): 135-138, 144. 10.14088/j.cnki.issn0439-8114.2021.07.027 | |
26 | 程铭恩,詹志来,张卫,等. 经典名方中黄柏的本草考证[J]. 中国中药杂志, 2019, 44(21):4768-4771. |
CHENG M E, ZHAN Z L, ZHANG W, et al. Textual research of “Huangbo” in classical prescriptions[J]. China Journal of Chinese Materia Medica, 2019, 44(21): 4768-4771. | |
27 | 姚丽佳,梁渝陵. 知母与混用品知母的鉴别[J]. 中国药业, 2000, 9(4): 37. 10.3969/j.issn.1006-4931.2000.04.039 |
YAO L J, LIANG Y L. Identification of Anemarrhena asphodeloides and mixed Anemarrhena asphodeloides[J]. China Pharmaceuticals, 2000, 9(4): 37. 10.3969/j.issn.1006-4931.2000.04.039 | |
28 | 贾伟,闫颖盈,温川飙,等. 中药饮片切面纹理特征提取研究[J]. 成都中医药大学学报, 2017, 40(4):1-6. |
JIA W, YAN Y Y, WEN C B, et al. Texture feature extraction research of sections of traditional Chinese medicine[J]. Journal of Chengdu University of Traditional Chinese Medicine, 2017, 40(4): 1-6. | |
29 | TAMURA H, MORI S, YAMAWAKI T. Textural features corresponding to visual perception[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1978, 8(6): 460-473. 10.1109/tsmc.1978.4309999 |
30 | 陶欧,张燕玲,陈茜,等. 基于灰度共生矩阵的中药饮片横切面图像纹理特征参数的提取[J]. 世界科学技术—中医药现代化, 2014, 16(12):2531-2537. |
TAO O, ZHANG Y L, CHEN Q, et al. Extraction of texture feature parameter of transverse section in Chinese herbal medicine by gray-level co-occurrence matrix[J]. Modernization of Traditional Chinese Medicine and Materia Medica—World Science and Technology, 2014, 16(12): 2531-2537. | |
31 | 陶欧,林兆洲,张宪宝,等. 基于饮片切面图像纹理特征参数的中药辨识模型研究[J]. 世界科学技术—中医药现代化, 2014, 16(12):2558-2562. |
TAO O, LIN Z Z, ZHAG X B, et al. Research on identification model of Chinese herbal medicine by texture feature parameter of transverse section image[J]. Modernization of Traditional Chinese Medicine and Materia Medica—World Science and Technology, 2014, 16(12): 2558-2562. | |
32 | 王雪琰,张冲,张立. 卷积神经网络下的相似月季识别[J]. 安徽农业大学学报, 2021, 48(3):504-510. |
WANG X Y, ZHANG C, ZHANG L. Recognition of similar rose based on convolution neural network[J]. Journal of Anhui Agricultural University, 2021, 48(3): 504-510. | |
33 | KAN H X, JIN L, ZHOU F L. Classification of medicinal plant leaf image based on multi-feature extraction[J]. Pattern Recognition and Image Analysis, 2017, 27(3): 581-587. 10.1134/s105466181703018x |
34 | 夏永泉,李耀斌,曾莎. 基于HSI颜色空间的植物叶片病斑提取方法[J]. 江苏农业科学, 2015, 43(8):406-408. |
XIA Y Q, LI Y B, ZENG S. Method for extracting disease spots from plant leaves based on HSI color space[J]. Jiangsu Agricultural Sciences, 2015, 43(8): 406-408. | |
35 | 金梦然,袁航,黄大庄. 基于叶形和叶脉特征的植物数字化分类研究[J]. 林业与生态科学, 2020, 35(1):112-118. |
JIN M R, YUAN H, HUANG D Z. Study on digital classification of plants based on characteristics of leaf shape and leaf vein[J]. Forestry and Ecological Sciences, 2020, 35(1): 112-118. | |
36 | KOLIVAND H, FERN B M, SABA T, et al. A new leaf venation detection technique for plant species classification[J]. Arabian Journal for Science and Engineering, 2019, 44(4): 3315-3327. 10.1007/s13369-018-3504-8 |
37 | 金力,阚红星,许钒,等. 一种新的药用植物叶片自动分类方法的构建[J]. 通化师范学院学报, 2017, 38(4):42-45, 49. |
JIN L, KAN H X, XU F, et al. Construction of a new automatic classification method for medicinal plant leaves[J]. Journal of Tonghua Normal University, 2017, 38(4): 42-45, 49. | |
38 | ANAMI B S, NANDYAL S S, GOVARDHAN A. A combined color, texture and edge features based approach for identification and classification of Indian medicinal plants[J]. International Journal of Computer Applications, 2010, 6(12): 45-51. 10.5120/1122-1471 |
39 | BAO T Q, KIET N T T, DINH T Q, et al. Plant species identification from leaf patterns using histogram of oriented gradients feature space and convolution neural networks[J]. Journal of Information and Telecommunication, 2020, 4(2): 140-150. 10.1080/24751839.2019.1666625 |
40 | ZHAO J L, FANG Y, CHU G M, et al. Identification of leaf-scale wheat powdery mildew (Blumeria graminis f. sp. Tritici) combining hyperspectral imaging and an SVM classifier[J]. Plants, 2020, 9(8): No.936. 10.3390/plants9080936 |
41 | 陆楷煜,夏春蕾,戴曙光,等. 特征融合在植物叶片识别中的应用研究[J]. 软件导刊, 2020, 19(10):71-75. |
LU K Y, XIA C L, DAI S G, et al. Application research on multi-feature fusion in plant leaf recognition[J]. Software Guide, 2020, 19(10): 71-75. | |
42 | MAHAJAN S, RAINA A, GAO X Z, et al. Plant recognition using morphological feature extraction and transfer learning over SVM and AdaBoost[J]. Symmetry, 2021, 13(2): No.356. 10.3390/sym13020356 |
43 | HU K, HU P, CAO D, et al. A method for authenticity identification of Fritillaria Cirrhosa D. Don based on deep learning[C]// Proceedings of the IEEE 4th International Conference on Image, Vision and Computing. Piscataway: IEEE, 2019: 494-498. 10.1109/icivc47709.2019.8981401 |
44 | 吕宇琛,王健庆. 基于HOG-LBP特征的中药饮片图像识别[J]. 中国中医药信息杂志, 2019, 26(4):106-110. 10.3969/j.issn.1005-5304.2019.04.022 |
LYU Y C, WANG J Q. Image recognition of TCM decoction pieces based on HOG-LBP[J]. Chinese Journal of Information on TCM, 2019, 26(4): 106-110. 10.3969/j.issn.1005-5304.2019.04.022 | |
45 | 陶梦琳,顾文涛,汪子青,等. 基于支持向量机的黄连饮片产地识别研究[J]. 中草药, 2015, 46(21):3173-3178. 10.7501/j.issn.0253-2670.2015.21.008 |
TAO M L, GU W T, WANG Z Q, et al. Discrimination of Cotidis Rhizoma from different habitats by support vector machine[J]. Chinese Traditional and Herbal Drugs, 2015, 46(21): 3173-3178. 10.7501/j.issn.0253-2670.2015.21.008 | |
46 | 王礼,洪祖兵,方陆明,等. 基于iOS系统的观赏植物识别[J]. 浙江农林大学学报, 2018, 35(5):900-907. 10.11833/j.issn.2095-0756.2018.05.015 |
WANG L, HONG Z B, FANG L M, et al. iOS-based recognition of ornamental plants[J]. Journal of Zhejiang A&F University, 2018, 35(5): 900-907. 10.11833/j.issn.2095-0756.2018.05.015 | |
47 | 王雷宏,陈永生,郑玉红. 基于叶片数字纹理特征自动识别胡颓子属植物[J]. 中国农学通报, 2020, 36(11):20-25. |
WANG L H, CHEN Y S, ZHENG Y H. Automatic identification of Elaeagnus L. based on leaf digital texture feature[J]. Chinese Agricultural Science Bulletin, 2020, 36(11): 20-25. | |
48 | 谢文涌,柴琴琴,甘勇辉,等. 基于多特征提取和Stacking集成学习的金线莲品系分类[J]. 农业工程学报, 2020, 36(14):203-210. 10.11975/j.issn.1002-6819.2020.14.025 |
XIE W C, CHAI Q Q, GAN Y H, et al. Strains classification of Anoectochilus roxburghii strains based on multi-feature extraction and Stacking ensemble learning[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(14): 203-210. 10.11975/j.issn.1002-6819.2020.14.025 | |
49 | 王艳,孙薇,周小平. 基于深度学习的中草药植物图像识别方法研究[J]. 中医药信息, 2020, 37(6):21-25. |
WANG Y, SUN W, ZHOU X P. Research on image recognition of Chinese herbal medicine plants based on deep learning[J]. Information on Traditional Chinese Medicine, 2020, 37(6): 21-25. | |
50 | 聂聪颖,唐晶磊. 基于显著特征和全局特征融合的植物识别方法[J]. 计算机工程与设计, 2021, 42(4):976-984. 10.16208/j.issn1000-7024.2021.04.012 |
NIE C Y, TANG J L. Plant recognition method based on fusion of salient feature and global feature[J]. Computer Engineering and Design, 2021, 42(4): 976-984. 10.16208/j.issn1000-7024.2021.04.012 | |
51 | LI K Z, LIN J H, LIU J R, et al. Using deep learning for image-based different degrees of Ginkgo leaf disease classification[J]. Information, 2020, 11(2): No.95. 10.3390/info11020095 |
52 | 王耐,卢文彪,凌秀华,等. 牛膝和川牛膝药材的特征提取与图像识别[J]. 中国药房, 2017, 28(12):1670-1673. 10.6039/j.issn.1001-0408.2017.12.24 |
WANG N, LU W B, LING X H, et al. Feature extraction and image recognition of Achyranthes bidentata and Cyathula officinalis[J]. China Pharmacy, 2017, 28(12): 1670-1673. 10.6039/j.issn.1001-0408.2017.12.24 | |
53 | 余本国. BP神经网络局限性及其改进的研究[J]. 山西农业大学学报(自然科学版), 2009, 29(1):89-93. |
YU B G. Discussion on the limitation and improvement of BP neural network[J]. Journal of Shanxi Agricultural University (Natural Science Edition), 2009, 29(1): 89-93. | |
54 | 左羽,陶倩,吴恋,等. 基于卷积神经网络的植物图像分类方法研究[J]. 物联网技术, 2020, 10(3):72-75. |
ZUO Y, TAO Q, WU L, et al. Research on classification method of plant images based on convolutional neural network[J]. Internet of Things Technologies, 2020, 10(3): 72-75. | |
55 | 樊湘鹏,许燕,周建平,等. 基于迁移学习和改进CNN的葡萄叶部病害检测系统[J]. 农业工程学报, 2021, 37(6):151-159. 10.11975/j.issn.1002-6819.2021.06.019 |
FAN X P, XU Y, ZHOU J P, et al. Detection system for grape leaf diseases based on transfer learning and updated CNN[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(6): 151-159. 10.11975/j.issn.1002-6819.2021.06.019 | |
56 | 陈雁,邹立思. 基于BMFnet-WGAN的中药饮片智能甄别[J]. 中国实验方剂学杂志, 2021, 27(15):107-114. |
CHEN Y, ZOU L S. Intelligent screening of pieces of Chinese medicine based on BMFnet-WGAN[J]. Chinese Journal of Experimental Traditional Medical Formulae, 2021, 27(15): 107-114. | |
57 | 孙鑫,钱会南. 基于深度卷积网络的中药饮片图像识别[J]. 世界科学技术—中医药现代化, 2017, 19(2):218-222. |
SUN X, QIAN H N. Identification of the images of Chinese herb slices with deep convolutional network[J]. Modernization of Traditional Chinese Medicine and Materia Medica—World Science and Technology, 2017, 19(2): 218-222. | |
58 | 徐飞,孟沙,吴启南,等. 基于卷积神经网络的人参与西洋参饮片鉴别方法研究[J]. 南京中医药大学学报, 2018, 34(6):621-624. 10.14148/j.issn.1672-0482.2018.0621 |
XU F, MENG S, WU Q N, et al. Research on the differentiation of Ginseng radix and Panacis quinquefolii slices based on convolutional neural network[J]. Journal of Nanjing University of Traditional Chinese Medicine, 2018, 34(6): 621-624. 10.14148/j.issn.1672-0482.2018.0621 | |
59 | 王健庆,戴恺,李子柔. 基于深度学习的中药饮片图像识别研究[J]. 时珍国医国药, 2020, 31(12):2930-2933. 10.3969/j.issn.1008-0805.2020.12.030 |
WANG J Q, DAI K, LI Z R. Research on image recognition of Chinese herbal pieces based on deep learning[J]. Lishizhen Medicine and Materia Medica Research, 2020, 31(12): 2930-2933. 10.3969/j.issn.1008-0805.2020.12.030 | |
60 | 庄奕珊. 基于深度神经网络的中药材识别[D]. 广州:华南理工大学, 2018: 49-58. |
ZHUANG Y S. Identification of Chinese medicines based on deep neural network[D]. Guangzhou: South China University of Technology, 2018: 49-58. | |
61 | 刘捷. 基于图像分析的植物叶片识别研究[D]. 南京:南京信息工程大学, 2020: 48-52. |
LIU J. Research on plant leaf recognition based on image analysis[D]. Nanjing: Nanjing University of Information Science and Technology, 2020: 48-52. | |
62 | 吴云志,刘翱宇,朱小宁,等. 一种植物病害图像识别卷积网络架构[J]. 安徽农业大学学报, 2021, 48(1):150-156. |
WU Y Z, LIU A Y, ZHU X N, et al. A convolutional network for plant disease image recognition (FI-DenseNet)[J]. Journal of Anhui Agricultural University, 2021, 48(1): 150-156. | |
63 | ATILA Ü, UÇAR M, AKYOL K, et al. Plant leaf disease classification using EfficientNet deep learning model[J]. Ecological Informatics, 2021, 61: No.101182. 10.1016/j.ecoinf.2020.101182 |
64 | RAI P, LONDHE N D, RAJ R. Fault classification in power system distribution network integrated with distributed generators using CNN[J]. Electric Power Systems Research, 2020, 192: No.106914. 10.1016/j.epsr.2020.106914 |
65 | HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778. 10.1109/cvpr.2016.90 |
66 | ANGELINE R, VANI R. ResNet: a convolutional neural network for detecting and diagnosing of coronavirus pneumonia[J]. IOP Conference Series: Materials Science and Engineering, 2021, 1084: No.012011. 10.1088/1757-899x/1084/1/012011 |
67 | HUANG G, LIU Z, van der MAATEN L, et al. Densely connected convolutional networks[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 2261-2269. 10.1109/cvpr.2017.243 |
68 | IANDOLA F N, HAN S, MOSKEWICZ M W, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size[EB/OL]. (2016-11-04) [2021-05-20].. |
69 | ZHANG Y, ZHOU X Y, LIN M X, et al. ShuffleNet: an extremely efficient convolutional neural network for mobile devices[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 6848-6856. 10.1109/cvpr.2018.00716 |
70 | MA N N, ZHANG X Y, ZHENG H T, et al. ShuffleNet V2: practical guidelines for efficient CNN architecture design[C]// Proceedings of the 2018 European Conference on Computer Vision, LNCS 11218. Cham: Springer, 2018:122-138. |
71 | HOWARD A G, ZHU M L, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[EB/OL]. (2017-04-17) [2021-05-20].. 10.48550/arXiv.1704.04861 |
72 | SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 4510-4520. 10.1109/cvpr.2018.00474 |
73 | HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3[C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019:1314-1324. 10.1109/iccv.2019.00140 |
74 | MEHTA S, RASTEGARI M, CASPI A, et al. ESPNet: efficient spatial pyramid of dilated convolutions for semantic segmentation[C]// Proceedings of the 2018 European Conference on Computer Vision, LNCS 11214. Cham: Springer, 2018: 561-580. |
75 | MEHTA S, RASTEGARI M, SHAPIRO L, et al. ESPNetv2: a light-weight, power efficient, and general purpose convolutional neural network[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 9182-9192. 10.1109/cvpr.2019.00941 |
76 | WU B C, DAI X L, ZHANG P Z, et al. FBNet: Hardware-aware efficient ConvNet design via differentiable neural architecture search[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 10726-10734. 10.1109/cvpr.2019.01099 |
77 | WAN A, DAI X L, ZHANG P Z, et al. FBNetV2: differentiable neural architecture search for spatial and channel dimensions[C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 12962-12971. 10.1109/cvpr42600.2020.01298 |
78 | DAI X L, WAN A, ZHANG P Z, et al. FBNetV3: joint architecture-recipe search using predictor pretraining[EB/OL]. (2021-03-30) [2021-05-20].. 10.1109/cvpr46437.2021.01601 |
79 | TAN M X, LE Q V. EfficientNet: rethinking model scaling for convolutional neural networks[C]// Proceedings of the 36th International Conference on Machine Learning. New York: JMLR.org, 2019:6105-6114. |
80 | TAN M X, LE Q V. EfficientNetV2: smaller models and faster training[C]// Proceedings of the 38th International Conference on Machine Learning. New York: JMLR.org, 2021: 10096-10106. |
81 | ABRAHAMYAN L, ZIATCHIN V, CHEN Y M, et al. Bias loss for mobile neural networks[C]// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 6536-6546. 10.1109/iccv48922.2021.00649 |
[1] | 潘烨新, 杨哲. 基于多级特征双向融合的小目标检测优化模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2871-2877. |
[2] | 杨鑫, 陈雪妮, 吴春江, 周世杰. 结合变种残差模型和Transformer的城市公路短时交通流预测[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2947-2951. |
[3] | 付帅, 郭小英, 白茹意, 闫涛, 陈斌. 改进的CloFormer模型与有序回归相结合的年龄评估方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2372-2380. |
[4] | 陈彤, 杨丰玉, 熊宇, 严荭, 邱福星. 基于多尺度频率通道注意力融合的声纹库构建方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2407-2413. |
[5] | 王东炜, 刘柏辰, 韩志, 王艳美, 唐延东. 基于低秩分解和向量量化的深度网络压缩方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 1987-1994. |
[6] | 龙伍丹, 彭博, 胡节, 申颖, 丁丹妮. 基于加强特征提取的道路病害检测算法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2264-2270. |
[7] | 刘瑞华, 郝子赫, 邹洋杨. 基于多层级精细特征融合的步态识别算法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2250-2257. |
[8] | 施赛龙, 方智文. 基于多尺度聚合和共享注意力的注视估计模型[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2047-2054. |
[9] | 翟飞宇, 马汉达. 基于DenseNet的经典-量子混合分类模型[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1905-1910. |
[10] | 吴郅昊, 迟子秋, 肖婷, 王喆. 基于元学习自适应的小样本语音合成[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1629-1635. |
[11] | 孙子文, 钱立志, 杨传栋, 高一博, 陆庆阳, 袁广林. 基于Transformer的视觉目标跟踪方法综述[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1644-1654. |
[12] | 肖斌, 杨模, 汪敏, 秦光源, 李欢. 独立性视角下的相频融合领域泛化方法[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1002-1009. |
[13] | 崔晨辉, 蔺素珍, 李大威, 禄晓飞, 武杰. 基于孪生网络和Transformer的红外弱小目标跟踪方法[J]. 《计算机应用》唯一官方网站, 2024, 44(2): 563-571. |
[14] | 庞玉东, 李志星, 刘伟杰, 李天昊, 王宁宁. 基于改进实时检测Transformer的塔机上俯视场景小目标检测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3922-3929. |
[15] | 范艺扬, 张洋, 曾尚, 曾渝, 付茂栗. 基于分解和频域特征提取的多变量长时间序列预测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3442-3448. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||