A Hybrid Convolutional Neural Network for Plankton Classification

被引:20
|
作者
Dai, Jialun [1 ]
Yu, Zhibin [1 ]
Zheng, Haiyong [1 ]
Zheng, Bing [1 ]
Wang, Nan [1 ]
机构
[1] Ocean Univ China, Coll Informat Sci & Engn, Qingdao 266100, Shandong, Peoples R China
基金
中国国家自然科学基金;
关键词
IDENTIFICATION;
D O I
10.1007/978-3-319-54526-4_8
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Plankton are fundamental and essential to marine ecosystem, and its survey is significant for sustainable development and ecosystem balance of oceans. The large amount of plankton species and complex relationship among different classes bring difficulty for us to design an automatic plankton classification system. Thus, we develop our model based on convolutional neural network and aim to overcome these shortages. We consider two different ways to extract global and local features to describe shape and texture information of plankton. Furthermore, we design a pyramid fully connected structure to merge different inner products from each sub networks. The experimental results prove our model can take advantage of multiple features and performs better than original convolutional neural network.
引用
收藏
页码:102 / 114
页数:13
相关论文
共 50 条
  • [1] Automatic classification of marine plankton with digital holography using convolutional neural network
    Zhang, Yilong
    Lu, Yaoxiang
    Wang, Haixia
    Chen, Peng
    Liang, Ronghua
    [J]. OPTICS AND LASER TECHNOLOGY, 2021, 139
  • [2] Plankton Classification with Deep Convolutional Neural Networks
    Ouyang Py
    Hu Hong
    Shi Zhongzhi
    [J]. 2016 IEEE INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC), 2016, : 132 - 136
  • [3] Texture and Shape Information Fusion of Convolutional Neural Network for Plankton Image Classification
    Cui, Jinna
    Wei, Bin
    Wang, Chao
    Yu, Zhibin
    Zheng, Haiyong
    Zheng, Bing
    Yang, Hua
    [J]. 2018 OCEANS - MTS/IEEE KOBE TECHNO-OCEANS (OTO), 2018,
  • [4] Transferred parallel convolutional neural network for large imbalanced plankton database classification
    Wang, Chao
    Zheng, Xueer
    Guo, Chunfeng
    Yu, Zhibin
    Yu, Jia
    Zheng, Haiyong
    Zheng, Bing
    [J]. 2018 OCEANS - MTS/IEEE KOBE TECHNO-OCEANS (OTO), 2018,
  • [5] A hybrid convolutional neural network for intelligent wear particle classification
    Peng, Yeping
    Cai, Junhao
    Wu, Tonghai
    Cao, Guangzhong
    Kwok, Ngaiming
    Zhou, Shengxi
    Peng, Zhongxiao
    [J]. TRIBOLOGY INTERNATIONAL, 2019, 138 : 166 - 173
  • [6] Detection and classification of epilepsy using hybrid convolutional neural network
    Sabarivani, A.
    Ramadevi, R.
    [J]. CONCURRENT ENGINEERING-RESEARCH AND APPLICATIONS, 2022, 30 (03): : 253 - 261
  • [7] A Lightweight Hybrid Convolutional Neural Network for Hyperspectral Image Classification
    Ma, Xiaohu
    Kang, Xudong
    Qin, Huawei
    Wang, Wuli
    Ren, Guangbo
    Wang, Jianbu
    Liu, Baodi
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [8] Enhanced convolutional neural network for plankton identification and enumeration
    Cheng, Kaichang
    Cheng, Xuemin
    Wang, Yuqi
    Bi, Hongsheng
    Benfield, Mark C.
    [J]. PLOS ONE, 2019, 14 (07):
  • [9] Banana Plant Disease Classification Using Hybrid Convolutional Neural Network
    Narayanan, K. Lakshmi
    Krishnan, R. Santhana
    Robinson, Y. Harold
    Julie, E. Golden
    Vimal, S.
    Saravanan, V.
    Kaliappan, M.
    [J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
  • [10] Hybrid quantum-classical convolutional neural network for phytoplankton classification
    Shi, Shangshang
    Wang, Zhimin
    Shang, Ruimin
    Li, Yanan
    Li, Jiaxin
    Zhong, Guoqiang
    Gu, Yongjian
    [J]. FRONTIERS IN MARINE SCIENCE, 2023, 10