Open set maize seed variety classification using hyperspectral imaging coupled with a dual deep SVDD-based incremental learning framework
文献类型: 外文期刊
作者: Zhang, Liu 1 ; Huang, Jinze 1 ; Wei, Yaoguang 1 ; Liu, Jincun 1 ; An, Dong 1 ; Wu, Jianwei 5 ;
作者机构: 1.China Agr Univ, Natl Innovat Ctr Digital Fishery, Beijing 100083, Peoples R China
2.China Agr Univ, Key Lab Smart Farming Technol Aquat Anim & Livesto, Minist Agr & Rural Affairs, Beijing 100083, Peoples R China
3.Beijing Engn & Technol Res Ctr Internet Things Agr, Beijing 100083, Peoples R China
4.China Agr Univ, Coll Informat & Elect Engn, Beijing 100083, Peoples R China
5.Beijing Acad Agr & Forestry Sci, Res Ctr Informat Technol, Beijing 100097, Peoples R China
6.Beijing PAIDE Sci & Technol Dev Co Ltd, Beijing 100097, Peoples R China
关键词: Seed classification; Hyperspectral imaging; Open set recognition; Incremental learning; Deep learning
期刊名称:EXPERT SYSTEMS WITH APPLICATIONS ( 影响因子:8.5; 五年影响因子:8.3 )
ISSN: 0957-4174
年卷期: 2023 年 234 卷
页码:
收录情况: SCI
摘要: Rapid and non-destructive classification of seed varieties is one of the important goals pursued by modern seed industry. Due to the large number of maize varieties in practice, collecting training samples that exhaust all varieties to train a classifier is extremely difficult. Therefore, maize seed classification in the real world faces the challenge of variety renewal and rejection of unknown varieties. This paper proposes an end-to-end trainable incremental learning (IL) framework based on hypercube data. This method achieves class-IL via learning oneclass classifier (OCC) incrementally, and directly uses raw data as input without additional data preprocessing and feature extraction. The OCC is a dual deep support vector data description, which makes full use of spectral and spatial information to establish an exclusive hypersphere for a specific variety to receive the variety and reject unknown varieties. To remove the interference of redundant bands, a band attention and sparse constraint module is added to automatically assign the weights of redundant bands to zero, thereby maximally improving the performance of the model. Moreover, a new loss function is defined to alleviate the difficulty of parameter updating after sparse constraint. Experimental results on our open set indicate that the accuracy of the proposed method for receiving known varieties and rejecting unknown varieties are both above 91 %, which has significant advantages over the other two state-of-the-art IL methods. In the future, the corresponding OCCs can also be deleted from the whole framework according to the varieties eliminated by the government to reduce computational overhead and inter-class interference. Overall, the proposed method can perform both IL and open set recognition.
- 相关文献
作者其他论文 更多>>
-
A hyperspectral band selection method based on sparse band attention network for maize seed variety identification
作者:Zhang, Liu;Wei, Yaoguang;Liu, Jincun;An, Dong;Zhang, Liu;Wei, Yaoguang;Liu, Jincun;An, Dong;Zhang, Liu;Wei, Yaoguang;Liu, Jincun;An, Dong;Zhang, Liu;Wei, Yaoguang;Liu, Jincun;An, Dong;Wu, Jianwei;Wu, Jianwei
关键词:Hyperspectral imaging; Band selection; Attention mechanism; Deep learning; Seed variety identification
-
Maize seed variety identification using hyperspectral imaging and self-supervised learning: A two-stage training approach without spectral preprocessing
作者:Zhang, Liu;Zhang, Shubin;Liu, Jincun;Wei, Yaoguang;An, Dong;Zhang, Liu;Zhang, Shubin;Liu, Jincun;Wei, Yaoguang;An, Dong;Zhang, Liu;Zhang, Shubin;Liu, Jincun;Wei, Yaoguang;An, Dong;Zhang, Liu;Zhang, Shubin;Liu, Jincun;Wei, Yaoguang;An, Dong;Wu, Jianwei;Wu, Jianwei
关键词:Seed classification; Hyperspectral imaging; Self-supervised learning; Deep learning; Spectral analysis
-
Real-time fruit detection using deep neural networks on CPU (RTFD): An edge AI application
作者:Mao, DianHui;Sun, Hao;Li, XueBo;Yu, XuDong;Mao, DianHui;Zhang, QingChuan;Wu, JianWei
关键词:PicoDet-S; Lightweight; Edge devices; Quantization; Android
-
Development of an evapotranspiration estimation method for lettuce via mobile phones using machine vision: Proof of concept
作者:Zhangzhong, Lili;Gao, Hairong;Zheng, Wengang;Li, Jingjing;Wang, Dequn;Zhangzhong, Lili;Gao, Hairong;Zheng, Wengang;Li, Jingjing;Wang, Dequn;Wu, Jianwei
关键词:Image processing; Machine learning; Crop coefficient; Crop evapotranspiration
-
Non-destructive and in-situ detection of shrimp freshness using mid-infrared fiber-optic evanescent wave spectroscopy
作者:Zhou, Yunhai;Jiao, Leizi;Zhang, Yunhe;Dong, Daming;Zhou, Yunhai;Jiao, Leizi;Zhu, Qingzhen;Dong, Daming;Wu, Jianwei
关键词:Fiber-optic evanescent wave spectroscopy; Shrimp; Freshness; Non-destructive; In -situ
-
A novel honey authenticity detection system based on external cavity quantum cascade laser
作者:Liu, Yachao;Gao, Yuan;Jiao, Leizi;Dong, Daming;Gao, Yuan;Wu, Jianwei;Wu, Jianwei
关键词:Honey adulteration; Sweeteners; Identification; Infrared spectrum; Laser spectrum
-
A Combinatorial TIR1-Aux/IAA Co-Receptor System for Peach Fruit Softening
作者:Zhao, Yutong;Wang, Qing;Guan, Dan;Liu, Yueping;Yang, Haiqing;Wu, Jianwei;Liu, Yueping
关键词:peach; fruit ripening and softening; auxin; TIR1-Aux; IAA co-receptor