Abstract
To address the issues of slow classification speed, group confusion, and difficult feature extraction in the flue-tobacco grouping task using single-size convolutional kernels in traditional convolutional neural networks, we propose a lightweight network model called FSANet. This model combines a multi-scale convolutional structure and attention mechanism. Firstly, we design a multi-scale feature fusion module (FSAConv) to extract and fuse multi-scale features from flue-treated tobacco images. The module utilizes feature partitioning strategies to assign feature subsets for parallel convolution and pooling operations simultaneously, enhancing the network's sensitivity to different semantic targets. Additionally, the subset features are adaptively calibrated through the SE (squeeze and excitation) channel attention mechanism. Furthermore, FSAConv introduces the Ghost convolution module and HardSwish activation function to maintain model expressiveness while reducing parameter count. Finally, based on the inverted residual of MobileNet, we construct a lightweight network called FSANet by replacing 3 × 3 convolutions with FSAConv modules. Using our self-constructed flue-cured tobacco dataset, experimental results demonstrate that compared with GHostNet and MobileNetV3 models, FSANet exhibits an increase of 13.8% and 20% in parameter count respectively while achieving accuracy improvements of 5% and 10%. The constructed FSANet model enhances classification accuracy for flue-cured tobacco with superior overall performance suitable for actual production scenarios with limited storage resources and low hardware capabilities.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Luo, H., Zhang, C.: Features representation for flue-cured tobacco grading based on transfer learning to hard sample. In: 2018 14th IEEE International Conference on Signal Processing (ICSP), August 2018. https://doi.org/10.1109/icsp.2018.8652385
Man, Z.: Effect of body and color on quality of tobacco leaves in technology grading. J. Anhui Agric. Sci. (2013)
Yang, S., Dong, C., Wang, F., Zhou, M., Yuan, M., Huang, J.: Fisher's tobacco leaf grading method based on image multi-features. In: 2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT), September 2022. https://doi.org/10.1109/aicit55386.2022.9930167
Harjoko, A., Prahara, A., Supardi, T.W., Candradewi, I., Pulungan, R., Hartati, S.: Image processing approach for grading tobacco leaf based on color and quality. Int. J. Smart Sens. Intell. Syst. 12(1), 1 (2019). https://doi.org/10.21307/ijssis-2019-010
Lin, J., et al.: CAMFFNet: a novel convolutional neural network model for tobacco disease image recognition. Comput. Electron. Agric. 107390 (2022). https://doi.org/10.1016/j.compag.2022.107390
Wu, J., Yang, S.X.: Modeling of the bulk tobacco flue-curing process using a deep learning-based method. IEEE Access 9, 140424–140436 (2021)
Lu, M., Jiang, S., Wang, C., Chen, D., Chen, T.: Tobacco leaf grading based on deep convolutional neural networks and machine vision. J. ASABE 65(1), 11–22 (2021). https://doi.org/10.13031/ja.14537
Lin, H., Bi, Y., Zhang, X., et al.: Deep Tobacco Leaf Grading Using Self-Adaptive Attention. Available at SSRN 4414972
Wei, X.S., Wu, J., Cui, Q.: Deep learning for fine-grained image analysis: a survey, arXiv preprint arXiv:1907.03069 (2019)
Lu, M., Jiang, S., Wang, C., et al.: Tobacco leaf grading based on deep convolutional neural networks and machine vision. J. ASABE 65(1), 11–22 (2022)
Chen, D., Zhang, Y., He, Z., Deng, Y., Zhang, P., Hai, W.: Feature-reinforced dual-encoder aggregation network for flue-cured tobacco grading, SSRN, February 2023. https://doi.org/10.2139/ssrn.4355545
Xiaowei, X., Huili, G., Ruotong, H., et al.: Intelligent large-scale flue-cured tobacco grading based on deep densely convolutional network. Sci. Rep. 13(1), 11119 (2023)
Lu, M., Wang, C., Wu, W., et al.: Intelligent grading of tobacco leaves using an improved bilinear convolutional neural network. IEEE Access 11, 68153–68170 (2023)
Barman, U., Choudhury, R.D., Sahu, D., Barman, G.G.: Comparison of convolution neural networks for smartphone image based real time classification of citrus leaf disease. Comput. Electron. Agric. (2020). https://doi.org/10.1016/j.compag.2020.105661
Wang, H., Gu, W., Liu, X., et al.: Classification algorithm for natural state tobacco primary and secondary groups based on lightweight SE-PPM. J. Northwest A&F Univ. (Nat. Sci. Edn.) 01, 1–11 (2024). https://doi.org/10.13207/j.cnki.jnwafu.2024.01.006. Accessed 24 Oct 2023
He, Z., He, P., Zhang, Y., et al.: Real-time grouping of tobacco through channel weighting and dynamic loss regulation. Ind. Crops Prod. 195, 116427 (2023)
Ming, X., Jinfeng, G., Zhong, Z., et al.: Multi-channel and multi-scale separable dilated convolutional neural network with attention mechanism for flue-cured tobacco classification. Neural Comput. Appl. 35(21), 15511–15529 (2023)
Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 42(8), 2011–2023 (2020). https://doi.org/10.1109/tpami.2019.2913372
Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., Xu, C.: GhostNet: more features from cheap operations. In: Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020. https://doi.org/10.1109/cvpr42600.2020.00165
Howard, A., et al.: Searching for MobileNetV3. In: Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), October 2019. https://doi.org/10.1109/iccv.2019.00140
Longlong, L., Zhifeng, W., Tingting, Z.: GBH-YOLOv5: ghost convolution with BottleneckCSP and tiny target prediction head incorporating YOLOv5 for PV panel defect detection. Electronics 12(3), 561 (2023)
Li, M., Lu, Y., Cao, S., et al.: A hyperspectral image classification method based on the nonlocal attention mechanism of a multiscale convolutional neural network. Sensors 23(6), 3190 (2023)
Hoang, V.T., Jo, K.H.: PydmobileNet: improved version of mobilenets with pyramid depthwise separable convolution, arXiv preprint arXiv:1811.07083 (2018)
Zhang, H., Zu, K., Lu, J., Zou, Y., Meng, D.: EPSANet: an efficient pyramid split attention block on convolutional neural network, arXiv preprint, May 2021
Acknowledgement
This work was supported by China Tobacco Corporation Yunnan tobacco company science and technology plan key projects [grant number: 2020530000241003 and grant number: 2021530000241012] and Kunming University of Science and Technology 2022 Student Extracurricular Academic and Technological Innovation Fund Project [grant number: 2022KJ117].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Su, Y., Hou, K., Long, J., Gai, X., Zhang, Y., Zhang, X. (2024). FSANet: A Lightweight Network for Tobacco Grouping Using Multi-scale Convolution and Attention Mechanism. In: Jin, H., Pan, Y., Lu, J. (eds) Computer Networks and IoT. IAIC 2023. Communications in Computer and Information Science, vol 2060. Springer, Singapore. https://doi.org/10.1007/978-981-97-1332-5_26
Download citation
DOI: https://doi.org/10.1007/978-981-97-1332-5_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-1331-8
Online ISBN: 978-981-97-1332-5
eBook Packages: Computer ScienceComputer Science (R0)