Image classification of Chinese medicinal flowers based on convolutional neural network

Meiling Huang; Yixuan Xu; Meiling Huang; Yixuan Xu

doi:10.3934/mbe.2023671

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 8: 14978-14994. doi: 10.3934/mbe.2023671

Previous Article Next Article

Research article Special Issues

Image classification of Chinese medicinal flowers based on convolutional neural network

Meiling Huang ^,,
Yixuan Xu

Department of Industrial Engineering & Management, National Chin-Yi University of Technology, 57, Sec. 2, Chung-Shan Rd., Taiping, Taichung, Taiwan

Academic Editor: Shangce Gao

Received: 16 May 2023 Revised: 29 June 2023 Accepted: 09 July 2023 Published: 12 July 2023

Background and objective
Traditional Chinese medicine has used many herbs on the prevention and treatment of diseases for thousands of years. However, many flowers are poisonous and only few herbs have medicinal properties. Relying on experts for herbs identification is time consuming. An efficient and fast identification method is proposed in this study.

Methods
This study proposes ResNet101 models by combining SENet and ResNet101, adding convolutional block attention module or using Bayesian optimization on Chinese medicinal flower classification. The performances of the proposed ResNet101 models were compared.

Results
The best performance for accuracy, precision, recall, F1-score and PR-AUC are coming from ResNet101 model with Bayesian optimization which are 97.64%, 97.99%, 97.86%, 97.82% and 99.72%, respectively.

Conclusions
The proposed ResNet101 model provides a better solution on the image classification of Chinese medical flowers with favourable accuracy.
- Chinese medicinal flower,
- Squeeze-and-Excitation,
- classification,
- deep learning
Citation: Meiling Huang, Yixuan Xu. Image classification of Chinese medicinal flowers based on convolutional neural network[J]. Mathematical Biosciences and Engineering, 2023, 20(8): 14978-14994. doi: 10.3934/mbe.2023671

Related Papers:

Abstract

Background and objective

Traditional Chinese medicine has used many herbs on the prevention and treatment of diseases for thousands of years. However, many flowers are poisonous and only few herbs have medicinal properties. Relying on experts for herbs identification is time consuming. An efficient and fast identification method is proposed in this study.

Methods

This study proposes ResNet101 models by combining SENet and ResNet101, adding convolutional block attention module or using Bayesian optimization on Chinese medicinal flower classification. The performances of the proposed ResNet101 models were compared.

Results

The best performance for accuracy, precision, recall, F1-score and PR-AUC are coming from ResNet101 model with Bayesian optimization which are 97.64%, 97.99%, 97.86%, 97.82% and 99.72%, respectively.

Conclusions

The proposed ResNet101 model provides a better solution on the image classification of Chinese medical flowers with favourable accuracy.

References

[1]	H. Yuan, S. Jiang, Y. Liu, M. Daniyal, Y. Jian, C. Peng, et al., The flower head of Chrysanthemum morifolium Ramat. (Juhua): A paradigm of flowers serving as Chinese dietary herbal medicine, J. Ethnopharmacol., 261 (2020), 113043. https://doi.org/10.1016/j.jep.2020.113043 doi: 10.1016/j.jep.2020.113043
[2]	Y. Xu, G. Wen, Y. Hu, M. Luo, D. Dai, Y. Zhuang, et al., Multiple attentional pyramid networks for Chinese herbal recognition, Pattern Recognit., 110 (2021), 107558. https://doi.org/10.1016/j.patcog.2020.107558 doi: 10.1016/j.patcog.2020.107558
[3]	F. Jiang, Y. Lu, Y. Chen, D. Cai, G. Li, Image recognition of four rice leaf diseases based on deep learning and support vector machine, Comput. Electron. Agric., 179 (2020), 105824. https://doi.org/10.1016/j.compag.2020.105824 doi: 10.1016/j.compag.2020.105824
[4]	P. Kumari, B. Bhargava, Phytochemicals from edible flowers: Opening a new arena for healthy lifestyle, J. Funct. Foods, 78 (2021), 104375. https://doi.org/10.1016/j.jff.2021.104375 doi: 10.1016/j.jff.2021.104375
[5]	T. Lv, R. Teng, Q. Shao, H. Wang, W. Zhang, M. Li, et al., DNA barcodes for the identification of Anoectochilus roxburghii and its adulterants, Planta, 242 (2015), 1167–1174. https://doi.org/10.1007/s00425-015-2353-x doi: 10.1007/s00425-015-2353-x
[6]	Y. Chen, J. Huang, Z. Q. Yeap, X. Zhang, S. Wu, C. H. Ng, et al., Rapid authentication and identification of different types of A. roxburghii by Tri-step FT-IR spectroscopy, Spectrochim. Acta, Part A, 199 (2018), 271–282. https://doi.org/10.1016/j.saa.2018.03.061 doi: 10.1016/j.saa.2018.03.061
[7]	A. Jahanbakhshi, Y. Abbaspour-Gilandeh, K. Heidarbeigi, M. Momeny, Detection of fraud in ginger powder using an automatic sorting system based on image processing technique and deep learning, Comput. Biol. Med., 136 (2021), 104764. https://doi.org/10.1016/j.compbiomed.2021.104764 doi: 10.1016/j.compbiomed.2021.104764
[8]	K. IlBae, J. Park, J. Lee, Y. Lee, C. Lim, Flower classification with modified multimodal convolutional neural networks, Expert Syst. Appl., 159 (2020), 113455. https://doi.org/10.1016/j.eswa.2020.113455 doi: 10.1016/j.eswa.2020.113455
[9]	Q. Chai, J. Zeng, D. Lin, X. Li, J. Huang, W. Wang, Improved 1D convolutional neural network adapted to near-infrared spectroscopy for rapid discrimination of Anoectochilus roxburghii and its counterfeits, J. Pharm. Biomed. Anal., 199 (2021), 114035. https://doi.org/10.1016/j.jpba.2021.114035 doi: 10.1016/j.jpba.2021.114035
[10]	Y. Xu, G. Wen, Y. Hu, M. Luo, D. Dai, Y. Zhuang, et al., Multiple attentional pyramid networks for Chinese herbal recognition, Pattern Recognit., 110 (2021), 107558. https://doi.org/10.1016/j.patcog.2020.107558 doi: 10.1016/j.patcog.2020.107558
[11]	M. L. Huang, Y. X. Xu, Chinese medicinal blossom-dataset, Mendeley Data, V1, 2021. https://doi.org/10.17632/r3z6vp396m.1
[12]	K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016 (2016), 770–778. https://doi.org/10.1109/CVPR.2016.90
[13]	K. He, G. Gkioxari, P. Dollár, R. Girshick, Mask R-CNN, IEEE Trans. Pattern Anal. Mach. Intell., 42 (2020), 386–397. https://doi.org/10.1109/TPAMI.2018.2844175 doi: 10.1109/TPAMI.2018.2844175
[14]	W. Zhou, H. Wang, Z. Wan, Ore image classification based on improved CNN, Comput. Electr. Eng., 99 (2022), 107819. https://doi.org/10.1016/j.compeleceng.2022.107819 doi: 10.1016/j.compeleceng.2022.107819
[15]	X. Zhao, K. Li, Y. Li, J. Ma, L. Zhang, Identification method of vegetable diseases based on transfer learning and attention mechanism, Comput. Electron. Agric., 193 (2022), 106703. https://doi.org/10.1016/j.compag.2022.106703 doi: 10.1016/j.compag.2022.106703
[16]	A. Ma, Y. Wan, Y. Zhong, J. Wang, L. Zhang, SceneNet: Remote sensing scene classification deep learning network using multi-objective neural evolution architecture search, ISPRS J. Photogramm. Remote Sens., 172 (2021), 171–188. https://doi.org/10.1016/j.isprsjprs.2020.11.025 doi: 10.1016/j.isprsjprs.2020.11.025
[17]	Y. Wan, Y. Zhong, A. Ma, J. Wang, L. Zhang, E2SCNet: Efficient multiobjective evolutionary automatic search for remote sensing image scene classification network architecture, IEEE Trans. Neural Networks Learn. Syst., 2022 (2022). https://doi.org/10.1109/TNNLS.2022.3220699 doi: 10.1109/TNNLS.2022.3220699
[18]	D. Yu, Q. Xu, H. Guo, C. Zhao, Y. Lin, D. Li, An efficient and lightweight convolutional neural network for remote sensing image scene classification, Sensors, 20 (2020), 1999. https://doi.org/10.3390/s20071999 doi: 10.3390/s20071999
[19]	Z. Wu, F. Jiang, R. Cao, Research on recognition method of leaf diseases of woody fruit plants based on transfer learning, Sci. Rep., 12 (2022), 1538.
[20]	Y. Liu, Y. Sun, B. Xue, M. Zhang, G. G. Yen, K. C. Tan, A survey on evolutionary neural architecture search, IEEE Trans. Neural Networks Learn. Syst., 34 (2023), 550–570. https://doi.org/10.1109/TNNLS.2021.3100554 doi: 10.1109/TNNLS.2021.3100554
[21]	H. Li, Skin burns degree determined by computer image processing method, Phys. Procedia, 33 (2012), 758–764. https://doi.org/10.1016/j.phpro.2012.05.132 doi: 10.1016/j.phpro.2012.05.132
[22]	H. He, X. Huang, Y. Song, Z. Zhang, M. Wang, B. Chen, et al., An insulator self-blast detection method based on YOLOv4 with aerial images, Energy Rep., 8 (2022), 448–454. https://doi.org/10.1016/j.egyr.2021.11.115 doi: 10.1016/j.egyr.2021.11.115
[23]	L. Yang, H. Yu, Y. Cheng, S. Mei, Y. Duan, D. Li, et al., A dual attention network based on efficientNet-B2 for short-term fish school feeding behavior analysis in aquaculture, Comput. Electron. Agric., 187 (2021), 106316. https://doi.org/10.1016/j.compag.2021.106316 doi: 10.1016/j.compag.2021.106316
[24]	R. Zhang, J. Zhao, H. Xie, T. Wang, G. Chen, G. Zhang, et al., Automatic diagnosis for aggressive posterior retinopathy of prematurity via deep attentive convolutional neural network, Expert Syst. Appl., 187 (2021), 115843. https://doi.org/10.1016/j.eswa.2021.115843 doi: 10.1016/j.eswa.2021.115843
[25]	J. Hu, L. Shen, S. Albanie, G. Sun, E. Wu, Squeeze-and-Excitation networks, IEEE Trans. Pattern Anal. Mach. Intell., 42 (2020), 2011–2023. https://doi.org/10.1109/TPAMI.2019.291337 doi: 10.1109/TPAMI.2019.291337
[26]	S. Woo, J. Park, J. Y. Lee, I. S. Kweon, CBAM: Convolutional block attention module, in Proceedings of the European Conference on Computer Vision (ECCV), (2018), 3–19. https://doi.org/10.1007/978-3-030-01234-2_1

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)