Medicinal Plant Leaf Classification using Deep Learning and Vision Transformers
DOI:
https://doi.org/10.21123/bsj.2024.10844Keywords:
Classification, CNN-ViT, Medicinal Plant Leaf, Transfer learning, Vision Transformer.Abstract
Identification of medicinal plant leaves is very crucial as their cultivation and production are essential for the medicine industry. Many different classes of medicinal leaves look identical but serve different purposes in the medicine industry and have different remedies for different diseases. Hence it is imperative to use methods that are automated, faster, and produce good accuracy. Cutting-edge models have been trained to discern the subtle distinctions between various species of leaves, accounting for a myriad of factors such as leaf texture, shape, and color variations, which are often imperceptible to the human eye. In this research, Transfer learning (TL) based VGG16 and Vision Transformer (ViT) models such as ConvMixer and Compact Convolutional Transformer (CCT) are implemented for the classification of medicinal leaf images using a dataset of 38066 leaf images having 10 different classes. The proposed customized Convolutional Neural Network (CNN) and hybrid CNN-ViT models both have a very low number of parameters compared to the other models in comparison making them light and capable of being less computationally expensive. In the experimental evaluation, all the results are collected for 30 epochs. VGG16, CCT, and ConvMixer produce AUC scores of 0.50, 0.79, and 0.50, respectively for the dataset while the proposed CNN and hybrid model gave AUC scores of 0.83 and 0.74, respectively. In addition, a hybrid denoising approach with Wavelet thresholding and Gaussian blurring is utilized to minimize the noises in the images by retaining the original image quality.
Received 04/02/2024
Revised 24/05/2024
Accepted 26/05/2024
Published Online First 20/10/2024
References
Hassoon IM, Qassir SA, Riyadh M. PDCNN: FRAMEWORK for Potato Diseases Classification Based on Feed Foreword Neural Network. Baghdad Sci J. 2021; 18(2 (Suppl.)): 1012-1012. https://doi.org/10.21123/bsj.2023.9120.
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM. 2017 May 24; 60(6): 84-90. https://doi.org/10.1145/3065386.
Jassim OA, Abed MJ, Saied ZH. Indoor/Outdoor Deep Learning Based Image Classification for Object Recognition Applications. Baghdad Sci J. 2023; 20(6 (Suppl.)): 2540-2540. https://doi.org/10.21123/bsj.2023.8177
Abdullah TH, Alizadeh F, Abdullah BH. COVID-19 Diagnosis System using SimpNet Deep Model. Baghdad Sci J. 2022; 19: 1078-1089. https://doi.org/10.21123/bsj.2022.6074
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint. 2020 Oct 22; 1-22. https://doi.org/10.48550/arXiv.2010.11929.
Ariful Hassan M, Sydul Islam M, Mehedi Hasan M, Shorif SB, Tarek Habib M, Uddin MS. Medicinal plant recognition from leaf images using deep learning. In Computer Vision and Machine Learning in Agriculture. Singapore: Springer Singapore. 2022 Mar 14; 137-154. https://doi.org/10.1007/978-981-16-9991-7_9.
Chanyal H, Yadav RK, Saini DK. Classification of medicinal plants leaves using deep learning technique: A review. Int J Int Sys App Eng. 2022 Dec 16; 10(4): 78-87. https://orcid.org/0000-0001-9678-0125
Naeem S, Ali A, Chesneau C, Tahir MH, Jamal F, Sherwani RA, Ul Hassan M. The classification of medicinal plant leaves based on multispectral and texture feature using machine learning approach. J Agron. 2021 Jan 30; 11(2): 1-15. https://doi.org/10.3390/agronomy11020263.
Kaur M, Bhatia R. Development of an improved tomato leaf disease detection and classification method. In IEEE Conference on Information and Communication Technology 2019; Dec 6: 1-5. IEEE. https://doi.org/10.1109/CICT48419.2019.9066230.
Rani L, Devika G, Karegowda AG, Vidya S, Bhat S. Identification of medicinal leaves using state of art deep learning techniques. In IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE). 2022; Apr 23: 1-5. IEEE. https://doi.org/10.1109/ICDCECE53908.2022.9792712
Ahmed MR, Fahim MA, Islam AM, Islam S, Shatabda S. DOLG-NeXt: Convolutional neural network with deep orthogonal fusion of local and global features for biomedical image segmentation. J Neurocom. 2023 Aug 14; 546: 126362. https://doi.org/10.1016/j.neucom.2023.126362.
Islam S, Ahmed MR, Islam S, Rishad MM, Ahmed S, Utshow TR, Siam MI. BDMediLeaves: A leaf images dataset for Bangladeshi medicinal plants identification. J Data Brief. 2023 Oct 1; 50: 109488. https://doi.org/10.1016/j.dib.2023.109488.
Chithra K, Santhanam T. Hybrid denoising technique for suppressing Gaussian noise in medical images. IEEE Int Conf PCSI 2017; Sep 21: 1460-1463. IEEE. https://doi.org/10.1109/ICPCSI.2017.8391954.
Al Jumah A. Denoising of an image using discrete stationary wavelet transform and various thresholding techniques. JSIP 2013; 4: 33–41. https://doi.org/10.4236/jsip.2013.41004.
Devi TG, Patil N, Rai S, Philipose CS. Gaussian blurring technique for detecting and classifying acute lymphoblastic leukemia cancer cells from microscopic biopsy images. J Life. 2023 Jan 28; 13(2): 1-12 https://doi.org/10.3390/life13020348.
Hassani A, Walton S, Shah N, Abuduweili A, Li J, Shi H. Escaping the big data paradigm with compact transformers. arXiv preprint arXiv:2104.05704. 2021 Apr 12; 1-18 https://doi.org/10.48550/arXiv.2104.05704.
Trockman A, Kolter JZ. Patches are all you need?. arXiv preprint arXiv. 2022 Jan 24; 1-16. https://doi.org/10.48550/arXiv.2201.09792
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv. 2014; 1409:1556, 1-14. https://doi.org/10.48550/arXiv.1409.1556.
Downloads
Issue
Section
License
Copyright (c) 2024 Shahriar Hossain, Rizbanul Hasan, Jia Uddin
This work is licensed under a Creative Commons Attribution 4.0 International License.