Deep Learning-Based Galls and Healthy Leaf Recognition Using Depthwise Separable CNN Architecture
Received: 26 March 2025 | Accepted: 1 May 2025 | Online: 4 June 2025
Corresponding author: Imam Yuadi
Abstract
Alstonia scholaris plays an important role in tropical ecosystems, contributing to soil conservation and carbon sequestration. However, it is susceptible to pest infestations, especially galls caused by a variety of factors, which can affect the growth and health of plants. This study employed a deep learning approach to classify healthy and gall-affected leaves using CNN with Depthwise Separable Convolution (DSC). A dataset consisting of 11,800 leaf images was processed with various augmentation and filtering techniques to evaluate their effect on classification performance. The experimental results indicated that the optimized filter achieved the highest accuracy (99.3%) in differentiating between healthy leaves and leaves affected by galls. The CNN model utilizing DSC was selected for its ability to significantly decrease computational complexity while maintaining classification accuracy, making it suitable for efficient image analysis jobs. This study shows that deep learning could function as an effective option for the early detection of plant diseases. Future investigations should examine transfer learning and multispectral imaging methods to improve model adaptability and classification precision.
Keywords:
alstonia scholaris, plants, CNN depthwise separable convolution, image preprocessingDownloads
References
H. Singh, "An integrated approach considering physiological- and biophysical-based indicators for assessing tolerance of roadside plantations of Alstonia scholaris towards urban roadside air pollution: an assessment of adaptation of plantations for mitigating roadside air pollution," Trees, vol. 37, no. 1, pp. 69–83, Feb. 2023. DOI: https://doi.org/10.1007/s00468-021-02179-8
S. Sookying, A. Panase, P. Srisuttha, A. Chaophothun, and P. Panase, "Devil’s tree flower ( Alstonia scholaris ) extract: positive effects on growth performance and serum biochemical indices in Channa striata (Bloch, 1793)," Journal of Applied Animal Research, vol. 51, no. 1, pp. 677–683, Dec. 2023. DOI: https://doi.org/10.1080/09712119.2023.2273279
A. Majid and H. R. Faraj, "A review Study of The Chemical Constituents and Pharmacological Activities of Alstonia scholaris linn," University of Thi-Qar Journal of Science, vol. 10, no. 1, pp. 81–86, Jun. 2023. DOI: https://doi.org/10.32792/utq/utjsci/v10i1.934
Ka. Chowdary and R. Jash, "Ethanolic extracts of Alstonia Scholaris and Bacopa Monniera possess neuroleptic activity due to anti-dopaminergic effect," Pharmacognosy Research, vol. 6, no. 1, 2014, Art. no. 46. DOI: https://doi.org/10.4103/0974-8490.122917
K. Pandey and A. S. Kate, "Comparative analysis of foliar galls and ungalled leaves of Alstonia scholaris with a focus on tissue ultrastructure and phytochemistry," Biochemical Systematics and Ecology, vol. 115, Aug. 2024, Art. no. 104851. DOI: https://doi.org/10.1016/j.bse.2024.104851
O. P. Datta and S. C. Datta, "Studies on the histomorphology of leaf galls on Alstonia scholaris L. (Apocynaceae) induced by Pauropsylla tuberculata Crawford," International Journal of Agricultural Invention, vol. 1, no. 01, pp. 65–70, Jun. 2016. DOI: https://doi.org/10.46492/IJAI/2016.1.1.10
A. Muhammad, N. Kumar, I. I. Dangora, I. I. Muhammad, A. Mathur, and M. Abdulhamid, "Incidence, severity and biochemical studies of Alstonia scholaris (L.) R. Br. Foliar Galls," International Journal of Plant Pathology and Microbiology, vol. 3, no. 2, pp. 7–12, 2023.
M. Ayaz et al., "Automatic Early Diagnosis of Dome Galls in Cordia Dichotoma G. Forst. Using Deep Transfer Learning," IEEE Access, vol. 11, pp. 59511–59523, 2023. DOI: https://doi.org/10.1109/ACCESS.2023.3283568
R. Harsha, S. Karthika, M. Priya D, R. Kanna P, G. Rajeshkumar, and E. Mythili, "Folla Disease Detection using In-Depth Learning," in 2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), Salem, India, May 2023, pp. 547–552. DOI: https://doi.org/10.1109/ICAAIC56838.2023.10141305
M. Dias and C. T. Lopes, "Optimization of Image Processing Algorithms for Character Recognition in Cultural Typewritten Documents," Journal on Computing and Cultural Heritage, vol. 16, no. 4, pp. 1–25, Dec. 2023. DOI: https://doi.org/10.1145/3606705
M. B. E. Luogon and F. Al-Turjman, "Cassava leave disease image classification based on deep convolutional neural network," in Artificial Intelligence of Things (AIoT), Elsevier, 2025, pp. 65–72. DOI: https://doi.org/10.1016/B978-0-443-26482-5.00008-0
T. Ren, Y. Zhang, and C. Wang, "Identification of Corn Leaf Disease Based on Image Processing," in 2019 2nd International Conference on Information Systems and Computer Aided Education (ICISCAE), Dalian, China, Sep. 2019, pp. 165–168. DOI: https://doi.org/10.1109/ICISCAE48440.2019.221610
Y. Q. Liu, X. Du, H. L. Shen, and S. J. Chen, "Estimating Generalized Gaussian Blur Kernels for Out-of-Focus Image Deblurring," IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 3, pp. 829–843, Mar. 2021. DOI: https://doi.org/10.1109/TCSVT.2020.2990623
P. A. Lyakhov, A. S. Abdulsalyamova, M. R. Kiladze, D. I. Kaplun, and A. S. Voznesensky, "Method of Oriented Contour Detection on Image Using Lorentz Function," in 2020 9th Mediterranean Conference on Embedded Computing (MECO), Budva, Montenegro, Jun. 2020, pp. 1–4. DOI: https://doi.org/10.1109/MECO49872.2020.9134224
R. Ratajczak, C. F. Crispim-Junior, E. Faure, B. Fervers, and L. Tougne, "Automatic Land Cover Reconstruction From Historical Aerial Images: An Evaluation of Features Extraction and Classification Algorithms," IEEE Transactions on Image Processing, vol. 28, no. 7, pp. 3357–3371, Jul. 2019. DOI: https://doi.org/10.1109/TIP.2019.2896492
W. Li, Z. Zhao, J. Du, and Y. Wang, "Edge-Preserve Filter Image Enhancement with Application to Medical Image Fusion," Journal of Medical Imaging and Health Informatics, vol. 7, no. 1, pp. 16–24, Feb. 2017. DOI: https://doi.org/10.1166/jmihi.2017.1980
L. Zhang and Y. Wan, "Color-to-gray image conversion using salient colors and radial basis functions," Journal of Electronic Imaging, vol. 33, no. 01, Feb. 2024. DOI: https://doi.org/10.1117/1.JEI.33.1.013047
B. J. Borah and C.-K. Sun, "A GPU-Accelerated Modified Unsharp-Masking Method for High-Frequency Background- Noise Suppression," IEEE Access, vol. 9, pp. 68746–68757, 2021. DOI: https://doi.org/10.1109/ACCESS.2021.3077287
R. Zhang, F. Zhu, J. Liu, and G. Liu, "Depth-Wise Separable Convolutions and Multi-Level Pooling for an Efficient Spatial CNN-Based Steganalysis," IEEE Transactions on Information Forensics and Security, vol. 15, pp. 1138–1150, 2020. DOI: https://doi.org/10.1109/TIFS.2019.2936913
S. Sathyanarayanan, "Confusion Matrix-Based Performance Evaluation Metrics," African Journal of Biomedical Research, pp. 4023–4031, Nov. 2024. DOI: https://doi.org/10.53555/AJBR.v27i4S.4345
S. Farhadpour, T. A. Warner, and A. E. Maxwell, "Selecting and Interpreting Multiclass Loss and Accuracy Assessment Metrics for Classifications with Class Imbalance: Guidance and Best Practices," Remote Sensing, vol. 16, no. 3, Jan. 2024, Art. no. 533. DOI: https://doi.org/10.3390/rs16030533
L. Liao, B. Li, and J. Tang, "Plants Disease Image Classification Based on Lightweight Convolution Neural Networks," International Journal of Pattern Recognition and Artificial Intelligence, vol. 36, no. 13, Oct. 2022, Art. no. 2254013. DOI: https://doi.org/10.1142/S0218001422540131
A. Patil, "Plant Leaf Disease Classification Using SVM and CNN Algorithms," International Journal of Food And Nutrutional Sciences, vol. 11, no. 13, pp. 223–227, Nov. 2022.
K. Kc, Z. Yin, M. Wu, and Z. Wu, "Depthwise separable convolution architectures for plant disease classification," Computers and Electronics in Agriculture, vol. 165, Oct. 2019, Art. no. 104948. DOI: https://doi.org/10.1016/j.compag.2019.104948
R. H. Altaie and H. K. Hoomod, "An Intrusion Detection System using a Hybrid Lightweight Deep Learning Algorithm," Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 16740–16743, Oct. 2024. DOI: https://doi.org/10.48084/etasr.7657
S. Saleem, M. I. Sharif, M. I. Sharif, M. Z. Sajid, and F. Marinello, "Comparison of Deep Learning Models for Multi-Crop Leaf Disease Detection with Enhanced Vegetative Feature Isolation and Definition of a New Hybrid Architecture," Agronomy, vol. 14, no. 10, Sep. 2024, Art. no. 2230. DOI: https://doi.org/10.3390/agronomy14102230
M. A. Naeem et al., "Deep Learning-Based Approach for Identification of Potato Leaf Diseases Using Wrapper Feature Selection and Feature Concatenation." arXiv, Apr. 29, 2025. DOI: https://doi.org/10.21203/rs.3.rs-4155580/v1
S. Saleem, A. Hussain, N. Majeed, Z. Akhtar, and K. Siddique, "A Multi-Scale Feature Extraction and Fusion Deep Learning Method for Classification of Wheat Diseases," Journal of Computer Science, vol. 21, no. 1, pp. 34–42, Jan. 2025. DOI: https://doi.org/10.3844/jcssp.2025.34.42
Downloads
How to Cite
License
Copyright (c) 2025 Imam Yuadi, Nisak Ummi Nazikhah, Chih-Chien Hu, Khoirun Nisa’, Vasanthadev S. Suryakala
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
