Implementation of Convolutional Neural Network for Leaf Disease Detection in Cayenne Pepper Plantsaper
DOI:
https://doi.org/10.29103/sisfo.v10i2.27552Keywords:
Convolutional Neural Network, Cayenne Pepper, Leaf Disease DetectionAbstract
Cayenne pepper (Capsicum frutescens L.) is an economically important horticultural crop in Indonesia; however, its productivity is frequently affected by leaf diseases, including leaf curl, leaf spot, and yellow leaf disease. Conventional disease identification mainly relies on visual inspection, making the diagnosis highly dependent on farmers’ experience and increasing the possibility of inaccurate identification and delayed treatment. This study proposes a Convolutional Neural Network (CNN)-based approach for automatic chili leaf disease classification and implements the trained model in an Android application for offline real-time detection. A total of 2,000 images were collected from chili plantations located in Lhokseumawe City and Aceh Tamiang Regency. The dataset was organized into five balanced categories, namely healthy leaf, leaf curl, leaf spot, yellow leaf, and non-leaf, with 400 images assigned to each category. The addition of a non-leaf category enables the application to distinguish chili leaves from irrelevant objects during mobile-based detection. Before training, all images were resized to 150 × 150 pixels, normalized, and partitioned into training, validation, and testing sets using an 80:10:10 ratio. The proposed CNN architecture comprised three convolutional layers followed by max-pooling layers, a flatten layer, a fully connected layer, a dropout layer, and a Softmax output layer. Experimental evaluation on the testing dataset produced an overall accuracy of 89.50%, while the macro-average precision, recall, and F1-score reached 90%, 89%, and 89%, respectively. The trained model was successfully converted into TensorFlow Lite (TFLite) format and integrated into an Android application capable of providing real-time disease prediction, confidence scores, disease descriptions, treatment recommendations, and detection history without requiring an Internet connection. These results indicate that the proposed system is suitable for practical field deployment to support early identification of chili leaf diseases.
References
[1] Badan Pusat Statistik, “Produksi Tanaman Sayuran dan Buah–Buahan Semusim Menurut Jenis Tanaman, 2024,” Badan Pusat Statistik. Accessed: Jun. 01, 2026. [Online]. Available: https://www.bps.go.id/id/statistics-table/3/VFV4MmQxaG9kakZrVUdWeEx6aDFUMnN6WmpocVp6MDkjMw%3D%3D/produksi-tanaman-sayuran-dan-buah---buahan-semusim-menurut-jenis-tanaman--2024.html?year=2024
[2] C. Fadhila et al., “The threat of seed-transmissible pepper yellow leaf curl Indonesia virus in chili pepper,” Microb. Pathog., vol. 143, p. 104132, 2020, doi: 10.1016/j.micpath.2020.104132.
[3] D. G. W. Selangga, S. H. Hidayat, A. D. Susila, and S. Wiyono, “The Effect of Silica (SiO2) to the Severity of Yellow Leaf Curl Disease on Chili Pepper,” Jurnal Perlindungan Tanaman Indonesia, vol. 23, no. 1, p. 54, Jul. 2019, doi: 10.22146/jpti.38951.
[4] R. Kirana et al., “Interaction of Capsicum spp. with Bemisia tabaci and pepper yellow leaf curl virus (PepYLCV) Disease,” Sci. Rep., vol. 16, no. 1, p. 19211, Apr. 2026, doi: 10.1038/s41598-026-50183-0.
[5] T. Nyawose, R. C. Maswanganyi, and P. Khumalo, “A Review on the Detection of Plant Disease Using Machine Learning and Deep Learning Approaches,” Oct. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/jimaging11100326.
[6] X. Sun, S. Mu, Y. Xu, Z. Cao, and T. Su, “Image Recognition of Tea Leaf Diseases Based on Convolutional Neural Network,” CoRR, vol. abs/1901.02694, 2019, [Online]. Available: http://arxiv.org/abs/1901.02694
[7] M. Krichen, “Convolutional Neural Networks: A Survey,” Computers, vol. 12, no. 8, Aug. 2023, doi: 10.3390/computers12080151.
[8] F. N. Firdaus, “Analisis Kinerja MobileNetV2 dalam Klasifikasi Penyakit Daun Cabai Berdasarkan Citra,” Prosiding Seminar Nasional Teknologi dan Sains, 2026, pp. 289–296.
[9] M. R. Saputra and N. Rachmat, “Penggunaan Mobilenetv2 Pada Klasifikasi Penyakit Daun Cabai,” Jurnal Algoritme, vol. 6, no. 2, pp. 269–282, 2026, doi: 10.35957/algoritme.v6i2.13562.
[10] M. R. Ridhwan and Hudori, “Identifikasi Penyakit Virus Kuning pada Tanaman Cabai dengan Pendekatan CNN,” Jurnal SAINTEKOM (Sains dan Teknologi Komputasi), vol. 2, no. 1, pp. 66–78, Apr. 2026, doi: 10.36350/jskom.v2i1.81.
[11] I. I. Khoirunnisa, A. Fadlil, and H. Yuliansyah, “Perbandingan Kinerja MobileNetV2 dan VGG16 dalam Klasifikasi Penyakit pada Citra Daun Tanaman Cabai,” Jurnal Informatika Sunan Kalijaga), vol. 11, no. 1, pp. 70–82, 2026.
[12] R. Andrian, A. Junaidi, and D. Indah Lestari, “Aplikasi Pengukuran Luas Daun Tanaman Menggunakan Pengolahan Citra Digital Berbasis Android,” Jurnal Agrotropika, vol. 21, no. 2, pp. 115–123, 2022.
[13] A. Ramadhanu and H. Syahputra, “Pengenalan Teknologi Pengolahan Citra Digital (Digital Image Processing) Untuk Santri Di Rahmatan Lil’alamin International Islamic Boarding School,” Communnity Development Journal, vol. 3, no. 2, pp. 1239–1244, 2022.
[14] R. Yu, S. Liu, and X. Wang, “Dataset distillation: A comprehensive review,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 46, no. 1, pp. 150–170, 2023.
[15] A. Shamsaldin, P. Fattah, T. Rashid, and N. Al-Salihi, “A Study of The Convolutional Neural Networks Applications,” UKH Journal of Science and Engineering, vol. 3, no. 2, pp. 31–40, Dec. 2019, doi: 10.25079/ukhjse.v3n2y2019.pp31-40.
[16] Purwono, A. Ma’arif, W. Rahmaniar, H. I. K. Fathurrahman, A. Z. K. Frisky, and Q. M. U. Haq, “Understanding of Convolutional Neural Network (CNN): A Review,” International Journal of Robotics and Control Systems, vol. 2, no. 4, pp. 739–748, 2022, doi: 10.31763/ijrcs.v2i4.888.
[17] U. S. Rahmadhani and N. L. Marpaung, “Klasifikasi Jamur Berdasarkan Genus Dengan Menggunakan Metode CNN,” Jurnal Pengembangan IT (JPIT), vol. 8, no. 2, May 2023, doi: 10.30591/jpit.v8i2.5229.
[18] A. Zafar et al., “A Comparison of Pooling Methods for Convolutional Neural Networks,” Applied Sciences (Switzerland), vol. 12, no. 17, pp. 2–21, Sep. 2022, doi: 10.3390/app12178643.
[19] M. A. Haq, A. Ahmed, and J. Gyani, “Implementation of CNN for Plant Identification using UAV Imagery,” IJACSA) International Journal of Advanced Computer Science and Applications, vol. 14, no. 4, pp. 370–378, 2023, [Online]. Available: www.ijacsa.thesai.org
[20] A. Yulianto, W. Andreas, and S. Sabariman, “Perancangan Prototype Brankas Menggunakan Sistem Pengenalan Wajah Dengan Metode Convolutional Neural Network (CNN),” Telcomatics, vol. 8, no. 1, p. 10, Jun. 2023, doi: 10.37253/telcomatics.v8i1.7852.
[21] M. M. Taye, “Theoretical Understanding of Convolutional Neural Network: Concepts, Architectures, Applications, Future Directions,” Computation, vol. 11, no. 3, pp. 1–23, Mar. 2023, doi: 10.3390/computation11030052.
[22] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” arXiv preprint arXiv:1412.6980, 2014.
[23] B. Barz and J. Denzler, “Deep Learning on Small Datasets without Pre-Training using Cosine Loss,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 1371–1380.
[24] F. N. Rahman, T. Listyorini, and E. Supriyati, “Analisis Akurasi Cnn Pada Data Olah Suara Manusia Menggunakan Parameter Koefisien Mfcc Dan Max Length,” Jurnal Digit, vol. 15, no. 1, pp. 1–9, May 2025, doi: 10.51920/jd.v15i1.416.
[25] C. Imanuel and I. Fenriana, “Perancangan Aplikasi Presensi Jemaat Menggunakan Face Recognition Dengan Tensorflow Lite Pada Gereja Gkpy Vti Berbasis Android,” Akselerator : Jurnal Sains Terapan dan Teknologi, vol. 5, no. 1, pp. 75–90, Apr. 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ayu Suningsih, Zara Yunizar, Rizki Suwanda
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors retain copyright and grant the journal right of first publication and this work is licensed under a Creative Commons Attribution-ShareAlike 4.0 that allows others to share the work with an acknowledgement of the works authorship and initial publication in this journal.
All articles in this journal may be disseminated by listing valid sources and the title of the article should not be omitted. The content of the article is liable to the author.
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 acknowledgment 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) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
In the dissemination of articles by the author must declare the Sisfo: Jurnal Ilmiah Sistem Informasi as the first party to publish the article.
