PENERAPAN MODEL YOLOV8 UNTUK IDENTIFIKASI DINI PENYAKIT DAUN TOMAT MENGGUNAKAN CITRA DIGITAL

Arvina Rizqi Nurul'aini; Mohammad Mahruf Alam

doi:10.30587/indexia.v7i2.9910

Authors

Arvina Rizqi Nurul'aini Universitas Negeri Semarang
Mohammad Mahruf Alam Universitas Negeri Semarang

DOI:

https://doi.org/10.30587/indexia.v7i2.9910

Keywords:

Deteksi Citra Digital, Penyakit Daun Tomat, YOLOv8

Abstract

Deteksi dini penyakit daun tomat sangat penting untuk menjaga produktivitas pertanian dan keberlanjutan pangan. Penelitian ini menggunakan model YOLOv8 untuk mendeteksi dan mengklasifikasikan sembilan jenis kondisi daun tomat berdasarkan citra digital. Dataset yang digunakan berasal dari Tomato Leaf Dataset dengan proses praproses meliputi penambahan data dan konversi label ke format YOLO. Model dilatih dan diuji menggunakan metrik evaluasi seperti presisi, recall, dan F1-score. Hasilnya menunjukkan kinerja tinggi pada kelas Late Blight dengan F1-score sebesar 0,979, presisi 0,959, dan recall 1,000. Sementara itu, kelas dengan performa rendah adalah Bacterial Spot (F1-score 0,525, presisi 0,541, recall 0,510) dan Healthy (F1-score 0,499, presisi 0,923, recall 0,342), terutama disebabkan oleh ketidakseimbangan data. Confusion Matrix menunjukkan bahwa kesalahan klasifikasi terbesar terjadi pada kelas dengan gejala visual yang mirip atau jumlah data yang terbatas. Model ini menunjukkan potensi besar dalam mendeteksi penyakit daun tomat secara otomatis. Namun, peningkatan kinerja per kelas masih diperlukan melalui penyeimbangan data dan strategi pelatihan tingkat lanjut.

Downloads

Download data is not yet available.

References

[1] K. Roy dkk., “Detection of Tomato Leaf Diseases for Agro-Based Industries Using Novel PCA DeepNet,” IEEE Access, vol. 11, hlm. 14983–15001, 2023, doi: 10.1109/ACCESS.2023.3244499.

[2] B. S. Vidhyasagar, K. Harshagnan, M. Diviya, dan S. Kalimuthu, “Prediction of Tomato Leaf Disease Plying Transfer Learning Models,” IFIP Adv Inf Commun Technol, vol. 683 AICT, hlm. 293–305, 2024, doi: 10.1007/978-3-031-45878-1_20.

[3] J. Agarwal, S. Gupta, N. Sharma, dan M. Manchanda, “A CNN Method Based Predictive Model for Tomato Leaf Disease Prediction,” Proceedings - International Conference on Technological Advancements in Computational Sciences, ICTACS 2023, hlm. 262–266, 2023, doi: 10.1109/ICTACS59847.2023.10390480.

[4] M. Sardogan, A. Tuncer, dan Y. Ozen, “Plant Leaf Disease Detection and Classification Based on CNN with LVQ Algorithm,” UBMK 2018 - 3rd International Conference on Computer Science and Engineering, hlm. 382–385, Des 2018, doi: 10.1109/UBMK.2018.8566635.

[5] K. Simonyan dan A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 2015.

[6] M. R. Foolad, H. L. Merk, dan H. Ashrafi, “Genetics, Genomics and Breeding of Late Blight and Early Blight Resistance in Tomato,” CRC Crit Rev Plant Sci, vol. 27, no. 2, hlm. 75–107, Mar 2008, doi: 10.1080/07352680802147353.

[7] R. Concepcion, S. Lauguico, E. Dadios, A. Bandala, E. Sybingco, dan J. Alejandrino, “Tomato septoria leaf spot necrotic and chlorotic regions computational assessment using artificial bee colony-optimized leaf disease index,” IEEE Region 10 Annual International Conference, Proceedings/TENCON, vol. 2020-November, hlm. 1243–1248, Nov 2020, doi: 10.1109/TENCON50793.2020.9293743.

[8] J. Abdulridha, Y. Ampatzidis, S. C. Kakarla, dan P. Roberts, “Detection of target spot and bacterial spot diseases in tomato using UAV-based and benchtop-based hyperspectral imaging techniques,” Precis Agric, vol. 21, no. 5, hlm. 955–978, Okt 2020, doi: 10.1007/S11119-019-09703-4/METRICS.

[9] Y. Lakhdari, E. Soldevila, J. Rezgui, dan É. Renault, “Detection of Plant Diseases in an Industrial Greenhouse: Development, Validation & Exploitation,” 2023 International Symposium on Networks, Computers and Communications, ISNCC 2023, 2023, doi: 10.1109/ISNCC58260.2023.10323932.

[10] M. Kavaliauskas dan T. Sledevič, “Identification of Tomato Leaf Disease using YOLOv8 Detection Models on GPU and Raspberry Pi,” 2024 IEEE Open Conference of Electrical, Electronic and Information Sciences, eStream 2024 - Proceedings, 2024, doi: 10.1109/ESTREAM61684.2024.10542533.

[11] M. Shahriar Zaman Abid, B. Jahan, A. Al Mamun, M. Jakir Hossen, dan S. Hossain Mazumder, “Bangladeshi crops leaf disease detection using YOLOv8,” Heliyon, vol. 10, no. 18, hlm. e36694, Sep 2024, doi: 10.1016/J.HELIYON.2024.E36694.

[12] X. Liu, H. Lei, Y. Zhou, J. M. Feng, G. Niu, dan Y. Zhou, “Tomato leaf disease detection based on improved YOLOv8,” 2024 6th International Conference on Internet of Things, Automation and Artificial Intelligence, IoTAAI 2024, hlm. 145–150, 2024, doi: 10.1109/IOTAAI62601.2024.10692846.

[13] S. G. E. Brucal, L. C. M. De Jesus, S. R. Peruda, L. A. Samaniego, dan E. D. Yong, “Development of Tomato Leaf Disease Detection using YoloV8 Model via RoboFlow 2.0,” GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics, hlm. 692–694, 2023, doi: 10.1109/GCCE59613.2023.10315251.

[14] D. Sutaji dan O. Yıldız, “LEMOXINET: Lite ensemble MobileNetV2 and Xception models to predict plant disease,” Ecol Inform, vol. 70, hlm. 101698, Sep 2022, doi: 10.1016/J.ECOINF.2022.101698.

[15] A. Imtiaz, F. B. I. Swapnil, S. R. Masud, dan D. Karmaker, “Tomato leaf dataset: A dataset for multiclass disease detection and classification,” Data Brief, vol. 60, hlm. 111520, Jun 2025, doi: 10.1016/J.DIB.2025.111520.

[16] S. G. E. Brucal, L. C. M. De Jesus, S. R. Peruda, L. A. Samaniego, dan E. D. Yong, “Development of Tomato Leaf Disease Detection using YoloV8 Model via RoboFlow 2.0,” GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics, hlm. 692–694, 2023, doi: 10.1109/GCCE59613.2023.10315251.

[17] N. K. E, K. M, P. P, A. R, dan V. S, “Tomato Leaf Disease Detection using Convolutional Neural Network with Data Augmentation,” hlm. 1125–1132, Jul 2020, doi: 10.1109/ICCES48766.2020.9138030.

[18] A. Swaroop, A. Satsangi, M. Sameer, dan G. Ahmad, “Performance Evaluation of YOLOv5 and YOLOv8 for Vehicle Detection: A Comparative Study,” 2024 15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024, 2024, doi: 10.1109/ICCCNT61001.2024.10723901.

[19] “Ringkasan singkat struktur model YOLOv8 · Edisi #189 · ultralytics/ultralytics.” Diakses: 4 Juni 2025. [Daring]. Tersedia pada: https://github.com/ultralytics/ultralytics/issues/189