Klasifikasi Tingkat Kematangan Buah Tomat Berbasis Pengolahan Citra Dengan Metode YoloV8
DOI:
https://doi.org/10.29407/38wngc02Keywords:
HSV, , Kematangan Tomat, , Pengolahan Citra, YOLOv8, , Thresholding, Deteksi ObjekAbstract
Penelitian ini mengembangkan sistem klasifikasi tingkat kematangan buah tomat berbasis pengolahan citra dengan mengintegrasikan metode deteksi objek YOLOv8 dan analisis warna pada ruang warna HSV. Dataset yang digunakan dalam penelitian ini terdiri dari 150 citra buah tomat dengan variasi tingkat kematangan dan kondisi pencahayaan. Penentuan kematangan secara manual sering menimbulkan ketidakkonsistenan akibat subjektivitas penilai dan perbedaan intensitas cahaya. Untuk mengatasi permasalahan tersebut, YOLOv8 digunakan pada tahap awal untuk mendeteksi objek tomat melalui mekanisme single-stage object detection, di mana model secara simultan memprediksi kelas objek dan koordinat bounding box dalam satu proses inferensi. Hasil deteksi ini digunakan untuk mengekstraksi Region of Interest (ROI) secara presisi sehingga area analisis terbebas dari gangguan latar belakang.ROI yang diperoleh kemudian dikonversi dari ruang warna RGB ke HSV untuk memisahkan informasi warna dari komponen intensitas cahaya. Proses klasifikasi tingkat kematangan dilakukan dengan menganalisis distribusi nilai Hue menggunakan metode multi-level thresholding ke dalam tiga kategori, yaitu hijau, oranye, dan merah. Hasil pengujian menunjukkan bahwa YOLOv8 memperoleh akurasi deteksi sebesar 91,33%, yang merepresentasikan kemampuan model dalam menemukan dan membatasi objek tomat dengan bounding box yang tepat. Pada tahap klasifikasi, sistem berbasis analisis Hue menghasilkan akurasi sebesar 86,25%, dengan nilai presisi 92%, recall 93,24%, dan F1-score 92,62%. Perbedaan nilai akurasi tersebut disebabkan oleh perbedaan tujuan evaluasi, di mana akurasi deteksi mengukur performa lokalisasi objek, sedangkan akurasi klasifikasi mengukur ketepatan identifikasi tingkat kematangan. Tantangan seperti variasi intensitas cahaya, refleksi permukaan, serta tumpang tindih spektrum warna pada tomat setengah matang menyebabkan akurasi klasifikasi cenderung lebih rendah dibandingkan akurasi deteksi. Secara keseluruhan, integrasi YOLOv8 dengan analisis Hue pada ruang warna HSV mampu memberikan performa yang stabil dan andal untuk proses sortasi otomatis dan aplikasi pertanian cerdas (smart agriculture).
Downloads
References
[1] A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv preprint arXiv:2004.10934, 2020.
[2] J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
[3] Ultralytics, “YOLOv8 Documentation,” 2023. [Online]. Available: https://docs.ultralytics.com/
[4] W. Liu et al., “SSD: Single Shot MultiBox Detector,” in European Conference on Computer Vision, 2016, pp. 21–37.
[5] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed. Pearson, 2018.
[6] A. R. Smith, “Color gamut transform pairs,” ACM SIGGRAPH Computer Graphics, vol. 12, no. 3, pp. 12–19, 1978.
[7] N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62–66, 1979.
[8] H. D. Cheng, X. Jiang, Y. Sun, and J. Wang, “Color image segmentation: Advances and prospects,” Pattern Recognition, vol. 34, no. 12, pp. 2259–2281, 2001.
[9] G. Sharma, “Digital color imaging,” IEEE Transactions on Image Processing, vol. 12, no. 9, pp. 1241–1253, 2003.
[10] P. Soille, Morphological Image Analysis, 2nd ed. Springer, 2003.
[11] J. Serra, Image Analysis and Mathematical Morphology. Academic Press, 1982.
[12] S. Dhakal and S. K. Boddhu, “Fruit maturity detection using CNN-based color and texture analysis,” International Journal of Computer Vision and Signal Processing, vol. 9, no. 2, pp. 33–42, 2019.
[13] P. Pawara et al., “Comparing CNN and hand-crafted features for classification of plant diseases,” International Journal of Advanced Science and Engineering, 2017.
[14] K. Patel and J. Kumar, “Tomato ripeness classification using machine learning approaches,” Journal of Agricultural Informatics, vol. 11, no. 2, pp. 45–55, 2020.
[15] S. A. Khoje, P. D. Muley, and S. K. Mankar, “Color-based fruit maturity detection using HSV and edge detection,” International Journal of Engineering Research and Technology, vol. 8, no. 6, pp. 512–516, 2019.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Servina Hoar Seran, Danang Wahyu Widodo, Umi Mahdiyah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment 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 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
