Optimasi dan Analisis Kinerja MobileNetV2 dan VGG16 untuk Klasifikasi Jenis Sirih Berdasarkan Morfologi Daun: Optimization and Performance Analysis of MobileNetV2 and VGG16 for Betel Leaf Species Classification Based on Leaf Morphological Characteristics

Pramita Widya Ningrum; Christian D. Suhendra; Elieser Y. I. V. Sirami

doi:10.57152/malcom.v6i3.2749

Authors

Pramita Widya Ningrum Universitas Papua
Christian D. Suhendra Universitas Papua
Elieser Y. I. V. Sirami Universitas Papua

DOI:

https://doi.org/10.57152/malcom.v6i3.2749

Keywords:

Klasifikasi sirih, MobileNetV2, VGG16, Morfologi Daun, Transfer Learning

Abstract

Daun sirih memiliki keragaman morfologi yang cukup tinggi, tanaman ini banyak digunakan dalam bidang kesehatan, praktik budaya, dan kegiatan ekonomi di berbagai wilayah Asia. Oleh karena itu, identifikasi spesies yang akurat menjadi penting untuk mendukung budidaya dan pemanfaatannya secara optimal. Namun, identifikasi secara manual masih menjadi tantangan karena sangat bergantung pada keahlian pakar. Sebagian besar penelitian berbasis citra pada daun sirih berfokus pada deteksi penyakit, sedangkan klasifikasi spesies masih mendapat perhatian yang terbatas. Akibatnya, bukti mengenai efektivitas model deep learning dalam membedakan perbedaan morfologi yang halus antarspesies daun sirih masih relatif sedikit. Penelitian ini mengevaluasi kinerja MobileNetV2 dan model VGG16 yang telah dioptimasi untuk mengklasifikasikan tiga jenis daun sirih berdasarkan karakteristik morfologinya. MobileNetV2 digunakan sebagai model transfer learning dasar (baseline). Sementara itu, VGG16 yang telah dilatih sebelumnya pada dataset ImageNet dioptimasi dengan membekukan lapisan konvolusional dan memodifikasi lapisan klasifikasi untuk tiga kelas keluaran. Hasil penelitian menunjukkan bahwa VGG16 yang telah dioptimasi mencapai akurasi validasi sebesar 95,50% dan macro F1-Score sebesar 0,95. Kinerja tersebut lebih baik dibandingkan MobileNetV2 yang memperoleh akurasi validasi sebesar 89,23% dan macro F1-Score sebesar 0,88. Temuan ini menunjukkan bahwa VGG16 yang telah dioptimasi merupakan pendekatan yang efektif dan andal untuk klasifikasi spesies daun sirih berdasarkan karakteristik morfologinya.

Downloads

Download data is not yet available.

References

N. Puspitasari, A. Septiarini, U. Hairah, A. Tejawati, and H. Sulastri, “Betel leaf classification using color-texture features and machine learning approach,” Bull. Electr. Eng. Informatics, vol. 12, no. 5, pp. 2939–2947, Oct. 2023, doi: 10.11591/EEI.V12I5.5101.

D. D. Simamora, M. Basri, and A. Zulherry, “Application of Support Vector Machine and Image Segmentation Methods to Classify Types of Medicinal Leaves in Betel Leaves,” IJATCoS Indones. J. Appl. Technol. Comput. Sci., vol. 2, no. 2, pp. 46–56, Aug. 2025, Accessed: Dec. 06, 2025. [Online]. Available: https://jurnal.umsu.ac.id/index.php/Ijatcos/article/view/21337

S. Tabassum and M. F. Ahamed, “CBAM Integrated Attention Driven Model For Betel Leaf Diseases Classification With Explainable AI,” Sep. 2025, Accessed: Jan. 14, 2026. [Online]. Available: https://arxiv.org/abs/2509.26484v1

B. D. Mardiana, W. B. Utomo, U. N. Oktaviana, G. W. Wicaksono, and A. E. Minarno, “Herbal Leaves Classification Based on Leaf Image Using CNN Architecture Model VGG16,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 7, no. 1, pp. 20–26, Feb. 2023, doi: 10.29207/RESTI.V7I1.4550.

B. Dey, J. Ferdous, R. Ahmed, and J. Hossain, “Assessing deep convolutional neural network models and their comparative performance for automated medicinal plant identification from leaf images,” Heliyon, vol. 10, no. 1, p. e23655, Jan. 2024, doi: 10.1016/J.HELIYON.2023.E23655.

W. Shafik, A. Tufail, C. De Silva Liyanage, and R. A. A. H. M. Apong, “Using transfer learning-based plant disease classification and detection for sustainable agriculture,” BMC Plant Biol., vol. 24, no. 1, p. 136, Dec. 2024, doi: 10.1186/S12870-024-04825-Y.

U. Khaira, E. Saputra, and A. Adriadi, “I-NusaPlant Apps?: Indonesian Medical Plants Identification Using Convolutional Neural Network With Pre-trained Model MobileNetV2,” J. Ilmu Komput. dan Agri-Informatika, vol. 11, no. 2, pp. 185–194, 2024, doi: 10.29244/jika.11.2.185-194.

I. Sahputra, A. F. Ulfa, B. A. Putri, and C. Y. Eviyanti, “Comparative Study of VGG16 and MobileNet Architectures for Rice Leaf Disease Classification Using CNN,” J. INFORMATICS Telecommun. Eng., vol. 9, no. 1, pp. 303–314, Aug. 2025, doi: 10.31289/JITE.V9I1.15458.

B. Kieffer, M. Babaie, S. Kalra, and H. R. Tizhoosh, “Convolutional Neural Networks for Histopathology Image Classification: Training vs. Using Pre-Trained Networks,” Proc. 7th Int. Conf. Image Process. Theory, Tools Appl. IPTA 2017, vol. 2018-January, pp. 1–6, Oct. 2017, doi: 10.1109/IPTA.2017.8310149.

S. Auliani, D. I. Indra, and F. U. Fitriyani, “Herbal Leaf Classification Using Convolutional Neural Network (CNN) Method With VGG16 Architecture,” IT J. Res. Dev., vol. 10, no. 2, pp. 57–65, Nov. 2025, doi: 10.25299/ITJRD.2025.24574.

Y. Xu, D. Li, C. Li, Z. Yuan, and Z. Dai, “LiSA-MobileNetV2: an extremely lightweight deep learning model with Swish activation and attention mechanism for accurate rice disease classification,” Front. Plant Sci., vol. 16, p. 1619365, Aug. 2025, doi: 10.3389/FPLS.2025.1619365/BIBTEX.

A. K. Mulugeta, D. P. Sharma, and A. H. Mesfin, “Deep learning for medicinal plant species classification and recognition: a systematic review,” Front. Plant Sci., vol. 14, p. 1286088, 2024, doi: 10.3389/FPLS.2023.1286088.

B. W. Sari, D. Prabowo, Y. Pristyanto, and A. Aminuddin, “Transfer Learning-Based Convolutional Neural Network for Accurate Detection of Rice Leaf Disease in Precision Agriculture,” J. Inf. Syst. Eng. Bus. Intell., vol. 11, no. 3, pp. 420–432, 2025, doi: 10.20473/jisebi.11.3.420-432.

S. M. Hassan, A. K. Maji, M. Jasi?ski, Z. Leonowicz, and E. Jasi?ska, “Identification of Plant-Leaf Diseases Using CNN and Transfer-Learning Approach,” Electron. 2021, Vol. 10, Page 1388, vol. 10, no. 12, p. 1388, Jun. 2021, doi: 10.3390/ELECTRONICS10121388.

J. Yao, S. N. Tran, S. Sawyer, and S. Garg, “Machine learning for leaf disease classification: data, techniques and applications,” Artif. Intell. Rev., vol. 56, no. 3, pp. 3571–3616, Dec. 2023, doi: 10.1007/S10462-023-10610-4/TABLES/2.

J. Ahmed et al., “Smartphone image dataset for turmeric plant leaf disease from Bangladesh spice fields,” Data Br., vol. 63, Dec. 2025, doi: 10.1016/J.DIB.2025.112184.

A. S. Paymode and V. B. Malode, “Transfer learning for Multi-Crop Leaf Disease Image Classification using Convolutional Neural Network VGG,” Artif. Intell. Agric., vol. 6, pp. 23–33, Jan. 2022, doi: 10.1016/J.AIIA.2021.12.002.

R. A. Kumala, C. A. Sari, and E. H. Rachmawanto, “A Comparison of MobileNetV2 and VGG16 Architectures with Transfer learning for Multi-Class Image-Based Waste Classification,” J. Appl. Informatics Comput., vol. 9, no. 4, pp. 1610–1624, Aug. 2025, doi: 10.30871/JAIC.V9I4.9958.

Aryawijaya and Kusnawi, “Chili Leaf Disease Classification Using Transfer learning with VGG16 and MobileNetV2 Combined with Random Search Hyperparameter Tuning,” SITEKNIK Sist. Informasi, Tek. dan Teknol. Terap., vol. 2, no. 4, pp. 324–332, Oct. 2025, doi: 10.5281/ZENODO.17383224.

M. Tariq et al., “Corn leaf disease: insightful diagnosis using VGG16 empowered by explainable AI,” Front. Plant Sci., vol. 15, p. 1402835, Jun. 2024, doi: 10.3389/FPLS.2024.1402835/BIBTEX.

L. Coelho, J. Nalepa, S. De Marchi, G. Batchuluun, S. Hyun Nam, and K. Ryoung Park, “Deep Learning-Based Plant-Image Classification Using a Small Training Dataset,” Math. 2022, Vol. 10, Page 3091, vol. 10, no. 17, p. 3091, Aug. 2022, doi: 10.3390/MATH10173091.

V. Ayumi et al., “Transfer learning for Medicinal Plant Leaves Recognition: A Comparison with and without a Fine-Tuning Strategy,” IJACSA) Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 9, p. 2022, Accessed: Dec. 17, 2025. [Online]. Available: www.ijacsa.thesai.org

T. Sanida, A. Sideris, M. V. Sanida, and M. Dasygenis, “Tomato leaf disease identification via two–stage transfer learning approach,” Smart Agric. Technol., vol. 5, p. 100275, Oct. 2023, doi: 10.1016/J.ATECH.2023.100275.

D. Sugiarto, J. Siswantoro, M. F. Naufal, and B. Idrus, “Mobile Application for Medicinal Plants Recognition from Leaf Image Using Convolutional Neural Network,” Indones. J. Inf. Syst., vol. 5, no. 2, pp. 43–56, Feb. 2023, doi: 10.24002/IJIS.V5I2.6633.

S. Orouji, M. C. Liu, T. Korem, and M. A. K. Peters, “Domain adaptation in small-scale and heterogeneous biological datasets”.