VGG-16 Transfer Learning for Accurate Classification of Three Local Durian Varieties Using Leaf Morphology Images

Ahmad Haikal  Nuqqy Zahhar; I Gede Susrama  Mas Diyasa; Made Hanindya  Prami Swari

doi:10.52436/1.jutif.2026.7.3.5506

Authors

Ahmad Haikal Nuqqy Zahhar Faculty of Computer Science, University of Pembangunan Nasional Veteran, East Java, Indonesia
I Gede Susrama Mas Diyasa Faculty of Computer Science, University of Pembangunan Nasional Veteran, East Java, Indonesia
Made Hanindya Prami Swari Faculty of Computer Science, University of Pembangunan Nasional Veteran, East Java, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.3.5506

Keywords:

Deep Learning, Durian Variety Classification, Leaf Morphology Recognition, Precision Agriculture Technology, Transfer Learning VGG-16

Abstract

Durian (Durio zibethinus Murr), recognized as the "king of fruits" in Southeast Asia, represents a significant genetic asset for Indonesian agriculture with high economic value. East Java leads national production, contributing 580.5 thousand tons (29.59%) of the total 19.6 million tons in 2024. However, local durian quality faces persistent challenges due to minimal maintenance practices and farmers' limited expertise in variety identification. Manual taxonomic identification based on leaf morphology requires specialized knowledge, is time-consuming, and prone to subjective errors, particularly for three popular Nganjuk varieties—local, montong, and lai—which exhibit similar leaf characteristics. Previous studies have addressed durian classification using fruit images or disease detection on leaves, but a research gap exists for variety classification specifically using leaf images with deep learning approaches. This study implements VGG-16 transfer learning architecture with ImageNet pre-trained weights to classify three durian varieties based on leaf morphology images. A dataset of 600 high-resolution images (2048×2048 pixels, 200 per class) was collected from Nganjuk orchards following standardized protocols and validated by three independent experts (two experienced farmers and one plant taxonomist), achieving substantial inter-annotator agreement (Fleiss' kappa = 0.87). Preprocessing included resizing to 224×224 pixels with bilinear interpolation, normalization to [0,1], and standardization using ImageNet statistics. Data augmentation through random rotation (±30°), horizontal flipping (48.8% probability), contrast adjustment (±50.1%), and width/height shifting (±12%) expanded the dataset fourfold to 2,400 images. Using a 90:10 train-test split (2,160:240), the VGG-16 model trained with Adam optimizer (learning rate 0.001, dropout 0.5, dense layer 256 units) achieved 97.08% accuracy after 4 epochs in 1.11 minutes. Performance metrics demonstrated high precision (0.93-1.00), recall (0.92-1.00), and F1-scores (0.95-0.99) across all classes. This research advances precision agriculture informatics by providing an automated, reliable tool for durian variety identification, supporting farmers in optimal cultivation decisions, quality control, and economic value enhancement while contributing to sustainable agricultural development and the Center for Plant Variety Protection and Agricultural Licensing (PVTPP) registration systems in Indonesia.

Downloads

Download data is not yet available.

References

P. Chatthaicharoen, S. Duangburong, and B. Phruksaphanrat, “Classification of Durian Foliar Diseases by Xception and Mask R-CNN Models,” Engineering, Technology & Applied Science Research, vol. 15, no. 5, pp. 27653–27659, Oct. 2025, doi: 10.48084/etasr.12461.

Jasminarni et al., “Identifikasi Karakter Morfologi Tanaman Durian (Durio zibethinus Murr ) Lokal Kerinci,” Jurnal Media Pertanian, vol. 8, no. 1, pp. 45–49, 2023, doi: 10.33087/jagro.v8i1.181.

Badan Pusat Statistik, “Produksi Tanaman Buah-buahan dan Sayuran Tahunan Menurut Provinsi dan Jenis Tanaman, 2024.”

F. Annisa, P. Priyanti, and D. Dasumiati, “Morfologi Daun Durian (Durio zibethinus L.) dan Keanekaragaman Genetiknya Berdasarkan Marka ISSR,” Al-Kauniyah: Jurnal Biologi, vol. 16, no. 1, pp. 212–221, Apr. 2023, doi: 10.15408/kauniyah.v16i1.23975.

K. Shamin-Shazwan, R. Shahari, C. N. Aini, C. Amri, M. Z. Ghazali, and R. Go, “Trichome Morphology of Durio Zibethinus L.,” Malaysian Journal of Microscopy, vol. 16, no. 1, pp. 196–204, 2020.

N. A. H. A. Halim, S. Suhaila, N. S. A. M. Taujuddin, and R. Hazli, “Durian Tree Type Identification Based on Durian Leaves,” Evolution in Electrical and Electronic Engineering, vol. 4, no. 1, pp. 551–558, 2023, doi: 10.30880/eeee.2023.04.01.066.

H. Yanik, E. Uysal, and H. Erol, “Automated Detection and Classification of Durian Leaf Diseases Using Advanced Deep Learning Architectures,” in 2025 9th International Artificial Intelligence and Data Processing Symposium (IDAP), 2025, pp. 1–7. doi: 10.1109/IDAP68205.2025.11222392.

D. Diana et al., “Convolutional Neural Network Based Deep Learning Model for Accurate Classification of Durian Types,” Journal of Applied Data Sciences, vol. 6, no. 1, pp. 101–114, Jan. 2025, doi: 10.47738/jads.v6i1.480.

N. Veerawong, A. Suthichayapipat, and P. Yasri, “Automated Classification of Monthong, Chanee, and Kan Yao Durians Using VGG16 Convolutional Neural Network,” 2025. [Online]. Available: https://rsucon.rsu.ac.th/proceedings

V. N. Mee, L. T. Ming, and L. Y. Mei, “Leveraging Transfer Learning for Durian Variety Classification,” Journal of Artificial Intelligence and Technology, vol. 5, pp. 135–142, May 2025, doi: 10.37965/jait.2025.0672.

Y. Thipsrirach, M. Kosacka-Olejnik, and K. Poonikom, “Classification of durian maturity using a convolutional neural network,” Engineering and Applied Science Research, vol. 50, no. 3, pp. 233–243, Apr. 2023, doi: 10.14456/easr.2023.26.

D. M. Asriny and R. Jayadi, “Transfer Learning VGG16 for Classification Orange Fruit Images,” Journal of System and Management Sciences, vol. 13, no. 1, pp. 206–217, 2023, doi: 10.33168/JSMS.2023.0112.

J. Thomkaew and S. Intakosum, “Improvement Classification Approach in Tomato Leaf Disease using Modified Visual Geometry Group (VGG)-InceptionV3,” 2022. [Online]. Available: www.ijacsa.thesai.org

M. A. Rajab, F. A. Abdullatif, and T. Sutikno, “Classification of grapevine leaves images using VGG-16 and VGG-19 deep learning nets,” Telkomnika (Telecommunication Computing Electronics and Control), vol. 22, no. 2, pp. 445–453, Apr. 2024, doi: 10.12928/TELKOMNIKA.v22i2.25840.

G. Kaur, N. Sharma, S. Malhotra, S. Devliyal, and B. V. Kumar, “Citrus Leaf Disease Classification Using VGG16 Convolutional Neural Network Architecture,” in 2024 IEEE 9th International Conference for Convergence in Technology, I2CT 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/I2CT61223.2024.10543761.

N. A. Octarina, R. Andrian, and R. Safei, “Classification of crown density and foliage transparency scale for broadleaf tree using VGG-16,” Journal of Soft Computing Exploration, vol. 4, no. 4, pp. 222–232, Dec. 2023, doi: 10.52465/joscex.v4i4.251.

T. D. Salka, M. B. Hanafi, S. M. S. A. A. Rahman, D. B. M. Zulperi, and Z. Omar, “Plant leaf disease detection and classification using convolution neural networks model: a review,” Artif Intell Rev, vol. 58, no. 10, Oct. 2025, doi: 10.1007/s10462-025-11234-6.

N. Ullah et al., “An effective approach for plant leaf diseases classification based on a novel DeepPlantNet deep learning model,” Front Plant Sci, vol. 14, 2023, doi: 10.3389/fpls.2023.1212747.

S. Aboelenin, F. A. Elbasheer, M. M. Eltoukhy, W. M. El-Hady, and K. M. Hosny, “A hybrid Framework for plant leaf disease detection and classification using convolutional neural networks and vision transformer,” Complex and Intelligent Systems, vol. 11, no. 2, Feb. 2025, doi: 10.1007/s40747-024-01764-x.

C. Pal, S. Karmakar, I. Mukherjee, and P. P. Chakrabarti, “A lightweight and explainable CNN model for empowering plant disease diagnosis,” Sci Rep, vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-94083-1.

R. Safe’i, R. Andrian, D. A. Sriatna, and F. R. Tarigan, “Classification of Density and Transparency of Needle Leaves Types Using AlexNet and VGG16 Architecture,” Ingenierie des Systemes d’Information, vol. 29, no. 3, pp. 929–939, Jun. 2024, doi: 10.18280/isi.290313.

J. Pardede, B. Sitohang, S. Akbar, and M. L. Khodra, “Implementation of Transfer Learning Using VGG16 on Fruit Ripeness Detection,” International Journal of Intelligent Systems and Applications, vol. 13, no. 2, pp. 52–61, Apr. 2021, doi: 10.5815/ijisa.2021.02.04.

M. M. Khalid and O. Karan, “Deep Learning for Plant Disease Detection,” International Journal of Mathematics, Statistics, and Computer Science, vol. 2, pp. 75–84, Nov. 2023, doi: 10.59543/ijmscs.v2i.8343.

S. Shilaskar et al., “Classification and Segmentation of Breast Tumor Ultrasound Images using VGG-16 and UNet,” Biomedical and Pharmacology Journal, vol. 18, no. 1, pp. 569–580, Mar. 2025, doi: 10.13005/bpj/3109.

M. I. Hossen, M. Awrangjeb, S. Pan, and A. Al Mamun, “Transfer learning in agriculture: a review,” Artif Intell Rev, vol. 58, no. 4, Apr. 2025, doi: 10.1007/s10462-024-11081-x.

R. Wijanarko, D. E. Ratnawati, and P. P. Adikara, “Analisis Sentimen Dampak Perkembangan Artificial Intelligence (AI) pada Media Sosial X/Twitter Menggunakan Metode Random Forest,” 2017. [Online]. Available: http://j-ptiik.ub.ac.id

M. Mathur, “‘A Comparative Analysis of Deep Learning Algorithms for Fruit Disease Classification,’” Journal of Electrical Systems, vol. 20, pp. 2621–2633, Dec. 2024, doi: 10.52783/jes.4098.

N. Arifin and C. N. Insani, “Comparative Analysis of CNN, SVM, Decision Tree, Random Forest, and KNN for Maize Leaf Disease Detection Using Color and Texture Feature Extraction,” Jurnal Teknik Informatika (Jutif), vol. 6, no. 5, pp. 3572–3586, Oct. 2025, doi: 10.52436/1.jutif.2025.6.5.5128.