Penerapan Convolutional Neural Network (CNN) pada Klasifikasi Tanaman Apel Menggunakan Resnet-50
-
M. Fauzan Djafaar
*
Program Studi Teknik Informatika, Fakultas Teknik Universitas Khairun, Ternate,
Indonesia
- Mohamad Jamil Program Studi Teknik Informatika, Fakultas Teknik Universitas Khairun, Ternate, Indonesia
Abstract
Apple plant classification based on leaf images still faces challenges in the form of variations in shape, texture, lighting, and visual similarity with other plants, which can potentially reduce identification accuracy. This problem impacts agricultural monitoring and decision-making processes that require high accuracy. This research aims to apply the Convolutional Neural Network (CNN) method, a deep learning approach designed for automatically extracting visual features, to apple plant classification using a fifty-layer Residual Network (ResNet-50) architecture. ResNet-50 uses a residual mechanism to overcome performance degradation in very deep networks. The results showed that the CNN model based on the ResNet-50 architecture was able to classify healthy and rotten apple leaf images with the highest accuracy of 82.40% using the 80:20 dataset split scenario. Evaluation using a confusion matrix and classification report produced a precision value of 0.86 for the rotten class and 0.79 for the healthy class, while the recal values were 0.77 and 0.88, respectivelty. These rindings indicate that ResNet-50 has a good capability in recognizing visual characteristics of apple leaves and can be effectively utilized as an image-based plant classification solution.
References
Z. Cao and S. Sun, “A Review of Computer Vision and Deep Learning Applications in Crop Growth Management,” 2025, doi: 10.3390/app15158438.
P. K. Illa, S. Ravuri, R. Vuppala, and B. M. Reddy, “Deep Learning Methods for Plant Disease Identification using Leaf Images : A Survey,” 2023 Int. Conf. Sustain. Comput. Smart Syst., no. Icscss, pp. 307–316, 2023, doi: 10.1109/ICSCSS57650.2023.10169260.
Y. Liu, H. Pu, and D. Sun, “Trends in Food Science & Technology Efficient extraction of deep image features using convolutional neural network ( CNN ) for applications in detecting and analysing complex food matrices,” Trends Food Sci. Technol., vol. 113, no. April, pp. 193–204, 2021, doi: 10.1016/j.tifs.2021.04.042.
M. Nikesh, D. Rohini, S. Shaankari, M. Bharathi, and T. A. S. Srinivas, “Verdant Vision : CNNs Revolutionizing Plant Leaf Disease Identification,” no. 2, pp. 1–6, 2024, doi: 10.48001/JoCSVL.2024.121-6.
C. A. Technology and I. Technologies, “Apple Disease Recognition Based on Comprehensive Application of Residual Neural Network,” vol. 0, 2023, doi: 10.3233/FAIA230765.
L. M. K. Sheikh, A. Shaikh, A. Sandupatla, R. Pudale, A. Bakare, and P. M. Chavan, “Classification of Simple CNN Model and ResNet50,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 12, no. 4, pp. 4606–4610, 2024, doi: 10.22214/ijraset.2024.60677.
S. A. Wicaqsana, A. Luthfiarta, A. Putri, D. Mareta, and M. S. Fitri, “Evaluation of the Accuracy and Efficiency of Deep CNN Architecture in Feature Extraction for Guava Disease Classification,” vol. 9, no. 6, pp. 3798–3809, 2025, doi: 10.30871/jaic.v9i6.11655.
T. D. Salka, M. Hanafi, S. M. Syed, and A. Abdul, “State-of-the-Art CNN Models for Plant Disease Classification : A Comparative Study,” vol. 33, no. 6, pp. 2541–2563, 2025, doi: 10.47836/pjst.33.6.07.
I. S. In and I. S. In, “Plant Disease Detection using ResNet,” 2023, doi: 10.1109/ICICT57646.2023.10133938.
M. R. Bhat et al., “Apple diseases : detection and classification using transfer learning,” vol. 15, pp. 27–37, 2023, doi: 10.15586/qas.v15iSP1.1167.
S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using Deep Learning for Image-Based Plant Disease Detection,” Front. Plant Sci., vol. 7, no. September, pp. 1–10, 2016, doi: 10.3389/fpls.2016.01419.
D. Learning, “Plant Disease Detection and Classification by Deep Learning,” Nature, vol. 29, no. 7553, pp. 1–73, 2019, doi: 10.3390.
B. Prashanthi, A. V. Praveen Krishna, and C. Mallikarjuna Rao, “A Comparative Study of Fine-Tuning Deep Learning Models for Leaf Disease Identification and Classification,” Eng. Technol. Appl. Sci. Res., vol. 15, no. 1, pp. 19661–19669, 2025, doi: 10.48084/etasr.9017.
J. G. A. Barbedo, “Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification,” Comput. Electron. Agric., vol. 153, pp. 46–53, 2018, doi: 10.1016/j.compag.2018.08.013.
R. Javed, A. M. Malik, A. F. Mirza, S. Aslam, A. Shabbir, and H. Tauseef, “Early Detection and Classification of Apple Leaf Diseases Using Deep Learning Technique,” vol. 4, no. 3, pp. 86–100, 2024, doi: 10.62019.
M. R. Mulia, A. B. Kaswar, D. D. Andayani, A. Sadri, U. N. Makassar, and P. Korespondensi, “KLASIFIKASI KANDUNGAN NUTRISI BUAH PISANG BERDASARKAN FITUR TEKSTUR DAN WARNA LAB MENGGUNAKAN JARINGAN SYARAF TIRUAN BERBASIS PENGOLAHAN
CITRA DIGITAL,” vol. 11, no. 3, pp. 507–518, 2024, doi: 10.25126/jtiik.938332.
P. Studi et al., “Klasifikasi Jenis Daun Tumbuhan Herbal Berdasarkan Lontar Usada Taru Pramana Menggunakan CNN Classification of Herbal Plant Leaf Types Based on Lontar Usada Taru Pramana Using,” vol. 23, no. 1, pp. 271–283, 2024, doi: 10.62411/tc.v23i1.9510.
W. S. Amurrokhman, “PERBANDINGAN RESNET50, MOBILENETV2, DAN MOBILENETV3-LARGE DALAM KLASIFIKASI MOTIF BATIK INDONESIA BERBASIS TRANSFER LEARNING,” vol. 11, no. 1, pp. 1457–1467, 2026, doi: 10.36341/rabit.v11i1.4579.
T. Pascal Munthe and M. Akbar, “Klasifikasi Citra Biji Kopi Temangung Menggunakan Residual Network (ResNet-50),” J. Pustaka Data (Pusat Akses Kaji. Database, Anal. Teknol. dan Arsit. Komputer), vol. 5, no. 1, pp. 94–102, 2025, doi: 10.55382/jurnalpustakadata.v5i1.1028.
L. M. K. Sheikh, A. Shaikh, A. Sandupatla, R. Pudale, A. Bakare, and P. M. Chavan, “Classification of Simple CNN Model and ResNet50,” no. April, 2024, doi: 10.22214/IJRASET.2024.60677.
Y. A. Abdillah and K. Kusrini, “Corn Leaf Disease Classification Optimization Using Resnet50 Architecture Utilizing Bayesian Optimization,” J. Electr. Eng. Comput., vol. 7, no. 1, pp. 8–15, 2025, doi: 10.33650/jeecom.v7i1.9809.
Arimbi Puspitasari, Diana Sava Salsabila, and Dwi Roliawati, “Penerapan ResNet50-CNN untuk Optimalisasi Klasifikasi pada Data Fashion,” Indones. J. Data Sci., vol. 3, no. 1, pp. 1–12, 2025, doi: 10.30989/ijds.v3i1.1533.
E. Ariawan, “Perbandingan Performa Arsitektur Convolutional Neural Network Menggunakan Transfer Learning untuk Model Deteksi Kesehatan Daun,” J. Bus. Audit Inf. Syst., vol. 8, no. 1, pp. 1–12, 2025, doi: 10.30813/jbase.v8i1.8116.
S. Khoria and R. Singh, “Predicting Lung Cancer Using ResNet-50 Deep Residual Learning Model using Relu-Memristor Activation Function,” vol. 29, no. 3, doi: 10.4186/ej.2025.29.3.45.
P. A. Azli, A. Syahrani, and G. Y. Swara, “Segmentasi Citra Daun Tomat untuk Klasifikasi Penyakit Tanaman Menggunakan Support Vector Machine (SVM),” vol. 10, no. 4, pp. 997–1008, 2025, doi: 10.30591/jpit.v10i4.9404.
Copyright (c) 2026 M. Fauzan Djafaar, Mohamad Jamil
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors retain copyright and grant the EXPLORER right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share (copy and redistribute the material in any medium or format) and adapt (remix, transform, and build upon the material) the work for any purpose, even commercially with an acknowledgement of the work's authorship and initial publication in EXPLORER.
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 acknowledgement of its initial publication in EXPLORER.
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 (See The Effect of Open Access).
.png)
