Comparative Study of Background Removal for Mango Fruit Disease Classification Using ResNet50-SVM
DOI:
https://doi.org/10.64366/ijids.v3i2.549Keywords:
Background Removal; Mango Fruit Disease; ResNet50; Support Vector Machine; Transfer LearningAbstract
Background removal is commonly applied in image classification to suppress irrelevant visual information and emphasize the target object. However, its contribution to disease classification may depend on whether background elimination also modifies contextual, boundary, and texture information used by deep feature extractors. This study evaluates the effect of background removal on five-class mango fruit disease classification using a hybrid ResNet50–Support Vector Machine (SVM) framework. A paired experimental design was constructed from 834 matched MangoFruitDDS image pairs representing Alternaria, Anthracnose, Black Mould Rot, Healthy, and Stem-End Rot. The paired data were stratified into 667 training and 167 test samples for each image condition. ImageNet-pretrained ResNet50 was used as a frozen feature extractor, producing 2,048-dimensional feature vectors that were standardized and classified using an optimized SVM. Background-removed images achieved a higher cross-validation macro F1-score (0.7559) than original images (0.7340). However, evaluation on the identical test set showed higher performance for original images, with 76.05% accuracy, 0.7687 macro F1-score, and 0.9541 macro ROC-AUC, compared with 74.25%, 0.7445, and 0.9425, respectively, after background removal. The effect was class-dependent: Healthy improved after background removal, whereas several disease classes declined, suggesting that removing the background may alter contextual, boundary, or texture-related information contributing to ResNet50 feature representations. Exact McNemar testing showed no statistically significant difference between the paired predictions (p = 0.783846). These findings indicate that developers should not assume hard background removal universally improves plant disease classification; class-specific validation and feature-preserving or attention-based alternatives should be considered.
Downloads
References
G. T. Yehulu et al., “Mango fruit disease detection and classification using MobileNetV3_large model,” Sci. African, vol. 30, no. October, p. e03061, 2025, doi: 10.1016/j.sciaf.2025.e03061.
O. Prabhu, M. T, and S. Shetty, “An investigation on advances in transfer learning and explainable AI for mango leaf disease detection,” Smart Agric. Technol., vol. 12, no. May, p. 101348, 2025, doi: 10.1016/j.atech.2025.101348.
K. Mookkandi, M. K. Nath, and K. Balakrishnan, “Robust method for classification of agricultural crops diseases using LGXP descriptor,” Results Eng., vol. 29, no. November 2025, p. 108826, 2026, doi: 10.1016/j.rineng.2025.108826.
R. A. Rizvee et al., “LeafNet: A proficient convolutional neural network for detecting seven prominent mango leaf diseases,” J. Agric. Food Res., vol. 14, no. August, p. 100787, 2023, doi: 10.1016/j.jafr.2023.100787.
R. Amalia, A. F. Zaidan, S. Ramadhan, F. Septian, A. M. Aqsha, and P. Rosyani, “Classification of Autoimmune Diseases Using the K-Nearest Neighbors Algorithm,” Formosa J. Sci. Technol., vol. 4, no. 1, pp. 337–348, Jan. 2025, doi: 10.55927/fjst.v4i1.13443.
M. Q. R. Pembury Smith and G. D. Ruxton, “Effective use of the McNemar test,” Behav. Ecol. Sociobiol., vol. 74, no. 11, 2020, doi: 10.1007/s00265-020-02916-y.
U. Sanath Rao et al., “Deep Learning Precision Farming: Grapes and Mango Leaf Disease Detection by Transfer Learning,” Glob. Transitions Proc., vol. 2, no. 2, pp. 535–544, 2021, doi: 10.1016/j.gltp.2021.08.002.
M. T. Rahman, S. D. Dipto, I. J. June, A. Momin, and M. R. Al Mamun, “Machine Learning-based Disease Classification in Tomato (Solanum lycopersicum) Plants,” J. Keteknikan Pertan. Trop. dan Biosist., vol. 12, no. 3, pp. 151–160, Dec. 2024, doi: 10.21776/ub.jkptb.2024.012.03.01.
A. Shahcheraghian, A. Ilinca, and N. Sommerfeldt, “K-means and agglomerative clustering for source-load mapping in distributed district heating planning,” Energy Convers. Manag. X, vol. 25, no. October 2024, p. 100860, 2025, doi: 10.1016/j.ecmx.2024.100860.
K. N. Rahman, S. C. Banik, R. Islam, and A. Al Fahim, “A real time monitoring system for accurate plant leaves disease detection using deep learning,” Crop Des., vol. 4, no. 1, Feb. 2025, doi: 10.1016/j.cropd.2024.100092.
G. Psaltakis, K. Rogdakis, M. Loizos, and E. Kymakis, “One-vs-One, One-vs-Rest, and a novel Outcome-Driven One-vs-One binary classifiers enabled by optoelectronic memristors towards overcoming hardware limitations in multiclass classification,” Discov. Mater. , vol. 4, no. 1, 2024, doi: 10.1007/s43939-024-00077-7.
M. M. Islam et al., “A two-stage model for enhanced mango leaf disease detection using an innovative handcrafted spatial feature extraction method and knowledge distillation process,” Ecol. Inform., vol. 91, no. July, p. 103365, 2025, doi: 10.1016/j.ecoinf.2025.103365.
F. Mahrus Fathoni, “Klasifikasi Penyakit Daun Tomat Menggunakan Algoritma K-NN Berdasarkan Ekstraksi Fitur GLCM dan LBP,” J. Tek. Inform. dan Teknol. Inf., vol. 4, no. 1, pp. 39–50, Jan. 2024, doi: 10.55606/jutiti.v4i1.3417.
T. Hu, M. Khishe, M. Mohammadi, G. R. Parvizi, S. H. Taher Karim, and T. A. Rashid, “Real?time COVID-19 diagnosis from X-Ray images using deep CNN and extreme learning machines stabilized by chimp optimization algorithm,” Biomed. Signal Process. Control, vol. 68, Jul. 2021, doi: 10.1016/j.bspc.2021.102764.
A. Venkataramana, K. Suresh Kumar, N. Suganthi, and R. Rajeswari, “Prediction of Brinjal Plant Disease Using Support Vector Machine and Convolutional Neural Network Algorithm Based on Deep Learning,” J. Mob. Multimed., vol. 18, no. 3, pp. 771–788, 2022, doi: 10.13052/jmm1550-4646.18315.
M. Damar, A. Putra, and S. Rakasiwi, “Penerapan Model SVM dengan Ekstraksi Fitur ResNet50 untuk Identifikasi Sel Darah Terinfeksi Malaria,” vol. 7, no. 3, pp. 1866–1874, 2026, doi: 10.47065/bits.v7i3.8750.
C. Wang, “ResNet50 Feature Extraction with SVM and kNN for Three-Class Dog Heart Size Classification”.
A. O. Anim-Ayeko, C. Schillaci, and A. Lipani, “Automatic blight disease detection in potato (Solanum tuberosum L.) and tomato (Solanum lycopersicum, L. 1753) plants using deep learning,” Smart Agric. Technol., vol. 4, Aug. 2023, doi: 10.1016/j.atech.2023.100178.
Y. A. Bezabh, A. M. Ayalew, B. M. Abuhayi, T. N. Demlie, E. A. Awoke, and T. E. Mengistu, “Classification of mango disease using ensemble convolutional neural network,” Smart Agric. Technol., vol. 8, no. April, p. 100476, 2024, doi: 10.1016/j.atech.2024.100476.
M. A. Hossain, S. Sakib, H. M. Abdullah, and S. E. Arman, “Deep learning for mango leaf disease identification: A vision transformer perspective,” Heliyon, vol. 10, no. 17, p. e36361, 2024, doi: 10.1016/j.heliyon.2024.e36361.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Comparative Study of Background Removal for Mango Fruit Disease Classification Using ResNet50-SVM
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2026 Perani Rosyani, Ines Heidiani Ikasari, Saprudin, Shita Nurul Ayasha, Alya Salsabila Az Zahra
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International 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 (Refer to The Effect of Open Access).
