Waste Image Classification Using EfficientNet B4 with MD5 and pHash Data Duplication Analysis on Two Datasets
DOI:
https://doi.org/10.30871/jaic.v10i4.13510Keywords:
Waste, Image classification, EfficientNet-B4, MD5, pHashAbstract
Waste sorting automation through deep learning is an important approach to support sustainable waste management systems. However, many studies still overlook dataset quality issues, especially exact and near duplicate images that can cause information leakage and overly optimistic evaluation metrics. This study proposes a waste image classification pipeline that integrates an explicit data quality analysis stage using MD5 hashing for exact duplicate detection and perceptual hashing (pHash) for near duplicate detection, followed by fine tuned EfficientNet B4 as the classification backbone. Experiments are conducted on two public datasets with distinct characteristics: Garbage Classification V2 (6 classes, 9,421 images) and RealWaste (9 classes, 4,749 images). With a Hamming distance threshold τ≤2, the pHash cleansing identifies zero duplicates in Dataset 1 and only three near duplicates (0.06%) out of 1,404,077 compared pairs in Dataset 2, confirming no evidence of image-duplication-based information leakage in either dataset. EfficientNet B4 achieves 97.77% test accuracy with a macro F1 Score of 0.9768 on Dataset 1 and 93.26% accuracy with a macro F1 Score of 0.9379 on Dataset 2, demonstrating consistent performance across these two datasets with different numbers of classes, data volumes, and visual heterogeneity. These findings should be interpreted as evidence of robustness within the scope of the two evaluated datasets, rather than as a claim of generalization to unseen, external, or cross-domain waste image datasets.
Downloads
References
[1] Z. Zhang et al., “Municipal solid waste management challenges in developing regions: A comprehensive review and future perspectives for Asia and Africa,” Science of The Total Environment, vol. 930, p. 172794, Jun. 2024, doi: 10.1016/j.scitotenv.2024.172794.
[2] Md. M. Islam, S. M. M. Hasan, Md. R. Hossain, Md. P. Uddin, and Md. Al Mamun, “Towards sustainable solutions: Effective waste classification framework via enhanced deep convolutional neural networks,” PLoS One, vol. 20, no. 6, p. e0324294, Jun. 2025, doi: 10.1371/journal.pone.0324294.
[3] W. Lu and J. Chen, “Computer vision for solid waste sorting: A critical review of academic research,” Waste Management, vol. 142, pp. 29–43, Apr. 2022, doi: 10.1016/j.wasman.2022.02.009.
[4] R. A. Kumala, C. A. Sari, and H. Rachmawanto, “A Comparison of MobileNetV2 and VGG16 Architectures with Transfer Learning for Multi-Class Image-Based Waste Classification,” Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 4, pp. 1610–1624, 2025, doi: https://doi.org/10.30871/jaic.v9i4.9958.
[5] E. Oktayaessofa, C. A. Sari, E. H. Rachmawanto, and N. M. Yaacob, “Classification Of Organic And Non-Organic Waste With Cnn-Mobilenet-V2,” Jurnal Teknik Informatika (Jutif), vol. 5, no. 4, pp. 1173–1180, Jul. 2024, doi: 10.52436/1.jutif.2024.5.4.2165.
[6] M. Zulhusni, C. A. Sari, and E. H. Rachmawanto, “Implementation of DenseNet121 Architecture for Waste Type Classification,” Advance Sustainable Science, Engineering and Technology, vol. 6, no. 3, May 2024, doi: 10.26877/asset.v6i3.673.
[7] U. Kumar Lilhore, S. Simaiya, S. Dalal, M. Radulescu, and D. Balsalobre-Lorente, “Intelligent waste sorting for sustainable environment: A hybrid deep learning and transfer learning model,” Gondwana Research, vol. 146, pp. 252–266, Oct. 2025, doi: 10.1016/j.gr.2024.07.014.
[8] J. Padhi, L. Korada, A. Dash, P. K. Sethy, S. K. Behera, and A. Nanthaamornphong, “Paddy Leaf Disease Classification Using EfficientNet B4 With Compound Scaling and Swish Activation: A Deep Learning Approach,” IEEE Access, vol. 12, pp. 126426–126437, 2024, doi: 10.1109/ACCESS.2024.3451557.
[9] A. Angdresey, I. Y. Kairupan, and A. G. Mongkareng, “Leveraging Convolutional Neural Networks for Multiclass Waste Classification,” Journal of Applied Informatics and Computing, vol. 9, no. 4, pp. 1137–1145, Aug. 2025, doi: 10.30871/jaic.v9i4.9373.
[10] J. J. C. Simbolon, Robet, and Hendri, “Household Waste Image Classification Using Deep Learning Model,” Journal of Artificial Intelligence and Engineering Applications (JAIEA), vol. 5, no. 1, pp. 1681–1690, Oct. 2025, doi: 10.59934/jaiea.v5i1.1690.
[11] G. Ahmad et al., “Intelligent waste sorting for urban sustainability using deep learning,” Sci. Rep., vol. 15, no. 1, p. 27078, Jul. 2025, doi: 10.1038/s41598-025-08461-w.
[12] T. Kurniawan, K. Khadijah, and R. Kusumaningrum, “An Efficient Model for Waste Image Classification Using EfficientNet-B0,” Jurnal Teknik Informatika (Jutif), vol. 6, no. 3, pp. 1147–1158, Jun. 2025, doi: 10.52436/1.jutif.2025.6.3.4417.
[13] M. A. Mohammed et al., “Automated waste-sorting and recycling classification using artificial neural network and features fusion: a digital-enabled circular economy vision for smart cities,” Multimed. Tools Appl., vol. 82, no. 25, pp. 39617–39632, Oct. 2023, doi: 10.1007/s11042-021-11537-0.
[14] I. K. M. C. Qinantha, I. G. A. Indrawan, I. P. S. U. Putra, I. G. A. A. M. Aristamy, and A. G. Willdahlia, “Classification Of Organic And Inorganic Waste Using Resnet50,” Indonesian Journal of Data and Science, vol. 6, no. 2, pp. 232–240, Jul. 2025, doi: 10.56705/ijodas.v6i2.267.
[15] M. Haqqi, L. Rochmah, A. D. Safitri, R. A. Pratama, and Tarwoto, “Implementation Of Machine Learning To Identify Types Of Waste Using CNN Algorithm,” JURNAL FASILKOM, vol. 14, no. 3, pp. 761–765, Dec. 2024, doi: 10.37859/jf.v14i3.8116.
[16] L. Du, A. T. S. Ho, and R. Cong, “Perceptual hashing for image authentication: A survey,” Signal Process. Image Commun., vol. 81, p. 115713, Feb. 2020, doi: 10.1016/j.image.2019.115713.
[17] Y. Jakhar and M. D. Borah, “Effective near-duplicate image detection using perceptual hashing and deep learning,” Inf. Process. Manag., vol. 62, no. 4, p. 104086, Jul. 2025, doi: 10.1016/j.ipm.2025.104086.
[18] A. Joshi, A. V Shet, A. S. Thambi, and S. R, “Quality Improvement of Image Datasets using Hashing Techniques,” in 2023 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), IEEE, Jan. 2023, pp. 18–23. doi: 10.1109/IITCEE57236.2023.10091044.
[19] A. Aghabagherloo, A. Abadi, S. Sarkar, V. A. Dasu, and B. Preneel, “Impact of Data Duplication on Deep Neural Network-Based Image Classifiers: Robust vs. Standard Models,” in 2025 IEEE Security and Privacy Workshops (SPW), IEEE, May 2025, pp. 177–183. doi: 10.1109/SPW67851.2025.00023.
[20] P. Ch, R. Swathi, K. Suneetha, I. Suneetha, B. V. Suresh Reddy, and S. K. Depuru, “Image Capturing and Deleting Duplicate Images through Feature Extraction using Hashing Techniques,” International Journal of Engineering Trends and Technology, vol. 72, no. 1, pp. 64–70, Jan. 2024, doi: 10.14445/22315381/IJETT-V72I1P107.
[21] Q. Zhang, Q. Yang, X. Zhang, Q. Bao, J. Su, and X. Liu, “Waste image classification based on transfer learning and convolutional neural network,” Waste Management, vol. 135, pp. 150–157, Nov. 2021, doi: 10.1016/j.wasman.2021.08.038.
[22] M. Malik et al., “Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models,” Sustainability, vol. 14, no. 12, p. 7222, Jun. 2022, doi: 10.3390/su14127222.
[23] L. Nanni, M. Paci, S. Brahnam, and A. Lumini, “Comparison of Different Image Data Augmentation Approaches,” J. Imaging, vol. 7, no. 12, p. 254, Nov. 2021, doi: 10.3390/jimaging7120254.
[24] W. Zeng, “Image data augmentation techniques based on deep learning: A survey,” Mathematical Biosciences and Engineering, vol. 21, no. 6, pp. 6190–6224, 2024, doi: 10.3934/mbe.2024272.
[25] S. Agustiani, A. Junaidi, R. Aryanti, A. Abdul, and B. Kamil, “Waste Classification using EfficientNetB3-Based Deep Learning for Supporting Sustainable Waste Management,” Bulletin of Informatics and Data Science, vol. 4, no. 1, pp. 62–70, 2025, doi: 10.61944/bids.v4i1.108.
[26] H. Singh and D. Rai, “24. Improved Efficientnet Transfer Learning Framework with Data Augmentation For Multiclass Skin Cancer Classification,” Int. J. Environ. Sci., vol. 11, no. 21, 2025, doi: 10.64252/bjajys38.
[27] Y. Puspitasari, J. S. Jong, and A. G. Prabawati, “23. Comparison Of Convolutional Neural Network Architectures Efficientnet-B4 And Mobilenetv2 In Cataract Disease Detection,” JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 11, no. 4, pp. 1020–1027, May 2026, doi: 10.33480/jitk.v11i4.7502.
[28] Z. Yao, A. Gholami, S. Shen, M. Mustafa, K. Keutzer, and M. Mahoney, “ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 12, pp. 10665–10673, May 2021, doi: 10.1609/aaai.v35i12.17275.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Abdul Qohhar, Christy Atika Sari, Hidayah Rahmalan
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:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement 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 acknowledgement 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 (See The Effect of Open Access).
