Comparative Analysis of Multispectral Image Classification Based on EfficientNetB0, ResNet152, DenseNet161, DenseNet121, and HSV Segmentation

Authors

  • Melinda Universitas Syiah Kuala
  • Yudha Nurdin Universitas Syiah Kuala
  • Alfatirta Mufti Universitas Syiah Kuala
  • Syifa Anzella Universitas Syiah Kuala
  • Siti Rusdiana Universitas Syiah Kuala
  • Donata D Acula University of Santo Tomas

DOI:

https://doi.org/10.29207/resti.v10i1.6873

Keywords:

CNN, deep learning, HHF, HSV segmentation, multispectral data

Abstract

This study established a classification system based on Convolutional Neural Networks (CNNs) to detect High-High Fluctuation (HHF) patterns in multispectral data derived from pure water (H2O) and a water-sodium hydroxide (NaOH) solution. This study combines HSV color-space-based segmentation to identify areas with the highest signal amplitude, thereby enhancing the feature extraction of the CNN model. Data augmentation techniques, including random flipping, rotation, and color jitter, along with training parameters such as a learning rate of 0.0001 and a batch size of 32, have been shown to effectively improve model generalization and reduce overfitting. Four different CNN architectures were evaluated: ResNet-152, DenseNet-161, DenseNet-121, and EfficientNet-B0. As a result, ResNet152 achieved the highest accuracy of 97.6%, attributed to its network depth and residual connections that effectively address the vanishing gradient problem. DenseNet161 and DenseNet121 also demonstrated competitive performance, achieving accuracies of 96.7% and 96.2%, respectively, which is supported by their dense connectivity that optimizes feature reuse. Conversely, EfficientNetB0, despite showing lower accuracy (90%), provides significant computational efficiency, making it suitable for real-time applications. These results underscore the importance of selecting a CNN architecture that balances accuracy and efficiency for multispectral data classification.

Downloads

Download data is not yet available.

References

O. Gutierrez-Navarro, L. Granados-Castro, A. R. Mejia-Rodriguez, and D. U. Campos-Delgado, “A Multi-Spectral Image Database for In-Vivo Hand Perfusion Evaluation,” IEEE Access, vol. 11, no. July, pp. 87543–87557, 2023, doi: 10.1109/ACCESS.2023.3305256.

B. Rusyn, O. Lutsyk, R. Kosarevych, T. Maksymyuk, and J. Gazda, “Features extraction from multi-spectral remote sensing images based on multi-threshold binarization,” Sci. Rep., 2023, doi: 10.1038/s41598-023-46785-7.

M. Melinda, Y. Yunidar, and N. A. C. Andryani, “Application of Convolutional Neural Network (CNN) Method in Fluctuations Pattern,” Green Intell. Syst. Appl., vol. 3, no. 2, pp. 56–68, 2023, doi: 10.53623/gisa.v3i2.270.

J. J. Senecal, J. W. Sheppard, and J. A. Shaw, “Efficient Convolutional Neural Networks for Multi-Spectral Image Classification,” in Proceedings of the International Joint Conference on Neural Networks, 2019. doi: 10.1109/IJCNN.2019.8851840.

Melinda, A. S. Tamsir, D. Sudiana, D. Gunawan, and M. Iqbal, “Implementation of segmentation scheme based on wavelet transform in multi-spectral fluctuation patterns,” J. Telecommun. Electron. Comput. Eng., vol. 8, no. 12, pp. 47–52, 2016, https://jtec.utem.edu.my/jtec/article/view/1434

D. Giuliani, “Metaheuristic Algorithms Applied to Color Image Segmentation on HSV Space,” J. Imaging, vol. 8, no. 1, 2022, doi: 10.3390/jimaging8010006.

M. Melinda, A. Tanjung, A. S. Tamsir, B. Basari, and D. Gunawan, “Grouped data analysis of H2O and H2O mixed with NaOH on multi spectral high fluctuation pattern,” Proc. - 2017 Int. Conf. Electr. Eng. Informatics Adv. Knowledge, Res. Technol. Humanit. ICELTICs 2017, vol. 2018-Janua, no. ICELTICs, pp. 184–188, 2017, doi: 10.1109/ICELTICS.2017.8253266.

S. Ortega, M. Halicek, H. Fabelo, G. M. Callico, and B. Fei, “Hyperspectral and multispectral imaging in digital and computational pathology: a systematic review [Invited],” Biomed. Opt. Express, 2020, doi: 10.1364/boe.386338.

G. B. Satrya, I. N. A. Ramatryana, and S. Y. Shin, “Compressive Sensing of Medical Images Based on HSV Color Space,” Sensors, 2023, doi: 10.3390/s23052616.

Y. Yunidar, Y. Yusni, N. Nasaruddin, and F. Arnia, “CNN Performance Improvement for Classifying Stunted Facial Images Using Early Stopping Approach,” J. RESTI, vol. 9, no. 1, pp. 62–68, 2025, doi: 10.29207/resti.v9i1.6068.

A. El Bergui, A. Porebski, and N. Vandenbroucke, “A lightweight spatial and spectral CNN model for classifying floating marine plastic debris using hyperspectral images,” Mar. Pollut. Bull., vol. 216, no. December 2024, p. 117965, 2025, doi: 10.1016/j.marpolbul.2025.117965.

A. Dastgir, W. Bin, M. U. Saeed, J. Sheng, L. Site, and H. Hassan, “Attention LinkNet-152: a novel encoder-decoder based deep learning network for automated spine segmentation,” Sci. Rep., vol. 15, no. 1, pp. 1–13, 2025, doi: 10.1038/s41598-025-95243-z.

N. Hasan, Y. Bao, A. Shawon, and Y. Huang, “DenseNet Convolutional Neural Networks Application for Predicting COVID-19 Using CT Image,” SN Comput. Sci., vol. 2, no. 5, pp. 1–11, 2021, doi: 10.1007/s42979-021-00782-7.

T. Chauhan, H. Palivela, and S. Tiwari, “Optimization and fine-tuning of DenseNet model for classification of COVID-19 cases in medical imaging,” Int. J. Inf. Manag. Data Insights, vol. 1, no. 2, p. 100020, 2021, doi: 10.1016/j.jjimei.2021.100020.

S. H. Lee et al., “Cropper : Vision-Language Model for Image Cropping through In-Context Learning”, DOI: https://doi.org/10.48550/arXiv.2408.07790

L. He, X. Cheng, A. Jiwa, D. Li, J. Fang, and Z. Du, “Zanthoxylum bungeanum Fruit Detection by Adaptive Thresholds in HSV Space for an Automatic Picking System,” IEEE Sens. J., vol. 23, no. 13, pp. 14471–14486, 2023, doi: 10.1109/JSEN.2023.3277042.

S. S. Sitanggang, Y. Yuhandri, and Adil Setiawan, “Image Transformation With Lung Image Thresholding and Segmentation Method,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 7, no. 2, pp. 278–285, 2023, doi: 10.29207/resti.v7i2.4321.

V. R. Joseph, “Optimal ratio for data splitting,” Stat. Anal. Data Min., vol. 15, no. 4, pp. 531–538, 2022, doi: 10.1002/sam.11583.

W. Zeng, “Image data augmentation techniques based on deep learning: A survey,” Math. Biosci. Eng., vol. 21, no. 6, pp. 6190–6224, 2024, doi: 10.3934/mbe.2024272.

S. Kumar, P. Asiamah, O. Jolaoso, and U. Esiowu, “Enhancing Image Classification with Augmentation: Data Augmentation Techniques for Improved Image Classification,” 2025, [Online]. Available: http://arxiv.org/abs/2502.18691

V. T. Hoang and K. H. Jo, “Practical Analysis on Architecture of EfficientNet,” Int. Conf. Hum. Syst. Interact. HSI, vol. 2021-July, pp. 2–5, 2021, doi: 10.1109/HSI52170.2021.9538782.

P. Jyothi, D. Haritha, and K. Arava, “Gender Classification Using Efficientnetb0 And Mobilenetv2,” vol. 14, no. 27, pp. 694–700, 2025, https://www.jneonatalsurg.com/index.php/jns/article/view/6499

P. Khairunnisa, W. E. Putra, and W. Yitong, “Convolutional Neural Networks Using EfficientNetB0 Architecture and Hyperparameters on Skin Disease Classification,” vol. 2, no. January, pp. 127–137, 2025, DOI: https://doi.org/10.57152/predatecs.v2i2.1569

N. P. Maylianti, I. G. Ngurah, L. Wijayakusuma, I. P. Chandra, and A. Wiguna, “Comparison of EfficientNet-B0 and ResNet-50 for Detecting Diseases in Cocoa Fruit,” vol. 9, no. 1, pp. 115–120, 2025, DOI: https://doi.org/10.30871/jaic.v9i1.8868

S. A. Hasanah, A. A. Pravitasari, A. S. Abdullah, I. N. Yulita, and M. H. Asnawi, “A Deep Learning Review of ResNet Architecture for Lung Disease Identification in CXR Image,” Appl. Sci., vol. 13, no. 24, 2023, doi: 10.3390/app132413111.

W. Xu and R. S. Cloutier, “A facial expression recognizer using modified ResNet-152,” EAI Endorsed Trans. Internet Things, vol. 7, no. 28, p. e5, 2022, doi: 10.4108/eetiot.v7i28.685.

A. D. C. Zebua, D. Y. Marbun, F. Thedora, and M. Harahap, “Classification of Lung Cancer with Convolutional Neural Network Method Using ResNet Architecture,” Teknika, vol. 13, no. 2, pp. 318–323, 2024, doi: 10.34148/teknika.v13i2.906.

M. Selin and K. P. Mathew, “ResNet152: A Deep Learning Approach for Robust Spoof Detection in Speaker Verification Systems,” J. Wirel. Mob. Networks, Ubiquitous Comput. Dependable Appl., vol. 15, no. 3, pp. 354–363, 2024, doi: 10.58346/JOWUA.2024.I3.023.

M. Talo, “Convolutional Neural Networks for Multi-class Histopathology Image Classification,” 2019, [Online]. Available: http://arxiv.org/abs/1903.10035

M. Zulhusni, C. A. Sari, and E. H. Rachmawanto, “Implementation of DenseNet121 Architecture for Waste Type Classification,” Adv. Sustain. Sci. Eng. Technol., vol. 6, no. 3, p. 02403015, 2024, doi: 10.26877/asset.v6i3.673.

H. Tian et al., “DenseNet model incorporating hybrid attention mechanisms and clinical features for pancreatic cystic tumor classification,” J. Appl. Clin. Med. Phys., vol. 25, no. 7, pp. 1–11, 2024, doi: 10.1002/acm2.14380.

P. M. A. Gawande and S. W. Varade, “MDVPB : Design of an Efficient Modified Densenet-161 Model for Advanced Vein Pattern Recognition in Biomedical Systems,” vol. 31, no. 8, pp. 692–714, 2024, DOI: https://doi.org/10.52783/cana.v31.1578

B. Alnur, Mulyono, Fitri Amillia, and S. Sutoyo, “JITE (Journal of Informatics andTelecommunication Engineering),” J. Informatics Telecommun. Eng., vol. 7, no. 1, pp. 102–111, 2023, [Online]. Available: https://www.researchgate.net/publication/335117624_Malang_City_Polytechnic_Web_Based_Student_Attendance_Information_System_Telecommunications_Engineering_Study_Program_Using_Fingerprint/fulltext/5d515fe34585153e594ef214/Malang-City-Polytechnic-Web-Based-S

B. Van Calster, L. Wynants, G. S. Collins, J. Y. Verbakel, and E. W. Steyerberg, “ROC curves for clinical prediction models part 3. The ROC plot: a picture that needs a 1000 words,” 2020. doi: 10.1016/j.jclinepi.2020.05.037.

J. Li, “Area under the ROC Curve has the most consistent evaluation for binary classification,” PLoS One, vol. 19, no. 12 December, 2024, doi: 10.1371/journal.pone.0316019.

T. C. F. Polo and H. A. Miot, “Use of roc curves in clinical and experimental studies,” 2020. doi: 10.1590/1677-5449.200186.

M. M. Ali, M. S. Islam, M. N. Uddin, and M. A. Uddin, “A conceptual IoT framework based on Anova-F feature selection for chronic kidney disease detection using deep learning approach,” Intell. Med., vol. 10, no. July, p. 100170, 2024, doi: https://doi.org/10.1590/1677-5449.200186.

X. Gao, N. Jamil, M. I. Ramli, and S. M. Z. S. Z. Ariffin, “A Comparative Analysis of Combination of CNN-Based Models with Ensemble Learning on Imbalanced Data,” Int. J. Informatics Vis., vol. 8, no. 1, pp. 456–464, 2024, doi: 10.62527/joiv.8.1.2194.

N. Hernandez, F. Carrillo-Perez, F. M. Ortuño, I. Rojas, and O. Valenzuela, “Understanding the Impact of Deep Learning Model Parameters on Breast Cancer Histopathological Classification Using ANOVA,” Cancers (Basel)., vol. 17, no. 9, pp. 1–24, 2025, doi: 10.3390/cancers17091425.

S. Waziry, A. B. Wardak, J. Rasheed, R. M. Shubair, K. Rajab, and A. Shaikh, “Performance comparison of machine learning driven approaches for classification of complex noises in quick response code images,” Heliyon, 2023, doi: 10.1016/j.heliyon.2023.e15108.

N. K. Naik, M. V. Subbarao, P. K. Sethy, S. K. Behera, and G. R. Panigrahi, “Machine learning with analysis-of-variance-based method for identifying rice varieties,” J. Agric. Food Res., vol. 18, no. March, p. 101397, 2024, doi: 10.1016/j.jafr.2024.101397.

Downloads

Published

2026-02-15

Issue

Section

Artificial Intelligence

How to Cite

Melinda, Nurdin, Y., Mufti, A., Anzella, S. ., Rusdiana, S., & D Acula, D. (2026). Comparative Analysis of Multispectral Image Classification Based on EfficientNetB0, ResNet152, DenseNet161, DenseNet121, and HSV Segmentation. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 10(1), 20-31. https://doi.org/10.29207/resti.v10i1.6873