Optimizing South Kalimantan Food Image Classification Through CNN Fine-Tuning
DOI:
https://doi.org/10.26555/jiteki.v10i4.30325Keywords:
CNN, Fine-Tuning, Image Classification, Traditional Food, South KalimantanAbstract
South Kalimantan's rich culinary heritage encompasses numerous traditional dishes that remain unfamiliar to visitors and digital platforms. While Convolutional Neural Networks (CNNs) have demonstrated remarkable success in image classification tasks, their application to regional cuisine faces unique challenges, particularly when dealing with limited datasets and visually similar dishes. This study addresses these challenges by evaluating and optimizing two pre-trained CNN architectures—EfficientNetB0 and InceptionV3—for South Kalimantan food classification. Using a custom dataset of 1,000 images spanning 10 traditional dishes, we investigated various fine-tuning strategies to maximize classification accuracy. Our results show that EfficientNetB0, with 30 fine-tuned layers, achieves the highest accuracy at 94.50%, while InceptionV3 reaches 92.00% accuracy with 40 layers fine-tuned. These findings suggest that EfficientNetB0 is particularly effective for classifying regional foods with limited data, outperforming InceptionV3 in this context. This study provides a framework for efficiently applying CNN models to small, specialized datasets, contributing to both the digital preservation of South Kalimantan’s culinary heritage and advancements in regional food classification. This research also opens the way for further research that can be applied to other less documented regional cuisines. The framework presented can be used as a reference for developing automated classification systems in a broader cultural context, thus enriching the digital documentation of traditional cuisines and preserving the culinary diversity of the archipelago for future generations.
References
[1] N. Suryani, A. N. Eliandha, and O. Libri, “Analisa Kandungan Zat Gizi Makro, Serat, Natrium, dan Kolesterol pada Kue Khas Kalimantan Selatan,” Jurnal Kesehatan Indonesia (The Indonesian Journal of Health), vol. 7, no. 3, pp. 125–29, Jul. 2021, [Online]. Available: https://journal.stikeshb.ac.id/index.php/jurkessia/article/download/448/194
[2] J. Jiang, “The eye of artificial intelligence - Convolutional Neural Networks,” Applied and Computational Engineering, vol. 76, no. 1, pp. 273–279, Jul. 2024, https://doi.org/10.54254/2755-2721/76/20240613.
[3] L. Balderas, M. Lastra, and J. M. Benítez, “Optimizing Convolutional Neural Network Architecture,” Mathematics, vol. 12, no. 3032, pp. 1–19, 2024, https://doi.org/10.3390/math12193032.
[4] H. Hashmi, R. K. Dwivedi, and A. Kumar, “Comparative Analysis of CNN-Based Smart Pre-Trained Models for Object Detection on Dota,” Journal of Automation, Mobile Robotics and Intelligent Systems, vol. 18, no. 2, pp. 31–45, Jun. 2024, https://doi.org/10.14313/JAMRIS/2-2024/11.
[5] G. Marques, D. Agarwal, and I. de la Torre Díez, “Automated medical diagnosis of COVID-19 through EfficientNet convolutional neural network,” Applied Soft Computing Journal, vol. 96, Nov. 2020, https://doi.org/10.1016/j.asoc.2020.106691.
[6] M. Harahap et al., “Skin cancer classification using EfficientNet architecture,” Bulletin of Electrical Engineering and Informatics, vol. 13, no. 4, pp. 2716–2728, Aug. 2024, https://doi.org/10.11591/eei.v13i4.7159.
[7] B. Alotaibi and M. Alotaibi, “A Hybrid Deep ResNet and Inception Model for Hyperspectral Image Classification,” PFG - Journal of Photogrammetry, Remote Sensing and Geoinformation Science, vol. 88, no. 6, pp. 463–476, Dec. 2020, https://doi.org/10.1007/s41064-020-00124-x.
[8] A. E. Minarno, L. Aripa, Y. Azhar, and Y. Munarko, “Classification of Malaria Cell Image Using Inception-V3 Architecture,” International Journal On Informatics Visualization, vol. 7, no. 2, pp. 273–278, 2023, https://dx.doi.org/10.30630/joiv.7.2.1301.
[9] F. Raza, “Transfer Learning in Deep Neural Networks,” Cosmic Bulletin Of Business Management, vol. 2, no. 1, pp. 189–205, Sep. 2023, http://dx.doi.org/10.13140/RG.2.2.25635.63529.
[10] B. Arslan, S. Memis, E. B. Sonmez, and O. Z. Batur, “Fine-Grained Food Classification Methods on the UEC FOOD-100 Database,” IEEE Transactions on Artificial Intelligence, vol. 3, no. 2, pp. 238–243, Apr. 2022, https://doi.org/10.1109/TAI.2021.3108126.
[11] D.-R.-N. Wang and Y. Dong, “Research on Food Fine Grain Image Classification Based on Improved Residual Network,” Res Sq, 2023, https://doi.org/10.21203/rs.3.rs-3377448/v1.
[12] S. Yadav, Alpana, and S. Chand, “Automated Food image Classification using Deep Learning approach,” in 2021 7th International Conference on Advanced Computing and Communication Systems, ICACCS 2021, Institute of Electrical and Electronics Engineers Inc., Mar. 2021, pp. 542–545. https://doi.org/10.1109/ICACCS51430.2021.9441889.
[13] E. S. Sreetha, G. N. Sundar, and D. Narmadha, “Enhancing Food Image Classification with Particle Swarm Optimization on NutriFoodNet and Data Augmentation Parameters,” International Journal of Computational and Experimental Science and Engineering, vol. 10, no. 4, pp. 718–730, Oct. 2024, https://doi.org/10.22399/ijcesen.493.
[14] S. Feng, Y. Wang, J. Gong, X. Li, and S. Li, “A fine-grained recognition technique for identifying Chinese food images,” Heliyon, vol. 9, no. 11, Nov. 2023, http://dx.doi.org/10.1016/j.heliyon.2023.e21565.
[15] K. Yu, “DimSum50: A benchmark dataset of Chinese food,” Applied and Computational Engineering, vol. 73, no. 1, pp. 271–279, Jul. 2024, https://doi.org/10.54254/2755-2721/73/20240411.
[16] S. Mainkar, “Efficient Deep Learning Approach for Food Image Classification,” The International journal of analytical and experimental modal analysis, vol. 15, no. 5, pp. 132–135, 2023, [Online]. Available: https://www.researchgate.net/publication/380597055
[17] A. M. Uddin, A. Al Miraj, M. Sen Sarma, A. Das, and M. M. Gani, “Traditional Bengali Food Classification Using Convolutional Neural Network,” in TENSYMP 2021 - 2021 IEEE Region 10 Symposium, Institute of Electrical and Electronics Engineers Inc., Aug. 2021. https://doi.org/10.1109/TENSYMP52854.2021.9550874.
[18] M. A. Rasyidi, Y. S. Mardhiyyah, Z. Nasution, and C. H. Wijaya, “Performance comparison of state-of-the-art deep learning model architectures in Indonesian food image classification,” Bulletin of Electrical Engineering and Informatics, vol. 13, no. 5, pp. 3355–3368, Oct. 2024, https://doi.org/10.11591/eei.v13i5.7996.
[19] M. Salvi, U. R. Acharya, F. Molinari, and K. M. Meiburger, “The impact of pre- and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis,” Elsevier Ltd., 2021, https://doi.org/10.1016/j.compbiomed.2020.104129.
[20] M. M. Ahsan, T. E. Alam, T. Trafalis, and P. Huebner, “Deep MLP-CNN model using mixed-data to distinguish between COVID-19 and Non-COVID-19 patients,” Symmetry (Basel), vol. 12, no. 9, pp. 1–14, Sep. 2020, https://doi.org/10.3390/sym12091526.
[21] A. Lalande et al., “Deep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge,” Med Image Anal, vol. 79, no. 102428, pp. 1–13, Jul. 2022, https://doi.org/10.1016/j.media.2022.102428.
[22] K. Tong, Y. Wu, and F. Zhou, “Recent advances in small object detection based on deep learning: A review,” Image Vis Comput, vol. 97, no. 103910, pp. 1–14, May 2020, https://doi.org/10.1016/j.imavis.2020.103910.
[23] O. Nassar, Data Leakage in Machine Learning. 2020. http://dx.doi.org/10.13140/RG.2.2.27468.59528.
[24] H. Abdel-Jaber, D. Devassy, A. Al Salam, L. Hidaytallah, and M. El-Amir, “A Review of Deep Learning Algorithms and Their Applications in Healthcare,” Algorithms, vol. 15, no. 2, 2022, https://doi.org/10.3390/a15020071.
[25] M. Abbasi, A. Shahraki, and A. Taherkordi, “Deep Learning for Network Traffic Monitoring and Analysis (NTMA): A Survey,” Comput Commun, vol. 170, pp. 19–41, Mar. 2021, https://doi.org/10.1016/j.comcom.2021.01.021.
[26] A. Wahid, K. Ullah, S. I. Ullah, M. Amin, S. Almutairi, and M. Abohashrh, “sEMG-based Upper Limb Elbow Force Estimation Using CNN, CNN-LSTM, and CNN-GRU Models,” IEEE Access, vol. 12, 2024, https://doi.org/10.1109/ACCESS.2024.3451209.
[27] L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J Big Data, vol. 8, no. 53, pp. 1–74, Dec. 2021, https://doi.org/10.1186/s40537-021-00444-8.
[28] L. Jiang et al., “Numerical investigation of the effective receptive field and its relationship with convolutional kernels and layers in convolutional neural network,” Front Mar Sci, vol. 11, Oct. 2024, https://doi.org/10.3389/fmars.2024.1492572.
[29] E. A. Mohamed, T. Gaber, O. Karam, and E. A. Rashed, “A Novel CNN pooling layer for breast cancer segmentation and classification from thermograms,” PLoS One, vol. 17, pp. 1–18, Oct. 2022, https://doi.org/10.1371/journal.pone.0276523.
[30] M Mesran, Sitti Rachmawati Yahya, Fifto Nugroho, and Agus Perdana Windarto, “Investigating the Impact of ReLU and Sigmoid Activation Functions on Animal Classification Using CNN Models,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 8, no. 1, pp. 111–118, Feb. 2024, https://doi.org/10.29207/resti.v8i1.5367.
[31] Y. Lee, “The CNN: The Architecture Behind Artificial Intelligence Development,” Journal of Student Research, vol. 12, no. 4, pp. 1–12, 2023, https://doi.org/10.47611/jsrhs.v12i4.5579.
[32] J. Pardede and A. S. Purohita, “The Advantage of Transfer Learning with Pre-Trained Model in CNN Towards Ct-Scan Classification,” Khazanah Informatika (Jurnal Ilmu Komputer dan Informatika), vol. 9, no. 2, pp. 155–161, Oct. 2023, https://doi.org/10.23917/khif.v9i2.19872.
[33] Y. Gao, P.-C. Luan, and A. Alahi, “Multi-Transmotion: Pre-trained Model for Human Motion Prediction,” ArXiv, 2024, https://doi.org/10.48550/arXiv.2411.02673.
[34] A. Philip, “Optimizing Food101 Classification with Transfer Learning: A Fine-Tuning Approach Using EfficientNetB0,” International Journal of Intelligent Information Systems, vol. 13, no. 4, pp. 59–77, Aug. 2024, https://doi.org/10.11648/j.ijiis.20241304.11.
[35] K. Kansal, T. B. Chandra, and A. Singh, “ResNet-50 vs. EfficientNet-B0: Multi-Centric Classification of Various Lung Abnormalities Using Deep Learning,” Procedia Comput Sci, vol. 235, pp. 70–80, 2024, https://doi.org/10.1016/j.procs.2024.04.007.
[36] J. Cao, M. Yan, Y. Jia, X. Tian, and Z. Zhang, “Application of a modified Inception-v3 model in the dynasty-based classification of ancient murals,” EURASIP J Adv Signal Process, vol. 49, 2021, https://doi.org/10.1186/s13634-021-00740-8.
[37] G. Vrbančič and V. Podgorelec, “Transfer learning with adaptive fine-tuning,” IEEE Access, vol. 8, pp. 196197–196211, Oct. 2020, https://doi.org/10.1109/ACCESS.2020.3034343.
[38] S. Ben Brahim, S. Dardouri, and R. Bouallegue, “Brain Tumor Detection Using a Deep CNN Model,” Applied Computational Intelligence and Soft Computing, vol. 2024, no. 1, Jan. 2024, https://doi.org/10.1155/2024/7634426.
[39] L. Ali, F. Alnajjar, H. Al Jassmi, M. Gochoo, W. Khan, and M. A. Serhani, “Performance evaluation of deep CNN-based crack detection and localization techniques for concrete structures,” Sensors, vol. 21, no. 5, pp. 1–22, Mar. 2021, https://doi.org/10.3390/s21051688.
[40] M. Owusu-Adjei, J. Ben Hayfron-Acquah, T. Frimpong, and G. Abdul-Salaam, “Imbalanced class distribution and performance evaluation metrics: A systematic review of prediction accuracy for determining model performance in healthcare systems,” PLOS Digital Health, vol. 2, no. 11 November, Nov. 2023, https://doi.org/10.1371/journal.pdig.0000290.
[41] Y. S. Taspinar, I. Cinar, and M. Koklu, “Classification by a stacking model using CNN features for COVID-19 infection diagnosis,” J Xray Sci Technol, vol. 30, no. 1, pp. 73–88, 2022, https://doi.org/10.3233/XST-211031.
[42] D. F. Anas, I. Jaya, and Y. Herdiyeni, “Measurement and Analysis of Detecting Fish Freshness Levels Using Deep Learning Method,” IJCCS (Indonesian Journal of Computing and Cybernetics Systems), vol. 18, no. 4, pp. 1–12, 2024, https://doi.org/10.22146/ijccs.95054.
[43] Ž. Vujović, “Classification Model Evaluation Metrics,” (IJACSA) International Journal of Advanced Computer Science and Applications, vol. 12, no. 6, pp. 599–606, 2021, https://doi.org/10.14569/IJACSA.2021.0120670.
[44] S. Suyahman, S. Sunardi, M. Murinto, and A. N. Khusna, “Siamese Neural Network Optimization Using Distance Metrics for Trademark Image Similarity Detection,” International Journal of Computing and Digital Systems, vol. 17, no. 1, 2024, http://dx.doi.org/10.13140/RG.2.2.11236.59522.
[45] S. A. Hicks et al., “On evaluation metrics for medical applications of artificial intelligence,” Sci Rep, vol. 12, no. 5979, pp. 1–9, 2022, https://doi.org/10.1038/s41598-022-09954-8.
[46] T. Thanchomnang, N. Chaibutr, W. Maleewong, and P. Janwan, “Automatic detection of Opisthorchis viverrini egg in stool examination using convolutional-based neural networks,” PeerJ, vol. 12, 2024, http://dx.doi.org/10.7717/peerj.16773.
[47] D. Chicco and G. Jurman, “The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation,” BMC Genomics, vol. 21, no. 6, pp. 1–13, Jan. 2020, https://doi.org/10.1186/s12864-019-6413-7.
[48] S. Farhadpour, T. A. Warner, and A. E. Maxwell, “Selecting and Interpreting Multiclass Loss and Accuracy Assessment Metrics for Classifications with Class Imbalance: Guidance and Best Practices,” Remote Sens (Basel), vol. 16, no. 3, pp. 1–22, Feb. 2024, https://doi.org/10.3390/rs16030533.
[49] M. Grandini, E. Bagli, and G. Visani, “Metrics for Multi-Class Classification: an Overview,” ArXiv, pp. 1–17, 2020, https://doi.org/10.48550/arXiv.2008.05756.
[50] M. Chun, H. Jeong, H. Lee, T. Yoo, and H. Jung, “Development of Korean Food Image Classification Model Using Public Food Image Dataset and Deep Learning Methods,” IEEE Access, vol. 10, pp. 128732–128741, 2022, https://doi.org/10.1109/ACCESS.2022.3227796.
[51] A. Wulandari, “Comparing CNN Architecture for Indonesian Speciality Cuisine Classification,” Engineering, MAthematics and Computer Science Journal (EMACS), vol. 6, no. 1, pp. 55–60, Jan. 2024, https://doi.org/10.21512/emacsjournal.v6i1.11076.
[52] S. Ittisoponpisan, C. Kaipan, S. Ruang-On, R. Thaiphan, and K. Songsri-In, “Pushing the Accuracy of Thai Food Image Classification with Transfer Learning,” Engineering Journal, vol. 26, no. 10, pp. 57–71, Oct. 2022, http://dx.doi.org/10.4186/ej.2022.26.10.57.
[53] D. D. Rao and N. P. Ranga, “Indian Food Image Classification Using K-Nearest-Neighbour and Support-Vector-Machines,” International Journal For Advanced Research In Science & Technology (IJARST), vol. 9, no. 6, pp. 201–208, Jun. 2021, Accessed: Oct. 22, 2024. [Online]. Available: https://www.ijarst.in/public/uploads/paper/224541651315848.pdf
[54] E. Tasci, “Voting combinations-based ensemble of fine-tuned convolutional neural networks for food image recognition,” Multimed Tools Appl, vol. 79, no. 79, pp. 30397–30418, 2020, https://doi.org/10.1007/s11042-020-09486-1.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Muhammad Ridha Maulidi, Fatma Indriani, Andi Farmadi, Irwan Budiman, Dwi Kartini
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with JITEKI agree to the following terms:
- Authors retain copyright and grant the journal the 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 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.
This work is licensed under a Creative Commons Attribution 4.0 International License
