Food Image Classification and Recipe Recommendation for South Sumatran Cuisine Using EfficientNetB1

Farhah Salsabillah; Ade Silvia Handayani; Nurhajar  Anugraha

doi:10.15408/jti.v18i2.46449

Authors

Farhah Salsabillah Department of Electrical Engineering, Telecommunication Engineering, Sriwijaya State Polytechnic, Indonesia https://orcid.org/0009-0004-7636-2910
Ade Silvia Handayani Department of Electrical Engineering, Telecommunication Engineering, Sriwijaya State Polytechnic, Indonesia https://orcid.org/0000-0002-4476-426X
Nurhajar Anugraha Department of Electrical Engineering, Telecommunication Engineering, Sriwijaya State Polytechnic, Indonesia https://orcid.org/0009-0001-0940-5974

DOI:

https://doi.org/10.15408/jti.v18i2.46449

Keywords:

convolutional neural network (CNN), EfficientNetB, food image classification, Transfer Learning, recipe recommendation system, large language model

Abstract

Visual-based food classification and recipe recommendation systems remain underexplored in the context of local culinary traditions. To address this gap, a system was developed using the EfficientNetB1 architecture of Convolutional Neural Networks (CNN), integrated with a Large Language Model (LLM) to generate South Sumatran recipes from food images, adapting suggestions to classification results. The model was trained using transfer learning on eight food ingredient classes selected for their prevalence in local cuisine. It achieved a validation accuracy of 98.2% and a test accuracy of 98%, with average precision, recall, and F1-score all exceeding 98%, indicating consistent and reliable performance. The system was deployed as a web-based application, DapoerKito, allowing users to upload food images, receive classification results, and obtain generated recipe suggestions. LLM-generated recipes are produced instantly, matched to ingredients, and shown in a clear format. These findings demonstrate the value of integrating computer vision and language generation in an AI-based platform that supports usability and cultural relevance. In addition to its technical capabilities, the system contributes to the digital preservation of regional culinary heritage through interactive AI. This CNN–LLM integration offers a novel approach for advancing food AI with diverse ingredients, personalized nutrition, and multilingual support.

References

[1] K. A. Nair, S. G. Chavhan, and T. N. Pawar, “Recipe-fusion : Multimodal Food Recipe Recommendation System,” J. Artif. Intell. Res. Adv., vol. 11, no. 3, pp. 82–91, 2024.

[2] P. V. G. Bharane, C. S. Ashish, D. V. Subhash, and Z. K. Bharat, “RecipeReveal – Ingredients and Recipe Generation from Food Image,” Int. J. Adv. Comput. Eng. Commun. Technol., vol. 14, no. 1, pp. 36–40, 2025.

[3] M. S. Rodrigues, F. Fidalgo, and Â. Oliveira, “RecipeIS—Recipe Recommendation System Based on Recognition of Food Ingredients,” Appl. Sci., vol. 13, no. 13, 2023, doi: 10.3390/app13137880.

[4] B. Reynaldy, “73% Masyarakat Indonesia Memasak dengan Resep Asal Keluarga,” GoodStats, 2024. [Online]. Available: https://data.goodstats.id/statistic/73-masyarakat-indonesia-memasak-dengan-resep-asal-keluarga-pZf3S.

[5] I. Fikriansyah, “10 Makanan Khas Sumatera Selatan Ini Wajib Dicoba, Enak Banget,” detikcom, 2023. [Online]. Available: https://www.detik.com/sumbagsel/kuliner/d-6763244/10-makanan-khas-sumatera-selatan-ini-wajib-dicoba-enak-banget.

[6] Kallysta Wijaya, “Mengenal Lezatnya Makanan Khas Palembang: Dari Pempek hingga Pindang Patin,” Good News From Indonesia, 2025. [Online]. Available: https://www.goodnewsfromindonesia.id/2025/02/20/mengenal-lezatnya-makanan-khas-palembang-dari-pempek-hingga-pindang-patin.

[7] M. Addanki, P. Patra, and P. Kandra, “Recent advances and applications of artificial intelligence and related technologies in the food industry,” Appl. Food Res., vol. 2, no. 2, p. 100126, 2022, doi: 10.1016/j.afres.2022.100126.

[8] Z. Zhu and Y. Dai, “A New CNN-Based Single-Ingredient Classification Model and Its Application in Food Image Segmentation,” J. Imaging, vol. 9, no. 10, p. 205, 2023, doi: 10.3390/jimaging9100205.

[9] S. E. Sreedharan, G. N. Sundar, and D. Narmadha, “NutriFoodNet: A High-Accuracy Convolutional Neural Network for Automated Food Image Recognition and Nutrient Estimation,” Trait. du Signal, vol. 41, no. 4, pp. 1953–1965, 2024, doi: 10.18280/ts.410425.

[10] X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif. Intell. Rev., vol. 57, no. 4, pp. 1–43, 2024, doi: 10.1007/s10462-024-10721-6.

[11] W. Hua, C. Li, and X. Wang, “Review of Convolutional Neural Network Models and Image Classification,” Acad. J. Sci. Technol., vol. 10, no. 3, pp. 178–184, 2024, doi: 10.54097/644jqv20.

[12] L. Alzubaidi et al., “Review of deep learning : concepts , CNN architectures , challenges , applications , future directions,” J. Big Data, vol. 8, p. Art. no. 53, 2021, doi: 10.1186/s40537-021-00444-8.

[13] M. Dandi Darojat, Y. A. Sari, and R. C. Wihandika, “Convolutional Neural Network untuk Klasifikasi Citra Makanan Khas Indonesia,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 5, no. 11, pp. 4764–4769, 2021.

[14] R. Abiyev and J. Adepoju, “Automatic Food Recognition Using Deep Convolutional Neural Networks with Self ‑ attention Mechanism,” Human-Centric Intell. Syst., vol. 4, no. 1, pp. 171–186, 2024.

[15] Z. Chen, J. Wang, and Y. Wang, “Enhancing Food Image Recognition by Multi-Level Fusion and the Attention Mechanism,” Foods, vol. 14, no. 3, pp. 1–21, 2025, doi: 10.3390/foods14030461.

[16] C. Mahaputri, Y. Kristian, and E. Setyati, “Pengenalan Makanan Tradisional Indonesia Beserta Bahan-bahannya dengan Memanfaatkan DCNN Transfer Learning,” INSYST Inf. Syst. Technol. J., vol. 04, no. 02, pp. 94–101, 2022, doi: 10.52985/insyst.v4i2.252.

[17] R. A. Boimau and Y. R. Kaesmetan, “Klasifikasi Citra Digital Bumbu dan Rempah Dengan Algoritma Convolutional Neural Network (CNN),” Repeater Publ. Tek. Inform. dan Jar., vol. 2, no. 3, pp. 26–34, 2024, doi: 10.62951/repeater.v2i3.81.

[18] W. Prayogo Kusumo and C. Sri Kusuma Aditya, “Klasifikasi Citra Makanan Berdasarkan Asal Daerah Menggunakan Convolutional Neural Network,” Techno.COM, vol. 23, no. 1, pp. 87–95, 2024, doi: 10.62411/tc.v23i1.9735.

[19] R. Raza et al., “Lung-EffNet: Lung cancer classification using EfficientNet from CT-scan images,” Eng. Appl. Artif. Intell., vol. 126, no. PB, p. 106902, 2023, doi: 10.1016/j.engappai.2023.106902.

[20] B. A. Y. K. W. Putra et al., DeepSeek AI: Panduan Super Lengkap untuk Memanfaatkan AI Secara Maksimal. SIEGA Publisher, 2025.

[21] Y. S. Soekamto, A. Lim, L. C. Limanjaya, Y. K. Purwanto, S. H. Lee, and D. K. Kang, “Pic2Plate: A Vision-Language and Retrieval-Augmented Framework for Personalized Recipe Recommendations,” Sensors, vol. 25, no. 2, pp. 1–37, 2025, doi: 10.3390/s25020449.

[22] G. Thiodorus, A. Prasetia, L. A. Ardhani, and N. Yudistira, “Klasifikasi citra makanan/non makanan menggunakan metode Transfer Learning dengan model Residual Network,” Teknologi, vol. 11, no. 2, pp. 74–83, 2021, doi: 10.26594/teknologi.v11i2.2402.

[23] M. R. M. Razali, H. F. Almarzuki, and N. A. S. Bahar, Rabiah Adawiyah Abdullah, “Food Recipe Recommendation Based on Ingredients Detection Using Deep Learning,” ACM Int. Conf. Proceeding Ser., no. InvENT, pp. 191–198, 2022, doi: 10.1145/3542954.3542983.

[24] K. A. Nfor, T. P. Theodore Armand, K. P. Ismaylovna, M. Il Joo, and H. C. Kim, “An Explainable CNN and Vision Transformer-Based Approach for Real-Time Food Recognition,” Nutr. , vol. 17, no. 2, pp. 1–24, 2025, doi: 10.3390/nu17020362.

[25] Z. Li, F. Li, L. Zhu, and J. Yue, “Vegetable recognition and classification based on improved VGG deep learning network model,” Int. J. Comput. Intell. Syst., vol. 13, no. 1, pp. 559–564, 2020, doi; 10.2991/ijcis.d.200425.001.