Mobile Application Deployment of CNN-based Food Classification System for Visually Impaired Individuals: A Real-Life Application for Nigerian Swallow Foods

The study addresses the significant challenge of food identification faced by visually impaired individuals, particularly in culturally specific contexts like Nigerian cuisine. A convolutional neural network (CNN) classification system was developed to categorize Nigerian swallow foods and assess their freshness (Fresh, 4 Hours Old, 1 Day Old) across 60 fine-grained classes using a dataset of 22,823 items. Six light CNN architectures were trained and evaluated based on metrics such as accuracy, macro-averaged precision, recall, F1 score, and AUC-ROC, alongside their parameter count and inference latency for deployment suitability. Among these, MobileNetV2 emerged as the top performer, achieving a test accuracy of 99.78%, a macro F1 score of 0.9979, and a perfect AUC-ROC of 1.0000, while maintaining a moderate parameter count of 2.33 million, making it suitable for mobile applications. LeNet-5 and ShuffleNetV2 also demonstrated strong performances with accuracies above 98.9%. In contrast, CCFNN exhibited poor performance with only 23.54% accuracy due to capacity issues. The best-performing model, MobileNetV2, was integrated into an application named Naija Food Eye, which facilitates food identification and freshness assessment for the visually impaired, providing confidence scores, top-5 predictions, and quick response times. The findings confirm that lightweight CNN models can effectively assist visually impaired individuals in recognizing foods within a culturally rich culinary landscape, offering a viable, deployable solution.

Assistive Technology, Convolutional Neural Network, Deep Learning, Food Classification, Mobile Application, Nigerian Swallow Foods, Transfer Learning, Visually Impaired.

1. World Health Organization (WHO), "World Report on Vision," WHO Press, Geneva, Switzerland, 2019. [Online]. Available: https://www.who.int/publications/i/item/9789241516570 [Google Scholar] [Crossref]

2. S. Memiş, B. Arslan, O. Z. Batur, and E. B. Sönmez, "A Comparative Study of Deep Learning Methods on Food Classification Problem," in Proc. 2020 IEEE Conf. Signal Processing and Communication Applications, Istanbul, Turkey, 2020, pp. 1–4. doi: 10.1109/SIU49456.2020.9302375 [Google Scholar] [Crossref]

3. 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. 128732–128743, Dec. 2022. doi: 10.1109/ACCESS.2022.3227796 [Google Scholar] [Crossref]

4. J. Gadhiya, A. Khatik, S. Kodinariya, and D. Ramoliya, "Classification of Regional Food Using Pre-Trained Transfer Learning Models," in Proc. 7th IEEE Int. Conf. Electronics, Communication and Aerospace Technology (ICECA), 2023, pp. 1–6. doi: 10.1109/ICECA58529.2023.10395249 [Google Scholar] [Crossref]

5. R. G. Tiwari, V. Gautam, A. K. Jain, and V. Sharma, "A Study on Food Classification and its Significance in Promoting Tourism and Boosting the Economy," in Proc. 2nd IEEE Int. Conf. Augmented Intelligence and Sustainable Systems (ICAISS), 2023, pp. 1–6. doi: 10.1109/ICAISS58487.2023.10250473 [Google Scholar] [Crossref]

6. S. S. Deven and P. M. Jacob, "An Android App Based Food Calorie Estimator Using Machine Vision," in Proc. 3rd IEEE Int. Conf. Advances in Computation, Communication and Information Technology (ICAICCIT), 2025, pp. 1–5. doi: 10.1109/ICAICCIT68829.2025.11434291 [Google Scholar] [Crossref]

7. N. K. Sripada, S. C. Challa, and S. Kothakonda, "AI-Driven Nutritional Assessment Improving Diets with Machine Learning and Deep Learning for Food Image Classification," in Proc. IEEE Int. Conf. Self Sustainable Artificial Intelligence Systems (ICSSAS), 2023, pp. 1–6. doi: 10.1109/ICSSAS57918.2023.10331787 [Google Scholar] [Crossref]

8. A. M. Antony and R. S. Kumar, "A Comparative Study on Predicting Food Quality using Machine Learning Techniques," in Proc. 7th IEEE Int. Conf. Advanced Computing and Communication Systems (ICACCS), 2021, pp. 1–5. doi: 10.1109/ICACCS51430.2021.9441743 [Google Scholar] [Crossref]

9. S. Jr. D. Rollo and J. P. T. Yusiong, "A Two-Color Space Input Parallel CNN Model for Food Image Classification," in Proc. IEEE Int. Conf. Information Technology Research and Innovation (ICITRI), 2024, pp. 138–143. doi: 10.1109/ICITRI62858.2024.10698941 [Google Scholar] [Crossref]

10. B. Panduri, N. Vullam, R. S. S. R. Battula, V. D. Babu, V. S. Desanamukula, and A. Lakshmanarao, "Food Classification Using a Hybrid Framework with Transfer Learning and Machine Learning Models," in Proc. IEEE Int. Conf. Advances in Modern Age Technologies for Health and Engineering Science (AMATHE), 2025, pp. 1–6. doi: 10.1109/AMATHE65477.2025.11081177 [Google Scholar] [Crossref]

11. E. K. Reddy, T. S. P. Balaji, and K. K. Manivannan, "AI Based Food Freshness Tracking System with Shelf-Life Prediction," in Proc. 5th IEEE Int. Conf. Intelligent Technologies (CONIT), 2025, pp. 1–5. doi: 10.1109/CONIT65521.2025.11166784 [Google Scholar] [Crossref]

12. J. Sultana, B. M. Ahmed, M. M. Masud, A. K. O. Huq, M. E. Ali, and M. Naznin, "A Study on Food Value Estimation From Images: Taxonomies, Datasets, and Techniques," IEEE Access, vol. 11, pp. 45904–45930, May 2023. doi: 10.1109/ACCESS.2023.3274475 [Google Scholar] [Crossref]

13. A. Hong, J.-S. Ma, and S. Bellur, "Comparative Analysis of AI Models for Fast Food Image Classification," in Proc. IEEE Int. Conf. Electrical and Computer Engineering Researches (ICECER), 2025, pp. 1–6. doi: 10.1109/ICECER65523.2025.11401344 [Google Scholar] [Crossref]

14. K. Tejaswi et al., "Automating Nutritional Claim Verification: The Role of OCR and Machine Learning in Enhancing Food Label Transparency," in Proc. IEEE Int. Conf. IoT Based Control Networks and Intelligent Systems (ICICNIS), 2024, pp. 1–5. doi: 10.1109/ICICNIS64247.2024.10823177 [Google Scholar] [Crossref]

15. R. Rahman, M. Hassan, A. F. Tasnim, and J. Ferdousmou, "AI-Powered Personalized Nutrition Based on Biochemical Data: An Exploration of Machine Learning Applications," in Proc. IEEE Int. Conf. Contemporary Computing and Communications (InC4), 2025, pp. 1–6. doi: 10.1109/InC465408.2025.11256407 [Google Scholar] [Crossref]

16. M. Hemalatha and G. Muthupandi, "A Comprehensive Framework for Nutrition Analysis and Ingredient Substitution using Machine Learning," in Proc. IEEE Int. Conf. Data Science, Agents and Artificial Intelligence (ICDSAAI), 2025, pp. 1–6. doi: 10.1109/ICDSAAI65575.2025.11011623 [Google Scholar] [Crossref]

17. X. Liu et al., "Automatic Detection Model of Food Microbial Contamination Combined with Image Processing and Pattern Recognition," in Proc. IEEE Int. Conf. Telecommunications and Power Electronics (TELEPE), 2024, pp. 1–5. doi: 10.1109/TELEPE64216.2024.00121 [Google Scholar] [Crossref]

18. R. Rajagopal and K. Chaithanya, "Comparative Study of Machine Learning and Deep Learning Models for Food Waste Detection Using Image Processing," in Proc. IEEE Int. Students' Conf. Electrical, Electronics and Computer Science (SCEECS), 2025, pp. 1–5. doi: 10.1109/SCEECS64059.2025.10941059 [Google Scholar] [Crossref]

19. N. Sateesh, N. Rawat, W. Patel, and H. Patil, "A Classification Model for Pesticide Residues in Food Based on Machine Learning Methods," in Proc. 5th IEEE Int. Conf. Innovative Trends in Information Technology (ICITIIT), 2024, pp. 1–5. doi: 10.1109/ICITIIT61487.2024.10580640 [Google Scholar] [Crossref]

20. S. Rastogi and Ranjana, "Comparative Analysis of Machine Learning Algorithms for Wheat Grain Classification using Ensemble Learning Approaches," in Proc. 14th IEEE Int. Conf. System Modeling and Advancement in Research Trends (SMART), 2025, pp. 1–6. doi: 10.1109/SMART66937.2025.11389335 [Google Scholar] [Crossref]

21. B. S. N. Rao et al., "An Innovative Machine Learning System for Optimal Multi-Class Classification of Date Fruits by Leveraging Backward Feature Engineering to Promote Sustainable Agriculture," in Proc. IEEE Int. Conf. Integrated Intelligence and Communication Systems (ICIICS), 2024, pp. 1–6. doi: 10.1109/ICIICS63763.2024.10859468 [Google Scholar] [Crossref]

22. S. Reddy and V. Subbaiah, "Comparative Analysis of Hyperspectral Imaging with Machine Learning Assessment of Crop Health and Honey Quality," in Proc. 2nd IEEE Int. Conf. Recent Advances in Information Technology for Sustainable Development (ICRAIS), 2024, pp. 1–5. doi: 10.1109/ICRAIS62903.2024.10811699 [Google Scholar] [Crossref]

23. E. S. Thomas et al., "EfficientNet-Based Feature Extraction and Ensemble Learning for Tomato Quality Classification," in Proc. 3rd IEEE Int. Conf. Intelligent Systems, Advanced Computing and Communication (ISACC), 2025, pp. 1–6. doi: 10.1109/ISACC65211.2025.10969232 [Google Scholar] [Crossref]

24. C. Harishankar, S. Anoop, and K. S. Niranjana, "An Explainable Hybrid Learning Model for Indian Food Image Classification," in Proc. 15th IEEE Int. Conf. Computing Communication and Networking Technologies (ICCCNT), 2024, pp. 1–6. doi: 10.1109/ICCCNT61001.2024.10724730 [Google Scholar] [Crossref]

25. Q.-L. Tran, G.-H. Lam, Q.-N. Le, T.-H. Tran, and T.-H. Do, "A Comparison of Several Approaches for Image Recognition used in Food Recommendation System," in Proc. IEEE Int. Conf. Communication, Networks and Satellite (COMNETSAT), 2021, pp. 1–6. doi: 10.1109/COMNETSAT53002.2021.9530793 [Google Scholar] [Crossref]

26. S. Sivagami et al., "Automated Digitally Modulated Signal Recognition and Classification using Machine Learning with Multimodal Information," in Proc. 2nd IEEE Int. Conf. Augmented Intelligence and Sustainable Systems (ICAISS), 2023, pp. 1–5. doi: 10.1109/ICAISS58487.2023.10250687 [Google Scholar] [Crossref]

27. S. Subedi et al., "Enhancing Allergy Prediction Accuracy Through Machine Learning and ProteinBERT," in Proc. IEEE Int. Conf. Machine Learning and Applications (ICMLA), 2024, pp. 1–6. doi: 10.1109/ICMLA61862.2024.00068 [Google Scholar] [Crossref]

28. A. Singh et al., "Diabetes Prediction System Using Machine Learning," in Proc. IEEE Int. Conf. Advances in Computation, Communication and Information Technology (ICAICCIT), 2023, pp. 1–5. doi: 10.1109/ICAICCIT60255.2023.10466034 [Google Scholar] [Crossref]

29. V. Shevchenko, A. Lukashevich, and Y. Maximov, "Climate Change Impact on Agricultural Land Suitability: An Interpretable Machine Learning-Based Eurasia Case Study," IEEE Access, vol. 12, pp. 14000–14020, Jan. 2024. doi: 10.1109/ACCESS.2024.3358865 [Google Scholar] [Crossref]

30. S. Milosavljević et al., "Exploiting Machine Learning for Industrial Defrost Cycle Characterization," in Proc. 33rd IEEE Telecommunications Forum (TELFOR), 2025, pp. 1–5. doi: 10.1109/TELFOR67910.2025.11314454 [Google Scholar] [Crossref]

31. A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, "MobileNets: Efficient convolutional neural networks for mobile vision applications," arXiv preprint arXiv:1704.04861, 2017. [Google Scholar] [Crossref]

32. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, Nov. 1998, doi: 10.1109/5.726791. [Google Scholar] [Crossref]

33. J. R. Olasina and O. H. Aliu, "Development of convolutional neural network (CNN)-based automatic food classification (AFC) model for visual impairments of Nigerians," in Applied Mathematics, Modeling and Computer Simulation. Amsterdam, The Netherlands: IOS Press, 2024, pp. 2–10, doi: 10.3233/ATDE240774. [Google Scholar] [Crossref]

34. F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and less than 0.5MB model size," arXiv preprint arXiv:1602.07360, 2016. [Google Scholar] [Crossref]

35. N. Ma, X. Zhang, H.-T. Zheng, and J. Sun, "ShuffleNet V2: Practical guidelines for efficient CNN architecture design," in Proc. Eur. Conf. Computer Vision (ECCV), Munich, Germany, 2018, pp. 116–131, doi: 10.1007/978-3-030-01264-9_8. [Google Scholar] [Crossref]

• Enhancing Formation Control of Multi Agent Systems Using Ann Based Technique
• Improving Sliding Mode Control with Chattering Reduction using Fuzzy Based Technique
• Cooking Quality, Fasting Blood Glucose, Glycemic Index and Load of High–Fiber Noodles Made from Wheat, Tiger Nut Residue and Cassava Flour Blends
• Matrix Rhythm Therapy Versus Interferential Therapy Combined with Lumbar Stabilization Exercises in Chronic Non-Specific Low Back Pain: A Randomized Comparative Trial
• Formulation and Sensory Evaluation of Functional Cake Prepared from Sweet Potato Powder