Although to have a healthy lifestyle, it is crucial to understand what is written on food product labels, a majority of consumers find it hard to decipher nutritional data and ingredient lists because of the complicated terms used and their ignorance. In this paper, the author will introduce an AI-based food label analyser which combines both the Optical Character Recognition (OCR) and barcodes scanning methods to deliver a practical and convenient solution to the analysis of packaged food products. The system proposed allows users to scan a product barcode or take an image of a food label. OCR is utilized to capture unstructured textual data like ingredients, nutritional values and additives to product packaging and barcode scanning is used to quickly access structured product information as it is stored in readily accessible databases. The information extracted are then processed and analysed with a machine learning-based classification technique to assess the overall nutritional quality of the product. This system is aimed at the detection of the most crucial health indicators, such as the sugar level, the fat content, the concentration of sodium and the presence of artificial additives or preservatives. Using this analysis, the application assigns food items to various levels of health and offers valuable insights to help users make healthy food choices. It is created with Flutter to be deployed on all platforms and uses Google ML Kit to detect barcodes and OCR in real-time. Experimental analysis shows that the system is very accurate in extracting text as well as reliable in barcode recognition to different conditions. OCR and barcode scanning together is more flexible, data is more reliable, and is more usable in real-life situations. On the whole, the suggested system will help spread health awareness by making the interpretation of food labels easier and making it possible to analyse nutrition in real- time and intelligently, using an accessible mobile platform.

This paper introduced an AI-driven food label analyser that combines OCR, barcode scanning, and machine learning methods to make it easier to understand information about food products. With a mobile app, the system lets users quickly get nutritional information from packaged foods and analyse it. Combining OCR and barcode scanning lets you quickly get structured product information from food labels and unstructured textual data from food labels. The machine learning model makes the system even better by looking at the nutritional value of food and sorting it into groups based on health factors. The tests show that the proposed system can give users accurate and useful information that helps them make smart choices about what to eat. The app is easy to use, works quickly, and can be used in real time, making it a good choice for promoting health awareness. There are many ways to make the proposed system even better so that it works better and can be used more widely. One possible improvement is to use more advanced deep learning models to make OCR more accurate, especially for images that are hard to read or of low quality. You can also connect the system to big cloud-based food databases to get more complete and up-to-date information about products. Adding personalised diet suggestions based on a user’s health profile can also make the app much more useful. Adding support for more than one language can make the system easier for more people to use. Real-time voice assistance and wearable device integration can also make it easier for users to interact with the system. These changes will make the system smarter, more flexible, and more focused on the needs of users

1.Parkavi,”Android App for Food Allergen Detection,”IEEE,2023. 2.K.Azzimani,”AI-Based Personalized Nutrition,”Information Fusion,vol.78,pp.1-12,2022. 3. S.-C.Huang and W.-C.Chiang,”An Image-Based AI Nutrition Analysis Platform for Tray Foods,”2023. 4.D.Khairani,”Hala Ingredient Detection Via OCR and Named Entity Recognition,”IEEE,2022. 5.S.P.Siddique Ibrahim,”Nutritional Claim verification Using Ai,”2024. 6.S.Xiong and G.Bai,”Food Safety Risk Detection Using Artificial Intelligence,”IEEE,2023. 7.P.Kwon,”Smart Nutrition Application for Children,”IEEE,2023. 8.H.A.AI-Manwari,”Smart Food Analyzer System,”2023. 9.D.Ilango,”Toxin Detection in Food Using AI,”IEEE,2024. 10.S.Kayalvizhi,”Detection of Unsafe Ingredients in Packaged Food,”IEEE,2023. 11.N.Prabha,”Nutriknow:AI-Based Ingredient Analyzer,”IJISRT,2025 12.S.Lodha,”Nutriscan:AI-Based Ingredient Detection and Evaluation,”IJERT,2025. 13.Y.Shah,”Nutrition Table and Ingredient Recognition Using Ai,”IJRASET,2025. 14.P,Ma et al.,”UMDFood:Vision-Language Models for Food Composition Compilation,”arXiv preprint arXiv:2306.01747,2023. 15.Bukya, Ravi, G. Madhu Mohan, and M. Kumar Swamy. “Artificial Intelligence role in optimizing electric vehicle charging patterns reduce costs and improve overall efficiency: A review.” Journal of Engineering, Management and Information Technology 2.3 (2024): 129-138. 16.R.L.Bailey,”ArtificialinNutritionResearch,”PNAS Nexus,2024

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close