Food Recognition and Calorie Estimation Using YOLO

AI-Driven Smart Food Perception and Nutrition Assessment

Maintaining a healthy diet requires accurate knowledge of the food consumed and its nutritional value. However, manually identifying food items and estimating their calorie content can be difficult and time-consuming. This project, "AI-Driven Smart Food Perception and Nutrition Assessment," presents an intelligent system that automatically recognizes food items from images and provides an estimate of their calorie content using deep learning techniques. The proposed framework employs a Convolutional Neural Network (CNN) to learn visual features from food images and classify different food categories with high accuracy. Before model training, the dataset undergoes preprocessing steps such as image resizing, normalization, and shuffling to improve learning performance. After recognizing the food item, the system retrieves its nutritional information from a calorie database and calculates the estimated calorie intake. It also keeps track of the total calories consumed and the remaining daily calorie allowance, helping users monitor their eating habits. The developed application provides a simple graphical interface for food image upload, model prediction, and nutritional assessment. Overall, the proposed system offers an efficient and practical solution for supporting healthier food choices and improving daily dietary management.

A Confidence-Aware Hybrid Vision–Language Framework for Food Recognition and Nutritional Monitoring

Background/Objectives: The objective evaluation of regional dietary intake remains a core challenge in personalized health management due to complex plate presentations and a lack of culturally specific dataset benchmarks. Methods: This study introduces a confidence-aware hybrid vision–language framework engineered for traditional Turkish food recognition and structured nutritional assessment. Results: We curate a balanced dataset containing 14,711 verified images spanning 40 representative Turkish culinary classes to train and evaluate seven deep learning architectures. Among the visual models, EfficientNet V2-L achieved the highest standalone performance with an accuracy of 93.47%, 0.92 macro-precision, 0.92 macro-recall, and a 0.92 F1 score. To overcome visual ambiguity and automate content analysis, a confidence-aware routing strategy escalates uncertain predictions (τ<0.70) or user-rejected classifications to the Google Gemini 2.5 Flash multimodal large language model (MLLM). Conclusions: This hybrid paradigm yields a combined classification accuracy of 95.50% while validating portion weight estimations within a mean absolute error (MAE) of 18.42 g and total energy within 36.75 kcal. Fully realized as a cross-platform Flutter mobile application, the end-to-end pipeline demonstrates localized plate detection, adaptive portion analysis, and structured nutrient tracking, providing a scalable design for consumer-facing digital nutrition platforms.

AI-based Automated Food Recognition and Pay-As-You-Eat Billing System

The traditional billing and nutrition tracking method still dependent on manual observation processes, leading to inaccurate food billing, food wastage, nutritional imbalance and fraudulent activities during food scanning. Food analysis and secure billing are still difficult to accomplish in a large-scale tray assembly system, in a hospital, in an educational institution or in a smart food service area. The study introduces an innovative AI-powered Smart Food Tray Analysis and Billing System with Nutrition and Fraud Detection, leveraging deep learning, image processing, and intelligent analytics to facilitate automated food recognition and dietary assessment. The proposed system uses YOLO-based object detection and segmentation methods that are advanced to detect food items in the images of the tray and determine the size of the portions in real time. The system also includes anti-fraud features to deter invalid or obstructed scans and automatically creates billing, nutritional, and recommendations for users. Plus, there's an inventory forecast and analytics feature for smart resource management and forecasting. The outcomes of the system are expected to be accurate billing, reduced human intervention, an increased nutritional awareness, minimized food wastage, and increased operational efficiency in smart cafeteria environments. The proposed framework is designed to be scalable, secure, and intelligent, while also offering a solution that is applicable to the modern food service ecosystem.

CTNet: learning local details and global context for food recognition

Assessing Hospital Patient Nutrient Intake with an AI-Powered Food Recognition System – A Feasibility Study of the FlavoriaFlex solution

Adequate dietary intake is essential for positive clinical outcomes of hospitalized patients, yet monitoring food intake is labor-intensive and often subjective. AI-based food recognition could automate monitoring and assessment, but evidence in real-world hospital settings is limited. This study evaluated an AI-powered food recognition system, FlavoriaFlex, to assess its detection performance, deployment feasibility, and acceptability among dietitians. Previously validated in restaurant (F1 0.75, weight MAE 23.6 g, energy MAE 235 kcal), the system was deployed in a hospital ward for six days. A total of 133 meals were recorded; 102 had paired leftover images (235 total images). Manual annotation of 483 food segments provided ground truth for evaluating food recognition and menu mapping. Semi-structured interviews with dietitians assessed usability, perceived benefits, and clinical value. FlavoriaFlex enabled automatic estimation of item- and meal-level consumption, including weights and energy- and macronutrient contents. Overall food recognition accuracy was 94% (F1 0.76), remaining high for served meals (96.5%, F1 0.85) and robust for visually complex leftovers (89.5%, F1 0.71). Unknown/non-food segments were minimal (2.4% of leftovers; 0.27% of weight). A web dashboard delivered real-time visualizations, including energy and nutrient intake. Dietitians reported reduced cognitive burden, more objective assessment, and improved observability into patient dietary intake, while emphasizing the need for further validation and integration for clinical use. These findings demonstrate that FlavoriaFlex could be integrated into hospital workflows to provide accurate, clinically meaningful intake estimates, with AI-assisted food recognition offering an efficient, reliable approach to improving nutritional monitoring at scale.

Multi-Scale Alcohol Consumption Behavior Detection from Wearable AI

Wearable sensor-based alcohol detection requires methods that are aligned with the available label structure, sensing modality, and temporal scale. This paper presents a comparative study across two alcohol sensing settings. The first setting uses the Bar Crawl dataset, where smartphone accelerometer data must be interpreted with delayed transdermal alcohol concentration (TAC) measurements. To address this weak supervision, we apply a backward-search framework anchored on TAC rise and prior motion activity. Candidate motion episodes were identified 35-37 minutes before TAC rise in observable cases, while sedentary behavior and limited observability explained non-detected cases. The second setting uses a wrist-worn IMU drinking gesture dataset with explicit gesture annotations under leave-one-subjectout (LOSO) evaluation. Among six models (LR, RF, SVM, XGB, LGBM, and 1D-CNN), LGBM achieved the best semi-controlled DX-I performance (F1=0.699), while RF achieved the best freeliving DX-II baseline performance $(\mathbf{F} \mathbf{1} \boldsymbol{=} \mathbf{0. 3 8 0})$. The results show that label structure, class imbalance, and evaluation protocol strongly influence valid methodology, reported performance, and generalizability in wearable alcohol sensing.