Artificial Intelligence in the Food Industry: Food Waste Estimation based on Computer Vision, a Brief Case Study in a University Dining Hall

2025-07-19

AI Summary

This study addresses the challenge of quantifying post-consumption food waste in university canteens. We propose a non-contact, low-cost monitoring framework based on RGB image semantic segmentation. Methodologically, we construct a dataset comprising pre- and post-meal images of five Iranian dishes, introduce the Distribution Pixel Agreement (DPA) metric to evaluate segmentation accuracy under diverse food morphologies, and employ lightweight U-Net variants trained with dynamic inverse-frequency loss and AdamW optimization on an NVIDIA T4 GPU for real-time inference. Key contributions include: (i) the first proposal of DPA—designed to accommodate heterogeneous food textures and structures; (ii) empirical validation of lightweight models’ robustness and real-time performance (≥30 FPS) across multi-dish scenarios; and (iii) DPA scores exceeding 90% for dry, rigid foods (e.g., rice, fries). The framework establishes a scalable, automated, and continuous monitoring paradigm for institutional food waste, enabling data-driven sustainable dietary management.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Quantifying post-consumer food waste in institutional dining settings is essential for supporting data-driven sustainability strategies. This study presents a cost-effective computer vision framework that estimates plate-level food waste by utilizing semantic segmentation of RGB images taken before and after meal consumption across five Iranian dishes. Four fully supervised models (U-Net, U-Net++, and their lightweight variants) were trained using a capped dynamic inverse-frequency loss and AdamW optimizer, then evaluated through a comprehensive set of metrics, including Pixel Accuracy, Dice, IoU, and a custom-defined Distributional Pixel Agreement (DPA) metric tailored to the task. All models achieved satisfying performance, and for each food type, at least one model approached or surpassed 90% DPA, demonstrating strong alignment in pixel-wise proportion estimates. Lighter models with reduced parameter counts offered faster inference, achieving real-time throughput on an NVIDIA T4 GPU. Further analysis showed superior segmentation performance for dry and more rigid components (e.g., rice and fries), while more complex, fragmented, or viscous dishes, such as stews, showed reduced performance, specifically post-consumption. Despite limitations such as reliance on 2D imaging, constrained food variety, and manual data collection, the proposed framework is pioneering and represents a scalable, contactless solution for continuous monitoring of food consumption. This research lays foundational groundwork for automated, real-time waste tracking systems in large-scale food service environments and offers actionable insights and outlines feasible future directions for dining hall management and policymakers aiming to reduce institutional food waste.

Problem

• Estimating plate-level food waste using computer vision
• Developing scalable real-time waste tracking systems
• Addressing limitations in segmentation for complex dishes

Innovation

• Computer vision estimates plate-level food waste
• Semantic segmentation with U-Net variants
• Real-time throughput on NVIDIA T4 GPU