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

arXiv: https://arxiv.org/abs/2507.14662 · HTML: https://mlsanity.com/paper/2507.14662/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 50 references that are in the map.
- First posted on arXiv 19 Jul 2025.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Effects of Image Size on Deep Learning](https://mlsanity.com/paper/2101.11508/) (2021)
- [Deep Learning and Machine Vision for Food Processing: A Survey](https://mlsanity.com/paper/2103.16106/) (2021)
- [Deep Learning for Classifying Food Waste](https://mlsanity.com/paper/2002.03786/) (2020)
- [Deep Learning based Food Instance Segmentation using Synthetic Data](https://mlsanity.com/paper/2107.07191/) (2021)
- [Computer Vision in the Food Industry: Accurate, Real-time, and Automatic Food Recognition with Pretrained MobileNetV2](https://mlsanity.com/paper/2405.11621/) (2024)
- [Calorie Counter: RGB-Depth Visual Estimation of Energy Expenditure at Home](https://mlsanity.com/paper/1607.08196/) (2016)
- [Enhanced Sentiment Analysis of Iranian Restaurant Reviews Utilizing Sentiment Intensity Analyzer & Fuzzy Logic](https://mlsanity.com/paper/2503.12141/) (2025)

## Abstract (arXiv)

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.