Summary of Vision-based Approach For Food Weight Estimation From 2d Images, by Chathura Wimalasiri et al.
Vision-Based Approach for Food Weight Estimation from 2D Images
by Chathura Wimalasiri, Prasan Kumar Sahoo
First submitted to arxiv on: 26 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed vision-based approach uses 2D images to efficiently estimate food weight without physical contact. The method integrates deep learning and computer vision techniques, leveraging Faster R-CNN for food detection and MobileNetV3 for weight estimation. The system achieved a high mean average precision (83.41%), Intersection over Union (91.82%), and classification accuracy (100%). For weight estimation, the model demonstrated a low root mean squared error (6.3204), mean absolute percentage error (0.0640%), and high R-squared value (98.65%). The study highlights potential applications in healthcare for nutrition counseling, fitness and wellness for dietary intake assessment, and smart food storage solutions to reduce waste. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper presents a new way to estimate food weight using 2D images. It’s like taking a picture of your food instead of weighing it. The method uses special computer programs (Faster R-CNN and MobileNetV3) to detect the food and calculate its weight. The system is very accurate, making mistakes only about 6% of the time. This technology could be used in hospitals to help people plan their meals, or at home to track what you eat. It could even help reduce food waste by knowing how much food you have left. |
Keywords
» Artificial intelligence » Classification » Cnn » Deep learning » Mean average precision
