Visual nutrition analysis: leveraging segmentation and regression for food nutrient estimation
Yaping Zhao, Ping Zhu, Yizhang Jiang, Kaijian Xia · 2024
Read Visual nutrition analysis: leveraging segmentation and regression for food nutrient estimation by Yaping Zhao, Ping Zhu, Yizhang Jiang, Kaijian Xia (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11685081.txt.
Description
Yaping Zhao, Ping Zhu, Yizhang Jiang, and Kaijian Xia build a system that estimates the nutrition of a dish from its photo. Their 2024 paper notes that most people cannot judge the nutrient content of food by eye. Earlier image methods measured food volume and looked up nutrients by category, which drifts from the true values.
Their approach first segments the food regions, then regresses nutrient amounts directly. They hand-labeled segmentations on a public data set that already carried true nutrient labels. The staged design, outline first and amounts second, grounds predictions in measured references rather than category averages. A phone photo that yields protein, fat, and energy estimates could support diet tracking for chronic disease care.
Catalog record
| CREATOR | Yaping Zhao, Ping Zhu, Yizhang Jiang, Kaijian Xia |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |