Meera Patel, PhD
Senior Researcher, Computational Methods
Meera Patel's research sits between food science and computer vision. She studies how image-based dietary assessment systems handle portion ambiguity, mixed dishes, and cuisine distribution shift, and how those failure modes interact with downstream calorie and macronutrient estimation. PhD in Food Science with a minor in Computer Science.
Areas of work: Image-based dietary assessment; Portion estimation; Cuisine-level evaluation; Computer vision for food
Joined the Initiative: 2024-02
ORCID: 0000-0003-1148-6602
Publications
- Independent validation of six commercial AI-assisted dietary assessment applications against weighed-food reference: a 180-meal cross-sectional study (2026)
- Manual-entry food databases: a quality and provenance audit of five major consumer applications (2026)
- Mixed-dish portion estimation: the unsolved problem at the centre of consumer dietary assessment (2025)
- A protocol for weighed-food reference meal construction: scale calibration, ingredient decomposition, and ground-truth lookup (2025)
- Independent validation of image-based dietary assessment applications: a systematic review and meta-analysis (2018-2024) (2025)
- Cuisine and population coverage in image-based dietary assessment benchmarks: an analysis of 23 published evaluation sets (2025)
Preprints
- Within-application accuracy gaps between manual-entry and photo-based modes in a single dietary tracking application: a focused replication (2026)
- Cuisine distribution shift in photo-based dietary assessment: a re-analysis of three publicly described evaluation sets (2025)
Methodology briefs
- Cuisine stratification in evaluation sets: definitions, allocations, and minimum N for inference (2025)
- Kitchen-scale calibration for weighed-food reference protocols: a checklist (2025)