Our great sponsors
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
You don't need any "contact measurement" or any magic "near infra-red specroscopy" nonsense. Just pictures of things in a specific location. Image Classification is not magic - and is only getting easier as time goes on as more and more tools are developed for building them. Heck, if you have a webcam you could build a classifier yourself with Microsoft's Lobe in half an hour that can tell an apple from a banana.
Checking the Vision API docs, if you want to "Classify images using custom labels " (probably what you'd want to get food specific labels beyond what the Vision API already has predefined), you need to use AutoML. I guess you might get away with the predefined labels!