The SCiO SDK supports identification of material by using two different models, Classification and Estimation.
Classification is the differentiation between categories, based on the spectral fingerprint of its components.
For example, if you were building your own app from this type of model, you could classify an apple from an orange, different types of pills, genuine leather vs. fake leather, and more.
Estimation works on a collection of samples which have a common numerical attribute, such as sugar content, fat content, hydration level of plants, and so on. Based on previously measured samples which have a full range of the target attribute, your users can scan their own sample and find out the value of the attribute of interest.