Skip to main content
. Author manuscript; available in PMC: 2018 Jun 1.
Published in final edited form as: J Raman Spectrosc. 2017 Apr 11;48(6):803–812. doi: 10.1002/jrs.5118

Figure 1.

Figure 1

Methodology implemented to quantify hyperspectral SRS images. In a first step, the data are characterized by unsupervised multivariate analysis based on vertex component analysis (VCA) k-means clustering analysis (KMCA). The outcome of the first step is used to train a random forests classifier, which is later used to describe the rest of the data set. The final labeled images are further used for quantification purposes.