A major promise of Raman microscopy is the label-free detailed recognition of cellular and subcellular structures. To this end, identifying colocalization patterns between Raman spectral images and fluorescence microscopic images is a key step to annotate subcellular components in Raman spectroscopic images. While existing approaches to resolve subcellular structures are based on fluorescence labeling, we propose a combination of a colocalization scheme with subsequent training of a supervised classifier that allows label-free resolution of cellular compartments. Our colocalization scheme unveils statistically significant overlapping regions by identifying correlation between the fluorescence color channels and clusters from unsupervised machine learning methods like hierarchical cluster analysis. The colocalization scheme is used as a pre-selection to gather appropriate spectra as training data. These spectra are used in the second part as training data to establish a supervised random forest classifier to automatically identify lipid droplets and nucleus. We validate our approach by examining Raman spectral images overlaid with fluorescence labelings of different cellular compartments, indicating that specific components may indeed be identified label-free in the spectral image. A Matlab implementation of our colocalization software is available at .