Dental caries is the most common oral disease that causes demineralization of the enamel and later of the dentin. Depth-wise assessment of the demineralization process could be used to help in treatment planning. In this study, we aimed to provide baseline information for the development of a Raman probe by characterizing the mineral composition of the dental tissues from large composition maps (6 × 3 mm2 with 15 μm step size) using Raman microspectroscopy. Ten human wisdom teeth with different stages of dental caries lesions were examined. All of the teeth were cut in half at representative locations of the caries lesions and then imaged with a Raman imaging microscope. The pre-processed spectral maps were combined into a single data matrix, and the spectra of the enamel, dentin, and caries were identified by K-means cluster analysis. Our results showed that unsupervised identification of dental caries is possible with the K-means clustering. The compositional analysis revealed that the carious lesions are less mineralized than the healthy enamel, and when the lesions extend into the dentin, they are even less mineralized. Furthermore, there were more carbonate imperfections in the mineral crystal lattice of the caries tissues than in healthy tissues. Interestingly, we observed gradients in the sound enamel showing higher mineralization and greater mineral crystal perfection towards the tooth surface. To conclude, our results provide a baseline for the methodological development aimed at clinical diagnostics for the early detection of active caries lesions.