The evaluation of optical properties of biological tissues has been pointed as an important tool for detection and diagnosis of tissue alterations. The Spatial Frequency Domain Imaging (SFDI) is a fast and non-invasive technique that provides quantitative information about light absorption and scattering properties in tissues from measurements of light diffuse reflectance. A fundamental step in this imaging technique is the proper correlation between the measured values of diffuse reflectance of light by the tissue, Rd, at different spatial frequencies and the corresponding pair of absorption and reduced scattering coefficients μ_a and μ_s^', respectively. In this work, the machine learning technique of Random Forests was applied to provide a regression model that efficiently computes μ_a and μ_s^' from Rd values. The database employed consisted of values of Rd at different spatial frequencies for different combinations of μ_a and μ_s^', obtained from Monte Carlo simulations. The database was splitted in training and testing groups, and a 3% Gaussian random noise was applied to the test group. Results showed that the correlation coefficient R2 between predicted and expected values from the test group were 0.96 and 0.97, for μ_a and μ_s^', respectively. The relative average errors for each coefficient were, respectively, 1% and 0.004%, with standard deviations of 11% and 7%. These results point to the good accuracy and precision of the models in predicting values of absorption and scattering coefficients. The developed models were applied to an in vivo study, where values of Rd from the dorsal region of the hand of a volunteer were obtained with an SFDI equipment using light wavelength of 650 nm. The obtained images of μ_a and μ_s^' showed enhanced contrast of blood vessels, pointing to the potential of the technique to identify vascular alterations that could be related to skin cancer.