Terahertz time-domain spectroscopy is a useful technique to determine some physical characteristics of materials, which is based on the selective frequency absorption of a broad-spectrum electromagnetic pulse. In order to investigate the potential of this technology to classify maturity states of Gruyere-type cheese, terahertz spectra (0.5-10 THz) of 4 samples of cheese made in the livestock area of Cajamarca - Peru were examined during 60 days. The acquired data matrices were analyzed with the application of MATLAB 2019b where absorbance curves were obtained and maturity states were classified by testing 24 classifier models, achieving differences of around 90%, obtained by the Gaussian SVM Algorithm Model with a 0.35 Kernel Scale and a multiclass method one vs one. It was concluded that the combined processing and classification of images obtained from Terahertz time-domain spectroscopy and the use of machine learning algorithms can be used to classify the different maturity states of cheeses.