The purpose of the work was the objective analysis of the cortical response signals after selective colour channel stimulation. Using the parameters of the visual evoked potential (VEP) we aimed to classify the separate colour channels as well as glaucoma patients and volunteers. On the basis of via the silent substitution technique (SST) flash stimulation, a selective S-cone stimulation and selective L- and M-cone stimulation was performed. 102 healthy subjects and 39 glaucoma patients were studied. The VEPs were recorded, pre-processed and analyzed. Based on the response signals, parameters were extracted. Using the parameters, a classification was done by the use of the binary logistic regression. The S-cone response and the LM-cone response could be differentiated with accuracy about 80%. Volunteers and glaucoma patients of the test group could be classified with overall accuracy of 85% at S-cone response and 76% at LM-cone response. The peak latency and reconstruction error seems to be a meaningful parameter for an effective classification. Good classification results could be achieved for the separate colour channels as well as for volunteers and glaucoma patients. The classification of glaucoma patients was clearly better by the use of the S-cone responses than by the use of LM-cone responses. Larger set of signals, especially from glaucoma patients, would probably improve the classification results.