P300 speller systems represent one of the most basic applications of Brain-Computer Interfaces (BCIs). A traditional P300 speller consists of a 6 by 6 grid of characters in which each column or row in this grid intensifies at random. During such intensification process, the electroencephalography (EEG) data of the subject is recorded and analyzed to determine the character to be spelled. In this paper, we demonstrate how to improve on the traditional P300 speller by investigating the effects of incorporating different color luminance in the columns and rows of the speller’s grid-of-characters (i.e. red, green and blue) as opposed to the conventional one-color (i.e. gray-scale) luminance. In our analysis, we used the Emotiv Neuroheadset to record scalp EEG obtained from the frontal, parietal and occipital brain regions. We examine four different feature extraction techniques in addition to two classifiers, namely, Linear discriminant analysis (LDA) and linear Support vector machines (LSVM). Offline and online tests conducted on four subjects demonstrate a significant performance increase (up to 16%) for the intermixed color luminance case compared to the gray luminance one. These results indicate the efficacy of incorporating colors into P300 spellers interface.