Algorithmic colorways for graphic designs

Abstract

Color harmony is the aesthetically pleasing arrangement of colors within a composition. It is a fundamental concept in design, art and visual composition. It is important in fields such as graphic design, interior design, fashion, fine arts etc. Among the many approaches to the study of color harmony tried so far, a relatively recent method is to leverage the large number of human-created and ranked color palettes, such as those hosted at COLOURlovers.com. This study analyzes and utilizes these datasets in two ways – a statistical method and a geometrical model – to create new harmonious color combinations. Analysis of these large datasets could provide insights into the nature of color harmony, but is usually overwhelming because of the sheer number of slightly differing colors. This study discusses the possibility of quantizing the colors in these color palettes to a manageable set of discrete colors without significantly affecting the aesthetics of the palette, and then builds on this finding to apply an n-Gram method to create new harmonious color combinations. Considering the quantized colors as words and palettes as sentences, it was possible to use the n-Gram method to create new color combinations. In this study, we created bigrams and trigrams from the corpus of highly ranked quantized color palettes and used them to predict new color combinations. Further, a large number of palettes with five colors were observed in 3D in different color spaces. It was found that a significant number of such palettes fit a single pitch of a helix aligned along the lightness axis, but not centered at the origin of the a-b plane in CIELAB and OKLAB spaces. Considering the presence of an accent color, more than 50% of the highly ranked palettes studied fit the helical model. The helical model was then used to create new color combinations. In a survey, respondents were asked to like or dislike the patterns colored with color combinations created using the n-Gram method and the helical model. It was found that the new color combinations thus formed were almost as harmonious and pleasing as the originals.

Thus, this study establishes that the process of quantization of individual colors has minimal effect on the overall harmony perception of a color palette. Based on the quantization of colors, this study proposes an n-Gram method to create new harmonious color combinations. Additionally, by analyzing the large datasets, this study verifies that a significant number of highly ranked color palettes follow a helical pattern in CIELAB and OKLAB color spaces. This proposed geometrical model is then used to create new harmonious color palettes.