Palettailor: Discriminable Colorization for Categorical Data

We present an integrated approach for creating and assigning color palettes to different visualizations such as multi-class scatterplots, line, bar charts. While other methods separate the creation of colors from their assignment, our takes data characteristics into account produce palettes, which are then assigned in a way that fosters better visual discrimination classes. To do so, we use customized optimization based on simulated annealing maximize combination three carefully designed scoring functions: point distinctness, name difference, discrimination. compare state-of-the-art with controlled user study scatterplots line charts, furthermore performed case study. Our results show Palettailor, fully-automated approach, generates higher quality than existing approaches. The efficiency allows us also incorporate modifications selection process.