Automatic Palette Extraction for Image Editing

Abstract

Interactive palette based colour editing applications have grown in popularity in recent years, but while many methods propose fast palette extraction techniques, they typically rely on the user to define the number of colours needed. In this paper, we present an approach that extracts a small set of representative colours from an image automatically, determining the optimal palette size without user interaction. Our iterative technique assigns a vote to each pixel in the image based on how close they are in colour space to the colours already in the palette. We use a histogram to divide the colours into bins and determine which colour occurs most frequently in the image but is far away from all of the palette colours, and we add this colour to the palette. This process continues until all pixels in the image are well represented by the palette. Comparisons with existing methods show that our colour palettes compare well to other state of the art techniques, while also computing the optimal number of colours automatically at interactive speeds. In addition, we showcase how our colour palette performs when used in image editing applications such as colour transfer and layer decomposition.