Example-Based Color Stylization of Images

Abstract

We describe a new computational approach to stylize the colors of an image by using a reference image. During processing, we take the characteristics of human color perception into account to generate more appealing results. Our system starts by classifying each pixel value into one of the basic color categories, derived from our psychophysical experiments. The basic color categories are perceptual categories that are universal to everyone, regardless of nationality or cultural background. These categories are used to provide restrictions on color transformations to avoid generating unnatural results. Our system then renders a new image by transferring colors from a reference image to the input image, based on these categorizations. To avoid artifacts due to the explicit clustering, our system defines fuzzy categorization when pseudocontours appear in the resulting image. We present a variety of results and show that our method performs a large, yet natural, color transformation without any sense of incongruity and that the resulting images automatically capture the characteristics of the colors used in the reference image.

Automated colour grading using colour distribution transfer

“…Another automated solution is to restrict the variability on the colour mapping. For example in [21,22], the pixels of both images are classified in a restricted set of basic colour categories, derived from psycho-physiological studies (red, blue, pink, etc.). The colour transfer ensures for instance that blue-ish pixels remain blue-ish pixels.…”

Color Improvement Based on Local Color Transfer in Digital Intermediate of Digital Cinema

“…It restricts the color transfer to a specific color category according to a given color. To categorize the colors, the Basic Color Terms (BCTs), which are black, white, red, green, yellow, blue, brown, purple, pink, orange, and gray, are adopted [11], [12]. A color-naming segmentation experiment was conducted for color categorization.…”

“…Yet, since a global color transfer method based on pixelwise matching lacks spatial information, significant spatial Copyright c 2015 The Institute of Electronics, Information and Communication Engineers artifacts are produced, such as local color distortion and gradient differences. Thus, Chang proposed an example-based color transfer method, which transfers color using linear mapping based on a basic convex hull in each color category [11], [12]. However, the color transfer is restricted to individual color categories.…”

Texture Transfer Based on Energy Minimization for Painterly Rendering

“…In Ref. [5], a target image is converted so that the image has colors that are used in a reference image. In the method, colors in target and reference images are classified into 11 basic ones according to the Basic Color Terms (BCTs) [4].…”

“…Although the combination of Refs. [13], [18], and [5] transfers both textures and colors, users have to prepare a pair of a photo and its converted image according to their preference.…”