Share Email Print

Proceedings Paper

Automatic image style transfer using emotion-palette
Author(s): Jing Huang; Shizhe Zhou; Xianyi Zhu; Yiwen Li; Chengfeng Zhou
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Palette-based color editing can form an intuitive interface through which novices can perform interesting color modifications. However, because such modifications involve pixel-level operations, considerable labor is needed to accomplish an image’s emotion transformation. In this paper, we propose a novel color-transferring framework for image based on palettes to evoke different emotions. The purpose is to use the emotion-related color combinations to change the picture's original color palette to obtain stylized images. For an input image, the optimized k-medoids algorithm is used to create a set of the most representative color palettes. The system search for the best color combinations from a predefined database according to the color palette characteristics of the input image. Finally, using the selected emotion-palette we conduct a color transfer. The novel method can transfer a wide range of image into a new color style depicting the required emotional impact.

Paper Details

Date Published: 9 August 2018
PDF: 10 pages
Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 108064A (9 August 2018); doi: 10.1117/12.2502935
Show Author Affiliations
Jing Huang, Hunan Univ. (China)
Shizhe Zhou, Hunan Univ. (China)
Xianyi Zhu, Hunan Univ. (China)
Yiwen Li, Hunan Univ. (China)
Chengfeng Zhou, Hunan Univ. (China)

Published in SPIE Proceedings Vol. 10806:
Tenth International Conference on Digital Image Processing (ICDIP 2018)
Xudong Jiang; Jenq-Neng Hwang, Editor(s)

© SPIE. Terms of Use
Back to Top