Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6865142 | Neurocomputing | 2018 | 8 Pages |
Abstract
Extracting color themes from an image is to get a color palette that consists of dominant colors of the image. In this article, we construct a color network to build the intrinsic connections of color information of pixels. By applying improved linear iterative clustering (SLIC) algorithm [1], [2], we obtain initial color themes. In the following stage, with learning from human-extract color themes, we can get the final sorted color themes result. Experimental results demonstrate that our model outperforms previous approaches in terms of the number of themes, span and accuracy.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Zunlei Feng, Wolong Yuan, Chunli Fu, Jie Lei, Mingli Song,