Saliency-based content-aware lifestyle image mosaics
Lists
Only you see this
Abstract
Highlights • We proposed a novel content-aware lifestyle image mosaic technique based on image saliency. • A novel energy map for variable-size tile decomposition is proposed by combining NIF and GBVS. • Saliency-weighted image retrieval is introduced to choose the tile images. • Seam carving is used to change the tile image’s aspect ratio to meet the tile. Abstract In this paper, a novel content-aware lifestyle image mosaic technique is proposed based on image saliency. The image saliency is used in the whole process of creating mosaics. Firstly, a novel energy map for variable-size tile decomposition is proposed by combining Neighborhood Inhomogeneity Factor and Graph-Based Visual Saliency. The target image is divided into small tiles with variable sizes based on the energy map. Secondly, saliency-weighted image retrieval is introduced to choose the tile images from a certain image database. Different aspect ratio between the tile and the corresponding tile image may lead to obvious distortion. Therefore, before filled into the tile, the chosen tile image is resized by seam carving to change its aspect ratio. At last, color correction is done on the mosaic result to improve the color similarity. Compared with other mosaic methods, the proposed technique creates much better mosaics in visual aspect.
BibTeX
@article{guo2015saliency,
author = {Dongyan Guo and Jinhui Tang and Ying Cui and Jundi Ding and Chunxia Zhao},
title = {{Saliency-based content-aware lifestyle image mosaics}},
journal = {J. Vis. Commun. Image Represent.},
year = {2015},
url = {https://openreview.net/forum?id=Z9DaZpR1Em1},
}Loading related content...