标题: 具形状感知的影像缩放技术
Shape Aware Image Resizing
作者: 李宜珊
Li, Yi-Shan
庄荣宏
王昱舜
Chuang, Jung-Hong
Wang, Yu-Shuen
多媒体工程研究所
关键字: 影像缩放;形状感知;影像形变;最佳化;image resizing;shape aware;image warping;optimization
公开日期: 2011
摘要: 过去以内容感知为依据的影像缩放技术皆依赖显着性区域侦测找出人眼视觉上重要的区域,并以此做为维持影像内容的重要度依据。然而,视觉上重要的区域并不代表是最需要被精确维持的。在本篇论文,我们利用影像中重要的轮廓结构来引导整个影像缩放的流程。首先,我们使用一个影像分割技术撷取影像中的重要轮廓结构。接着用一个包含轮廓结构资讯的三角形网格来表示这张影像。我们对这个网格做变形,基于以下几个条件限制:用来维持曲线形状的条件,平滑整个网格变形变化的条件,以及一个处理三角形翻转问题的条件。以上的限制条件可以使用最小平方法快速求解。实验结果证明我们的方法能产生合理的结果,且能极佳的维持影像内部结构。
Previous content-aware image resizing methods typically account for a saliency map to determine the visually importance of the content and uses the saliency value as a measure of preservation strength. However, it is observed that a visually salient region does not imply the region needs precise preservation. In this thesis, we use the global structure of an image, which is composed of the strong edges of the image, to guide the resizing steps. A powerful image segmentation scheme [1] is first employed to extract the global structure. The image is represented as a triangular mesh that fits the global structure. We deform the mesh with several constraints: curve constraints are used to preserve the shape of the curve, a smoothness constraint is used to smooth the deformation, and a foldover constraint is used to prevent the triangle foldover. The above constraints can be efficiently solved in the linear least-squares sense, and the experiments show that our method can produce convincing results and maintain the overall structure well.
URI: http://140.113.39.130/cdrfb3/record/nctu/#GT079857504
http://hdl.handle.net/11536/48425
显示于类别:Thesis


文件中的档案:

  1. 750401.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.