MULTIRESOLUTION IMAGE FUSION GUIDED BY A MULTIMODAL SEGMENTATION
MULTIRESOLUTION IMAGE FUSION GUIDED BY A MULTIMODAL SEGMENTATION
复制标题
DOI：
--
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
G. Piella;H. Heijmans
中科院分区：
文献类型：
--
作者：
G. Piella;H. Heijmans
我们提出了一种多分辨率融合算法，它结合了区域和基于像素的融合方面。我们使用多分辨率分解来表示在不同尺度的输入图像，并引入多分辨率/多模态分割在这些尺度上划分图像域。然后，该分割用于指导后续的融合过程。基于区域的多分辨率方法使我们能够考虑低级别以及中间级别的结构，并施加数据依赖的一致性约束的基础上的空间，间和尺度内的依赖关系。
We present a multiresolution fusion algorithm which combines aspects of region and pixel-based fusion. We use multiresolution decompositions to represent the input images at different scales, and introduce a multiresolution/multimodal segmentation to partition the image domain at these scales. This segmentation is then used to guide the subsequent fusion process. A region-based multiresolution approach allows us to consider low-level as well as intermediate-level structures, and to impose data-dependent consistency constraints based on spatial, inter- and intra-scale dependencies.