Zoom-invariant vision of figural shape: The mathematics of cores
Zoom-invariant vision of figural shape: The mathematics of cores
复制标题
DOI：
10.1006/cviu.1997.0563
复制
发表时间：
1998-01-01
影响因子：
4.5
通讯作者：
Morse, BS
中科院分区：
文献类型：
--
作者：
Pizer, SM;Eberly, D;Morse, BS
认为图形缩放不变性和中间轨迹所隐含的跨图形边界连接是物体形状的重要方面，我们给出了直接从图像强度中提取中间轨迹的数学和算法，称为核心的中间轨迹被定义为尺度空间中的一种形式的中间信息的广义极大值，其不随平移、旋转，特别是缩放而变化，这些轨迹对图像干扰非常不敏感，这与以前已有的中间轨迹形成强烈对比，如一篇文章所示。布置了与核心相关的几何属性和图像对象表示，与前述不敏感性一起，允许核心有效地用于各种图像分析目标。(C)1998年学术出版社。
Believing that figural zoom invariance and the cross-figural boundary linking implied by medial loci are important aspects of object shape, we present the mathematics of and algorithms for the extraction of medial loci directly from image intensities, The medial loci called cores are defined as generalized maxima in scale space of a form of medial information that is invariant to translation, rotation, and, in particular, zoom, These loci are very insensitive to image disturbances, in strong contrast to previously available medial loci, as demonstrated in a companion paper. Core-related geometric properties and image object representations are laid out which, together with the aforementioned insensitivities, allow the core to be used effectively for a variety of image analysis objectives. (C) 1998 Academic Press.