Equivalent contraction kernels to build dual irregular pyramids
Equivalent contraction kernels to build dual irregular pyramids
复制标题
构建双不规则金字塔的等效收缩核
DOI：
--
复制
发表时间：
1996
期刊：
影响因子：
--
通讯作者：
W. Kropatsch
中科院分区：
文献类型：
--
作者：
W. Kropatsch
原始数字图像由像素的2D空间排列组成，每个像素都是通过测量图像平面特定位置处的光而产生的。目前大多数人工传感器（例如CCD相机）具有正交网格的刚性结构，而大多数自然视觉系统基于传感器的非规则布置[1]。虽然阵列在技术上更容易管理，但拓扑关系似乎在自然系统中的视觉任务中扮演着比精确几何位置更重要的角色。
A raw digital image consists of a 2D spatial arragement of pixels each of which results from measuring the light at a specific location of the image plane. Currently most of the artificial sensors (e.g. CCD cameras) have the rigid structure of an orthogonal grid, whereas most natural vision systems are based on non-regular arrangements of sensors [1]. Although arrays are certainly easier to manage technically, topological relations seem to play an even more important role for vision tasks in natural systems than precise geometrical positions.