A general framework for low level vision

A general framework for low level vision
复制标题

DOI:
10.1109/83.661181
复制
发表时间:
1998-03-01
影响因子:
10.6
通讯作者:
Malladi, R
Malladi, R
中科院分区:
计算机科学1区
文献类型:
--
作者:
Sochen, N;Kimmel, R;Malladi, R

文献摘要

被引文献

相似文献

我们引入了一个新的几何框架,在此基础上给出了图像尺度空间和增强的自然流动,我们将强度图像视为(XI)空间中的曲面,因此对于灰度图像而言,图像是三维空间中的二维曲面,对于彩色图像而言,是五维空间中的二维曲面。新的公式统一了许多经典的方案和算法,通过对强度对比度的简单缩放,产生了新的高效方案,多维信号的扩展变得自然,并导致了强大的去离子和尺度空间算法。
We introduce a new geometrical framework based on which natural flows for image scale space and enhancement are presented, We consider intensity images as surfaces in the (x.I) space, The image is, thereby, a two-dimensional (2-D) surface in three-dimensional (3-D) space for gray-level images, and 2-D surfaces in five dimensions for color images. The new formulation unifies many classical schemes and algorithms via a simple scaling of the intensity contrast, and results in new and efficient schemes, Extensions to multidimensional signals become natural and lead to powerful deionising and scale space algorithms.