Multiscale principal components analysis for image local orientation estimation

Multiscale principal components analysis for image local orientation estimation
复制标题

DOI：
10.1109/acssc.2002.1197228
复制
发表时间：
2002-11
期刊：
Conference Record of the Thirty-Sixth Asilomar Conference on Signals, Systems and Computers, 2002.
影响因子：
--
通讯作者：
Xiaoguang Feng;P. Milanfar
Xiaoguang Feng;P. Milanfar
中科院分区：
其他
文献类型：
--
作者：
Xiaoguang Feng;P. Milanfar

文献摘要

被引文献

相似文献

本文提出了一种图像局部方向估计方法，该方法基于两种众所周知的技术的组合：主成分分析（PCA）和多尺度金字塔分解。应用 PCA 分析来查找局部方向的最大似然 (ML) 估计。所提出的技术被证明具有出色的抗噪声鲁棒性。我们提供了模拟和真实图像示例来演示所提出的技术。
This paper presents an image local orientation estimation method, which is based on a combination of two already well-known techniques: the principal component analysis (PCA) and the multiscale pyramid decomposition. The PCA analysis is applied to find the maximum likelihood (ML) estimate of the local orientation. The proposed technique is shown to enjoy excellent robustness against noise. We present both simulated and real image examples to demonstrate the proposed technique.