Learning Deformable Shape Manifolds.

Learning Deformable Shape Manifolds.
复制标题

DOI:
10.1016/j.patcog.2011.09.023
复制
发表时间:
2012-04
影响因子:
8
通讯作者:
Martinez A
Martinez A
中科院分区:
计算机科学1区
文献类型:
--
作者:
Rivera S;Martinez A

文献摘要

参考文献

被引文献

相似文献

我们提出了一种通过流形学习与回归对图像中高度可变形形状进行形状检测的方法。我们的方法不需要在高对比度图像区域定义形状关键点,也不需要对形状进行初始估计。我们只需要足够多的代表性训练数据,以及对物体位置和比例的粗略初始估计。我们演示了人脸形状学习方法,并与非线性主动外观模型进行了比较。我们的方法非常精确,几乎达到了像素精度,并且能够准确检测出表情变化剧烈的人脸形状。该技术对眼镜等遮挡物具有很强的鲁棒性,并能在图像分辨率极度降低的情况下获得合理的结果。
We propose an approach to shape detection of highly deformable shapes in images via manifold learning with regression. Our method does not require shape key points be defined at high contrast image regions, nor do we need an initial estimate of the shape. We only require sufficient representative training data and a rough initial estimate of the object position and scale. We demonstrate the method for face shape learning, and provide a comparison to nonlinear Active Appearance Model. Our method is extremely accurate, to nearly pixel precision and is capable of accurately detecting the shape of faces undergoing extreme expression changes. The technique is robust to occlusions such as glasses and gives reasonable results for extremely degraded image resolutions.
DOI: 10.1109/34.368173
发表时间: 1995-02-01
影响因子: 23.6
作者:
MALLADI, R;SETHIAN, JA;VEMURI, BC
通讯作者: VEMURI, BC
DOI: 10.1109/tpami.2002.1008382
发表时间: 2002-06-01
影响因子: 23.6
作者:
Martínez, AM
通讯作者: Martínez, AM
DOI: 10.1109/tpami.2008.234
发表时间: 2009-11-01
影响因子: 23.6
作者:
Hamsici, Onur C.;Martinez, Aleix M.
通讯作者: Martinez, Aleix M.
DOI: 10.1109/tpami.2008.238
发表时间: 2009-11-01
影响因子: 23.6
作者:
Liu, Xiaoming
通讯作者: Liu, Xiaoming
DOI: 10.1007/bf00133570
发表时间: 1987-01-01
影响因子: 19.5
作者:
KASS, M;WITKIN, A;TERZOPOULOS, D
通讯作者: TERZOPOULOS, D