Shape Matching Using Multiscale Integral Invariants

Shape Matching Using Multiscale Integral Invariants
复制标题

DOI:
10.1109/tpami.2014.2342215
复制
发表时间:
2015-01-01
影响因子:
23.6
通讯作者:
Soatto, Stefano
Soatto, Stefano
中科院分区:
计算机科学1区
文献类型:
--
作者:
Hong, Byung-Woo;Soatto, Stefano

文献摘要

被引文献

相似文献

提出了一种基于积分核的形状描述子。形状以隐式形式表示,其特征在于由一系列各向同性核提供所需的不变性。形状特征在多个尺度下被表征,其形成签名,该签名是在尺度范围上的形状的紧凑描述。形状签名被设计为相对于包括平移、旋转、缩放和反射的组变换是不变的。此外,表征局部形状几何形状的积分核使得形状签名相对于不期望的扰动是鲁棒的,同时保持辨别能力。使用我们的形状签名证明了形状匹配的基础上,一些合成和真实的例子。
We present a shape descriptor based on integral kernels. Shape is represented in an implicit form and it is characterized by a series of isotropic kernels that provide desirable invariance properties. The shape features are characterized at multiple scales which form a signature that is a compact description of shape over a range of scales. The shape signature is designed to be invariant with respect to group transformations which include translation, rotation, scaling, and reflection. In addition, the integral kernels that characterize local shape geometry enable the shape signature to be robust with respect to undesirable perturbations while retaining discriminative power. Use of our shape signature is demonstrated for shape matching based on a number of synthetic and real examples.