Em mrf
Download
1 / 54

基于 EM 的 MRF 彩色图像分割 - PowerPoint PPT Presentation


  • 173 Views
  • Uploaded on

基于 EM 的 MRF 彩色图像分割. 李求旭. 领域系统和势团 Markov Random Fields Markov-Gibbs 等价性 有用的 MRF 模型 多级 GRF 模型和 MML 模型 MAP-MRF 标记 观察模型. 一个简单的例子:图像纹理分割 MRF 参数估计 基于 EM 和 MRF 的彩色图像分割 图像特征的提取 聚类的个数的分析. 领域系统和势团. Sites 和 Labels

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about ' 基于 EM 的 MRF 彩色图像分割' - charis


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
Em mrf

基于EM的MRF彩色图像分割

李求旭


  • 领域系统和势团

  • Markov Random Fields

  • Markov-Gibbs 等价性

  • 有用的MRF模型

  • 多级GRF模型和MML 模型

  • MAP-MRF标记

  • 观察模型



领域系统和势团

  • Sites 和 Labels

  • A labeling of the sites in S in terms of the labels in L: f = { }

  • Sites S= {1,…m}




Cliques
Cliques set L to each of the sites in S.

  • A cliquec for (S, N) is defined as a subset of sites in S .在c中所有的sites都是相邻的。

  • 对于(S,N)所有势团的集合是:


Markov random fields
Markov Random Fields set L to each of the sites in S.


Definition
Definition set L to each of the sites in S.


Markov gibbs
Markov-Gibbs set L to each of the sites in S.等价性(证明省略)

  • An MRF is characterized by its local property (the Markovianity)

  • GRF is characterized by its global property (the Gibbs distribution).

  • The Hammersley-Clifford theorem establishes the equivalence of these two types of properties


  • The theorem states that set L to each of the sites in S.F is an MRF on S with respect to N if and only if F is a GRF on S with respect to N


Gibbs random field definition
Gibbs Random Field set L to each of the sites in S.----definition

  • F is said to be a Gibbs Random Field on S with respect to N if and only if its configurations obey a Gibbs distribution:


有用的 set L to each of the sites in S.MRF模型

  • Auto-Models

  • auto-logistic model (Ising model)

  • auto-binomial model

  • auto-normal model(Gaussian MRF )

  • multi-level logistic (MLL) model (potts model)

  • Hierarchical GRF Model


Mll grf
MLL set L to each of the sites in S.模型和多级GRF模型

  • There are M (>2) discrete labels in the label set ,L={1,2,…,M}.


在多级两层 set L to each of the sites in S.Gibbs模型中:

  • The higher level Gibbs distribution uses an isotropic random field (MLL)

  • A lower level Gibbs distribution describes the filling-in in each region

  • 在纹理分割中:

    blob-like regions are modeled by a high level MRF which is an isotropic MLL

    these regions are filled in by patterns generated according to MRFs at the lower level


Map mrf
MAP-MRF set L to each of the sites in S.标记

  • 1.贝叶斯估计:

    估计 的贝叶斯风险被定义为:

    2. d:观察的数据

    C( , f)是费用函数

    p(f | d)is the posterior distribution


  • 费用函数: set L to each of the sites in S.

  • 根据(1),贝叶斯风险为:


  • 根据( set L to each of the sites in S.2)贝叶斯风险为:

  • where k is the volume of the space containing all points f for which



Map mrf approach for solving computer vision problems
MAP-MRF approach for solving computer vision problems : set L to each of the sites in S.

  • Pose a vision problem as one of labeling in categories LP1-LP4 and choose an appropriate MRF representation f.

  • Derive the posterior energy to define the MAP solution to a problem.

  • Find the MAP solution.


The process of deriving the posterior energy
The process of deriving the posterior energy set L to each of the sites in S.


观察模型 set L to each of the sites in S.


一个简单的例子:图像纹理分割 set L to each of the sites in S.

  • Texture segmentation is to segment an image into regions according to the textures of the regions

  • Texture segmentation, as other labeling problems, is usually performed in an optimization sense, such as MAP


MRF set L to each of the sites in S.参数估计

  • EM算法:一种迭代的标记-估计算法


Em mrf1
基于 set L to each of the sites in S.EM和MRF的彩色图像分割

  • 对图像中的每个像素,计算一个d维的特征向量X, X可以包含各种不同的颜色表示,以及一序列滤波器的输出。

  • 我们将图像模型表示如下:图像中的每个像素均是由g个图像分割中的某一个的密度函数计算得到的。因此为产生一个像素,首先选择一个图像分割区域,然后通过该区域的密度函数生成所需的像素


  • 我们希望确定以下参数: set L to each of the sites in S.

  • 1.每一个分割(块)的参数

  • 2.混合权重

  • 3.各个像素来源于模型中的哪个分量(从而实现图像分割)


  • 一个两难问题的提出: set L to each of the sites in S.

  • 1 . 如果我们已经知道了各个像素分别来源于哪个分量,那么确定参数将会变得容易

    2. 如果知道了参数, 那么对于每个像素,就能够确定最可能产生那个像素的分量(这样就确定了图像分割)

    3.但问题是两者都不知道。




  • EM technique for finding maximum likelihood (ML) estimates with 算法的主要思想是1.通过用期望值来替代丢失的(隐藏的)数据,为丢失的数据获取工作变量的集合2.接着将计算出的不完备数据的期望值代入到完备数据的似然函数中,用这个函数计算相对要简单一些3.然后最大化这个函数获得参数的值。

  • 这时不完备数据的期望值可能已经改变了。

  • 通过交替执行期望阶段和最大化阶段,迭代直致收敛


EM technique for finding maximum likelihood (ML) estimates with 算法的形式化描述

  • 1.使用不完备的数据以及参数的当前值来计算完备数据的期望值(E步)

  • 2.使用E步计算出的完备数据的期望值,最大化完备数据关于参数的对数似然函数(M步)。

  • 1,2步交替直到收敛。




Label process
Label process there were no missing data as it had been filled in by the expectations

  • The label process w is modeled as a MRF

    with respect to a second order neighborhood system


Image process
Image process there were no missing data as it had been filled in by the expectations

  • 多元高斯密度分布是一种典型的适合大多数分类问题的模型。其中,对于某个给定的类m,特征向量d是连续取值的。


Posterior energy
Posterior energy there were no missing data as it had been filled in by the expectations



EM there were no missing data as it had been filled in by the expectations 算法

  • 假设存在r个像素,丢失(隐藏)的数据形成一个r×L的数组表示的指示变量Z.

  • 在每一行,除了一个像素,其他的值均为0,这个值表示每个像素的特征向量来源于哪个块(分割)


图像特征的提取 there were no missing data as it had been filled in by the expectations

  • The brightness and texture features are extracted from the L* component and the color features are extracted from the a* and b* components.


  • two brightness features: brightness gradient and local energy content of the L* component; three color features: color gradient, local energy content of the a* and b* components;

  • three texture features: phase divergence, homogeneity and homogeneous intensity; and two position features(x,y) coordinates of the pixels


聚类的个数的分析 energy content of the L* component; three color features: color gradient, local energy content of the a* and b* components;

  • 基于直方图的聚类个数分析


  • thanks energy content of the L* component; three color features: color gradient, local energy content of the a* and b* components;


ad