Graphical Models for Object Segmentation

نویسندگان

  • RUI HUANG
  • Rui Huang
  • Dimitris N. Metaxas
چکیده

OF THE DISSERTATION Graphical Models for Object Segmentation by Rui Huang Dissertation Director: Professor Dimitris N. Metaxas Object segmentation, a fundamental problem in computer vision, remains a challenging task after decades of research efforts. This task is made difficult by the intrinsic variability of the object’s shape, appearance, and its surrounding. It is compounded by the uncertainties arising from mapping the 3D world to the image plane and the noise in the acquisition systems. However, the human visual system often effectively entails the segmentation of the object from its background by fusing the bottom-up image cues with the top-down context. In this thesis we propose a novel probabilistic graphical modeling framework for object segmentation that effectively and flexibly fuses different sources of information, top and bottom, to produce highly accurate segmentation of objects in a computationally efficient manner. The main contributions of our work are: 1) We present a graphical model representing the relationship of the observed image features, the true region labels, and the underlying object contour based on the integration of Markov Random Fields (MRF) and deformable models. We propose two different solutions to this otherwise intractable joint region-contour inference and learning problem in the graphical model. 2) We introduce a Profile Hidden Markov Model (PHMM) built on the shape curvature sequence descriptor to improve the segmentation of specific objects. The special states and structure of PHMMs allow considerable shape contour perturbations and provide efficient inference and learning algorithms for shape modeling. Further embedding of the PHMM parameters captures the long term spatial dependencies on a shape profile, hence the global characteristics of a shape class.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

­­Image Segmentation using Gaussian Mixture Model

Abstract: Stochastic models such as mixture models, graphical models, Markov random fields and hidden Markov models have key role in probabilistic data analysis. In this paper, we used Gaussian mixture model to the pixels of an image. The parameters of the model were estimated by EM-algorithm.   In addition pixel labeling corresponded to each pixel of true image was made by Bayes rule. In fact,...

متن کامل

Video Image Segmentation with Graphical Models

Video image segmentation plays an important role in video processing and computer vision. This talk gives a brief introduction to some popular segmentation approaches based on the graphical models. A successful deterministic method maps the image segmentation into a minimum graph cut problem. Stochastic approaches are mainly based on the Gibbs sampler. We adopt the Potts model with external fie...

متن کامل

Segmentation Assisted Object Distinction for Direct Volume Rendering

Ray Casting is a direct volume rendering technique for visualizing 3D arrays of sampled data. It has vital applications in medical and biological imaging. Nevertheless, it is inherently open to cluttered classification results. It suffers from overlapping transfer function values and lacks a sufficiently powerful voxel parsing mechanism for object distinction. In this work, we are proposing an ...

متن کامل

Proposed Method for Image Segmentation Using Similarity Based Region Merging Techniques

Image Segmentation is a technique that partitioned the digital image into many number of homogeneous regions or sets of homogeneous pixels is called image segmentation. Efficient and effective image segmentation is an important task in computer vision and object recognition. Since fully automatic image segmentation is usually very hard for natural images, interactive schemes with a few simple u...

متن کامل

IMAGE SEGMENTATION USING GAUSSIAN MIXTURE MODEL

  Stochastic models such as mixture models, graphical models, Markov random fields and hidden Markov models have key role in probabilistic data analysis. In this paper, we have learned Gaussian mixture model to the pixels of an image. The parameters of the model have estimated by EM-algorithm.   In addition pixel labeling corresponded to each pixel of true image is made by Bayes rule. In fact, ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008