Results 1 
6 of
6
Image Segmentation from Consensus Information
 Computer Vision and Image Understanding
, 1997
"... A new approach toward image segmentation is proposed. A set of slightly different segmentations are derived from the same input and the final result is based on the consensus among them. The perturbations are introduced by exploiting the probabilistic component of a region adjacency graph (RAG) pyra ..."
Abstract

Cited by 31 (4 self)
 Add to MetaCart
(Show Context)
A new approach toward image segmentation is proposed. A set of slightly different segmentations are derived from the same input and the final result is based on the consensus among them. The perturbations are introduced by exploiting the probabilistic component of a region adjacency graph (RAG) pyramid based segmentation. From the set of initial segmentations the cooccurrence probability field is obtained in which global information about the delineated regions becomes locally available. The final segmentation is based on this field and is obtained with the same hierarchical, RAG pyramid technique. No user set parameters or context dependent thresholds are required. Keywords: Image Segmentation, Integration of Modules, LowLevel Processing. 3 Current address: Open Solution Center, Samsung Data System, 2191 MigunDong, SeodaemunGu, Seoul, Korea. 1 Introduction In image segmentation, given a homogeneity criterion, the image must be partitioned into regions within which the criterio...
An objectivebased framework for motion planning under sensing and control uncertainties
 International Journal of Robotics Research
, 1998
"... ..."
(Show Context)
Methods for Numerical Integration of HighDimensional Posterior Densities with Application to Statistical Image Models
"... Numerical computation with Bayesian posterior densities has recently received much attention both in the applied statistics and image processing communities. This paper surveys previous literature and presents new, efficient methods for computing marginal density values for image models that have ..."
Abstract

Cited by 5 (4 self)
 Add to MetaCart
(Show Context)
Numerical computation with Bayesian posterior densities has recently received much attention both in the applied statistics and image processing communities. This paper surveys previous literature and presents new, efficient methods for computing marginal density values for image models that have been widely considered in computer vision and image processing. The particular models chosen are a Markov random field formulation, implicit polynomial surface models, and parametric polynomial surface models. The computations can be used to make a variety of statisticallybased decisions, such as assessing region homogeneity for segmentation, or performing model selection. Detailed descriptions of the methods are provided, along with demonstrative experiments on real imagery.
Textured Image Segmentation: Returning Multiple Solutions
 Image and Vision Computing
, 1997
"... Traditionally, the goal of image segmentation has been to produce a single partition of an image. This partition is compared to some "ground truth," or human approved partition, to evaluate the performance of the algorithm. This paper utilizes a framework for considering a range of possibl ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Traditionally, the goal of image segmentation has been to produce a single partition of an image. This partition is compared to some "ground truth," or human approved partition, to evaluate the performance of the algorithm. This paper utilizes a framework for considering a range of possible partitions of the image to compute a probability distribution on the space of possible partitions of the image. This is an important distinction from the traditional model of segmentation, and has many implications in the integration of segmentation and recognition research. The probabilistic framework that enables us to return a confidence measure on each result also allows us to discard from consideration entire classes of results due to their low cumulative probability. The distributions thus returned may be passed to higherlevel algorithms to better enable them to interpret the segmentation results. Several experimental results are presented using Markov random fields as texture models to genera...
Textured Image Segmentation Using Markov Random Fields: Returning Multiple Solutions
, 1996
"... Traditionally, the goal of image segmentation is to produce a single partition of an image. This partition is then compared to some "ground truth," or human approved partition, to evaluate the performance of the algorithm. This thesis utilizes a framework for considering a range of possibl ..."
Abstract
 Add to MetaCart
(Show Context)
Traditionally, the goal of image segmentation is to produce a single partition of an image. This partition is then compared to some "ground truth," or human approved partition, to evaluate the performance of the algorithm. This thesis utilizes a framework for considering a range of possible partitions of the image to compute a distribution of possible partitions of the image. This is an important distinction from the traditional model of segmentation, and has many implications in the integration of segmentation and recognition research. The probabilistic framework that enables us to return a confidence measure on each result also allows us to discard from consideration entire classes of results due to their low cumulative probability. Several experimental results are presented using Markov random fields as texture models to generate distributions of segments and segmentations on textured images. Both simple, homogeneous images and natural scenes are presented. iii Dedicated to my par...
Computer Vision And Image Understanding
"... this paper is an effective way to obtain these quantitative measures. The differences in the initial segmentations are more significant for image parts where the The house image (Fig. 18d) is representative of the class employed homogeneity criterion is not adequate. These of outdoor scenes often us ..."
Abstract
 Add to MetaCart
this paper is an effective way to obtain these quantitative measures. The differences in the initial segmentations are more significant for image parts where the The house image (Fig. 18d) is representative of the class employed homogeneity criterion is not adequate. These of outdoor scenes often used in segmentation papers. The differences yield small cooccurrence probabilities and presence of textured areas (trees, bushes, grass) challenges therefore can prevent undersegmentation