An integrated approach for scene understanding based on Markov Random Field model

Kim, Il Y.; Yang, Hyun Seung

doi:10.1016/0031-3203(95)00061-5

Cited by 11 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Sonka et al (1993) use a genetic algorithm to produce optimal image interpretations, they integrate segmentation and interpretation into a single feedback process that incorporates contextual knowledge. More recently, Kim & Yang (1995) integrate segmentation and interpretation by forming a combined weighted energy function; the segmentation block is weighted high initially and then as the algorithm iterates the weights shift from the segmentation block to the interpretation block.…”

Section: Joint Segmentation and Image Interpretationmentioning

confidence: 99%

A modular integration and multiresolution framework for image interpretation

Kumar

Desai

1998

Sadhana

View full text Add to dashboard Cite

In this paper, we give a generalized formulation for a vision problem in the framework of modular integration and multiresolution. The developed framework is used to solve the high-level vision problem of scene interpretation. The formulation essentially involves the concept of reductionism and multiresolution, where the given vision task 12 is broken down into simpler subtasks)21,1;2 ..... Vm. Moreover, instead of solving the vision task ~ = 1,' at the finest resolution f2, we solve the synergetically coupled vision subtasks at coarser resolutions l; f2-N for f2 > N > 0 and use the results obtained at resolution (~-N) to solve V ~-N+l, the vision task at resolution (S2-N + 1). Image interpretation is a two-phased analysis problem where some salient features or objects in an image are identified by segmenting the image and the objects in the segmented image are interpreted based on their spatial relationships. We present a solution to the joint segmentation and interpretation problem in the proposed generalized framework. For the interpretation part we exploit the Markov Random Field (MRF) based image interpretation scheme developed by Modestino and Zhang. Experimental results on both indoor and outdoor images are presented to validate the proposed framework.

show abstract

Section: Joint Segmentation and Image Interpretationmentioning

confidence: 99%

A modular integration and multiresolution framework for image interpretation

Kumar

Desai

1998

Sadhana

View full text Add to dashboard Cite

show abstract

“…Os modelos MRF têm sido utilizados em aplicações de processamento de imagem de baixo nível, tais como segmentação e restauração de imagem ( [4]). No entanto, recentemente vem sendo utilizado em tarefas de análise de imagem de alto nível ( [6], [7], [8], [1], [9]). A análise de imagem usando MRF e formulada como um problema de estimação do maximum a posteriori (MAP).…”

Section: Introductionunclassified

Campos Aleatórios de Markov uma Abordagem para Caracterização Extração de Contornos de Telhados

Galvanin¹,

Póz²

2009

TEMA - Tendências Em Matemática Aplicada E Computacional

View full text Add to dashboard Cite

“…Image segmentation is the first stage of processing in many practical computer vision systems. Applications include image interpretation [9,4] and searching image databases by content [2]. Over the last few decades many segmentation algorithms have been developed, with the number growing steadily every year.…”

Section: Introductionmentioning

confidence: 99%

Evaluating image segmentation algorithms using monotonic hulls in fitness/cost space

Everingham

Muller²,

Thomas³

2001

Procedings of the British Machine Vision Conference 2001

View full text Add to dashboard Cite

Image segmentation is the first stage of processing in many practical computer vision systems. While development of particular segmentation algorithms has attracted considerable research interest, relatively little work has been published on the subject of their evaluation. In this paper we propose a framework for quantitative evaluation of segmentation algorithms which we believe addresses shortcomings of previous approaches, and use this framework to compare several state-of-the-art algorithms.

show abstract

An integrated approach for scene understanding based on Markov Random Field model

Cited by 11 publications

References 12 publications

A modular integration and multiresolution framework for image interpretation

A modular integration and multiresolution framework for image interpretation

Campos Aleatórios de Markov uma Abordagem para Caracterização Extração de Contornos de Telhados

Evaluating image segmentation algorithms using monotonic hulls in fitness/cost space

Contact Info

Product

Resources

About