Joint segmentation and image interpretation
DSpace at IIT Bombay
View Archive InfoField | Value | |
Title |
Joint segmentation and image interpretation
|
|
Creator |
KUMAR, KS
DESAI, UB |
|
Subject |
image interpretation
scene understanding modular integration high-level vision multiresolution segmentation scene analysis joint segmentation and interpretation |
|
Description |
The problem of image interpretation is formulated in the framework of modular integration and multiresolution. The formulation essentially involves the concept of reductionism and multiresolution, where the image interpretation task is broken down into simpler subtasks of segmentation and interpretation. Moreover, instead of solving the vision task at the finest resolution Omega, we solve the synergetically coupled vision subtasks at coarser resolutions Omega - xi for Omega greater than or equal to xi > 0 and use the results obtained at resolution (Omega - xi) to solve the vision task at resolution (Omega - xi + 1). We present a solution to the joint segmentation and interpretation problem in the proposed framework. For the interpretation part we exploit the Markov random held (MRF) based image interpretation scheme developed by Modestino and Zhang [IEEE Trans Pattern Anal. Mach. Intell. pp. 606-615 (1992)]. Experimental results on both indoor and outdoor images are presented to Validate the proposed framework. (C) 1999 Pattern Recognition Society. . .
|
|
Publisher |
PERGAMON-ELSEVIER SCIENCE LTD
|
|
Date |
2011-08-25T10:18:45Z
2011-12-26T12:57:02Z 2011-12-27T05:46:44Z 2011-08-25T10:18:45Z 2011-12-26T12:57:02Z 2011-12-27T05:46:44Z 1999 |
|
Type |
Article
|
|
Identifier |
PATTERN RECOGNITION, 32(4), 577-589
0031-3203 http://dspace.library.iitb.ac.in/xmlui/handle/10054/10986 http://hdl.handle.net/10054/10986 |
|
Language |
en
|
|