A PLATFORM FOR REGION SPACE ANALYSIS IN BINARY PARTITION TREES
Author(s):
Huihai Lu,
John C. Woods,
Mohammed Ghanbari
Paper abstract: In this paper, we present a novel region-based image analysis platform. With a human in the loop, it provides an efficient method for object extraction, image segmentation, and filtering. The region space is organised into a Binary Partition Tree representation where small homogenous regions are successively merged. The hindsight of the merging process is therefore stored within the tree structure and the evolutions from the seed to root nodes are studied. By analysing these evolutions, discontinuities caused by the merging of heterogeneous regions are identified and the corresponding tree nodes short listed. These nodes indicate salient details within the image and from them tree simplification and region based filtering becomes possible. Given a simpler version of the original tree, manually assisted object extraction and image segmentation can be easily achieved and the experimental results show that our method facilitates the extraction of semantic content from the image.
Keywords:
Object extraction, image segmentation, image filtering, binary partition tree
Type:
Journal Paper
Full Contents (click to dowload):
First Page: 96
Last Page: 110
Year:
2007
Editors:
Pedro Isaías and Marcin Paprzycki
ISBN:
ISSN: 1646-3692
Language:
English
Conference Name:
IADIS International Journal on Computer Science and Information System
