Paper Info
Title
Towards robust and efficient segmentation: An approach based on inter-region contour and intra-region content analysis
Abstract
We address the problem of boundary estimation by formulating it as inter-region contour and intra-region information analysis in the framework of graph-based segmentation. Given an image without any prior information about object model and class, we seek to approximate one's instant perception of visual similarity. The method can serve as a preprocessing step for many higher level operations that require regional support, such as scene understanding and object recognition. We show in this paper that the defined region comparison predicate makes a better boundary estimator than efficient graph-based image segmentation (EGS) - a well known and widely used segmentation method. We further illustrate, by making a small relaxation, further improvement of segmentation performance can be achieved. Experimental results have demonstrated the effectiveness of our proposed method.
Year
DOI
Venue
2011
10.1109/ICME.2011.6012005
ICME
Keywords
Field
DocType
segmentation method,efficient graph-based image segmentation,intra-region information analysis,better boundary estimator,boundary estimation,efficient segmentation,inter-region contour,intra-region content analysis,object recognition,graph-based segmentation,segmentation performance,object model,image segmentation,content analysis,maximum likelihood estimation,information analysis,robustness,labeling,merging
Computer vision,Scale-space segmentation,Pattern recognition,Computer science,Segmentation,Object model,Segmentation-based object categorization,Robustness (computer science),Image segmentation,Preprocessor,Artificial intelligence,Cognitive neuroscience of visual object recognition
Conference
ISSN
Citations 
PageRank 
1945-7871
0
0.34
References 
Authors
8
6
Name
Order
Citations
PageRank
Zhiding Yu142130.08
Oscar C. Au21592176.54
Ketan Tang310612.98
Lingfeng Xu4539.81
Wenxiu Sun516020.79
Yuanfang Guo69518.21