Proceedings Ninth IEEE International Conference on Computer Vision 2003
DOI: 10.1109/iccv.2003.1238418
|View full text |Cite
|
Sign up to set email alerts
|

Texture segmentation by multiscale aggregation of filter responses and shape elements

Abstract: Abstract

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
132
0

Year Published

2005
2005
2020
2020

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 176 publications
(133 citation statements)
references
References 13 publications
1
132
0
Order By: Relevance
“…The computation of PES (i|Ref ) for every pixel i (where Ref is either S or S) involves finding a 'maximal region' R surrounding i which has similar regions elsewhere in Ref , i.e., a region R that maximizes (4). An image region R (of any shape or size) is represented by a dense and structured 'ensemble of patch descriptors' using a star-graph model.…”
Section: Our Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…The computation of PES (i|Ref ) for every pixel i (where Ref is either S or S) involves finding a 'maximal region' R surrounding i which has similar regions elsewhere in Ref , i.e., a region R that maximizes (4). An image region R (of any shape or size) is represented by a dense and structured 'ensemble of patch descriptors' using a star-graph model.…”
Section: Our Resultsmentioning
confidence: 99%
“…We continue to describe our figure-ground segmentation algorithm in Sec. 4. Experimental results are provided in Sec.…”
Section: Fig 3 Notationsmentioning
confidence: 99%
See 1 more Smart Citation
“…Its goal to segment an image into regions with each region solely containing object(s) of a class. As object segmentation requires that each segmented region to be a semantic object, it is much more challenging than traditionally object segmentation [1,2,3,4]. There has been a substantial amount of research on image segmentation including clustering based methods, region growing methods [5], histogram based methods [6], and more recent one such as adaptive thresh-hold methods [7], level set methods [8], graph based methods [4,9] etc.…”
Section: Introductionmentioning
confidence: 99%
“…This algorithm has been extended to also handle texture cues [7], although our implementation did not make use of these cues. Below we describe the main principles behind the SWA algorithm (Section 3.1) and how we combine motion with intensity cues in this framework (Section 3.2).…”
Section: Using Intensity Cuesmentioning
confidence: 99%