2013
DOI: 10.1109/tip.2012.2226044
|View full text |Cite
|
Sign up to set email alerts
|

Shape Sparse Representation for Joint Object Classification and Segmentation

Abstract: In this paper, a novel variational model based on prior shapes for simultaneous object classification and segmentation is proposed. Given a set of training shapes of multiple object classes, a sparse linear combination of training shapes in a low-dimensional representation is used to regularize the target shape in variational image segmentation. By minimizing the proposed variational functional, the model is able to automatically select the reference shapes that best represent the object by sparse recovery and… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
22
0

Year Published

2013
2013
2024
2024

Publication Types

Select...
3
3
1

Relationship

1
6

Authors

Journals

citations
Cited by 37 publications
(22 citation statements)
references
References 43 publications
0
22
0
Order By: Relevance
“…The complexity also grows. So the Sparse filtering [9], [10] method is used in our algorithm to extract the text from depth images.…”
Section: Machine Self Learningmentioning
confidence: 99%
“…The complexity also grows. So the Sparse filtering [9], [10] method is used in our algorithm to extract the text from depth images.…”
Section: Machine Self Learningmentioning
confidence: 99%
“…Here, we test our model with comparison to three recent methods: shape sparse representation [11], kernel density estimate of shape prior in variational segmentation based on shape probabilistic definition [8], kernel density estimate of shape prior for level set segmentation [6] as shown in Fig. 5.…”
Section: Test On Dataset Mpeg-7mentioning
confidence: 99%
“…Now, an extended training set that contains 302 shapes simultaneously encodes both walking directions. The binary shapes [11], and the corresponding shapes in (e). (f) Segmentation results by kernel density estimate of shape prior for variational segmentation based on shape probabilistic definition [8], and the corresponding shapes in (g).…”
Section: Track a Walking Personmentioning
confidence: 99%
See 2 more Smart Citations