File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Learning Compositional Shape Models of Multiple Distance Metrics by Information Projection

TitleLearning Compositional Shape Models of Multiple Distance Metrics by Information Projection
Authors
KeywordsShape analysis.
object detection
information projection
Compositional model
Issue Date2016
Citation
IEEE Transactions on Neural Networks and Learning Systems, 2016, v. 27, n. 7, p. 1417-1428 How to Cite?
Abstract© 2015 IEEE. This paper presents a novel compositional contour-based shape model by incorporating multiple distance metrics to account for varying shape distortions or deformations. Our approach contains two key steps: 1) contour feature generation and 2) generative model pursuit. For each category, we first densely sample an ensemble of local prototype contour segments from a few positive shape examples and describe each segment using three different types of distance metrics. These metrics are diverse and complementary with each other to capture various shape deformations. We regard the parameterized contour segment plus an additive residual ϵ as a basic subspace, namely, ϵ-ball, in the sense that it represents local shape variance under the certain distance metric. Using these ϵ-balls as features, we then propose a generative learning algorithm to pursue the compositional shape model, which greedily selects the most representative features under the information projection principle. In experiments, we evaluate our model on several public challenging data sets, and demonstrate that the integration of multiple shape distance metrics is capable of dealing various shape deformations, articulations, and background clutter, hence boosting system performance.
Persistent Identifierhttp://hdl.handle.net/10722/273535
ISSN
2023 Impact Factor: 10.2
2023 SCImago Journal Rankings: 4.170
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLuo, Ping-
dc.contributor.authorLin, Liang-
dc.contributor.authorLiu, Xiaobai-
dc.date.accessioned2019-08-12T09:55:52Z-
dc.date.available2019-08-12T09:55:52Z-
dc.date.issued2016-
dc.identifier.citationIEEE Transactions on Neural Networks and Learning Systems, 2016, v. 27, n. 7, p. 1417-1428-
dc.identifier.issn2162-237X-
dc.identifier.urihttp://hdl.handle.net/10722/273535-
dc.description.abstract© 2015 IEEE. This paper presents a novel compositional contour-based shape model by incorporating multiple distance metrics to account for varying shape distortions or deformations. Our approach contains two key steps: 1) contour feature generation and 2) generative model pursuit. For each category, we first densely sample an ensemble of local prototype contour segments from a few positive shape examples and describe each segment using three different types of distance metrics. These metrics are diverse and complementary with each other to capture various shape deformations. We regard the parameterized contour segment plus an additive residual ϵ as a basic subspace, namely, ϵ-ball, in the sense that it represents local shape variance under the certain distance metric. Using these ϵ-balls as features, we then propose a generative learning algorithm to pursue the compositional shape model, which greedily selects the most representative features under the information projection principle. In experiments, we evaluate our model on several public challenging data sets, and demonstrate that the integration of multiple shape distance metrics is capable of dealing various shape deformations, articulations, and background clutter, hence boosting system performance.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Neural Networks and Learning Systems-
dc.subjectShape analysis.-
dc.subjectobject detection-
dc.subjectinformation projection-
dc.subjectCompositional model-
dc.titleLearning Compositional Shape Models of Multiple Distance Metrics by Information Projection-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TNNLS.2015.2440430-
dc.identifier.scopuseid_2-s2.0-84931055720-
dc.identifier.volume27-
dc.identifier.issue7-
dc.identifier.spage1417-
dc.identifier.epage1428-
dc.identifier.eissn2162-2388-
dc.identifier.isiWOS:000379752400002-
dc.identifier.issnl2162-237X-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats