Matches in SemOpenAlex for { <https://semopenalex.org/work/W1586388615> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W1586388615 endingPage "226" @default.
- W1586388615 startingPage "215" @default.
- W1586388615 abstract "AbstractScene categorization plays an important role in computer vision, image content understanding, and image retrieval. In this paper, back-propagation neural network (BPN) is served as the basic classifier for multi-class scene/image categorization. Four features, namely, SPM (spatial pyramid appearance descriptor represented by scale invariant feature transform), PHOG (pyramid histogram of oriented gradient), GIST, and HWVP (hierarchical wavelet packet transform) are selected as the basic inputs of BPNs. They are the appearance, shape and texture descriptors respectively. For an M (M>2) classes scene categorization problem, we cascade M one-versus-all BPNs to determine the accurate label of an image. An offline multi-class Adaboost algorithm is proposed to fuse multiple BPN classifiers trained with complementary features to improve scene categorization performance. Experimental results on the widely used Scene-13 and Sport Event datasets show the effectiveness of the proposed boosted BPN based scene categorization approach. Scene categorization performances of BPN classifiers with input features: SPM, PHOG, GIST and HWVP, boosted BPN classifiers of each of the four features, and the boosted classifiers of all the four features are given. Relationships of boosted classifiers number and the scene categorization performance are also discussed. Comparisons with some existing scene categorization methods using the authors’ datasets further show effectiveness of the proposed boosted BPN based approach.KeywordsScene Categorizationback-propagation neural networkadaboost" @default.
- W1586388615 created "2016-06-24" @default.
- W1586388615 creator A5010841617 @default.
- W1586388615 creator A5011451275 @default.
- W1586388615 creator A5014825654 @default.
- W1586388615 creator A5040009629 @default.
- W1586388615 creator A5062632609 @default.
- W1586388615 creator A5071277762 @default.
- W1586388615 creator A5074574647 @default.
- W1586388615 date "2010-01-01" @default.
- W1586388615 modified "2023-09-24" @default.
- W1586388615 title "Scene Categorization Using Boosted Back-Propagation Neural Networks" @default.
- W1586388615 cites W1566135517 @default.
- W1586388615 cites W2063867591 @default.
- W1586388615 cites W2102680763 @default.
- W1586388615 cites W2112020727 @default.
- W1586388615 cites W2113656553 @default.
- W1586388615 cites W2123241287 @default.
- W1586388615 cites W2125574651 @default.
- W1586388615 cites W2128554449 @default.
- W1586388615 cites W2129004009 @default.
- W1586388615 cites W2147625498 @default.
- W1586388615 cites W2150692003 @default.
- W1586388615 cites W2151103935 @default.
- W1586388615 cites W2151632536 @default.
- W1586388615 cites W2154610165 @default.
- W1586388615 cites W2154683974 @default.
- W1586388615 cites W2156344194 @default.
- W1586388615 cites W2158266063 @default.
- W1586388615 cites W2160254296 @default.
- W1586388615 cites W2162915993 @default.
- W1586388615 cites W2163766261 @default.
- W1586388615 cites W2165828254 @default.
- W1586388615 doi "https://doi.org/10.1007/978-3-642-15702-8_20" @default.
- W1586388615 hasPublicationYear "2010" @default.
- W1586388615 type Work @default.
- W1586388615 sameAs 1586388615 @default.
- W1586388615 citedByCount "3" @default.
- W1586388615 countsByYear W15863886152013 @default.
- W1586388615 crossrefType "book-chapter" @default.
- W1586388615 hasAuthorship W1586388615A5010841617 @default.
- W1586388615 hasAuthorship W1586388615A5011451275 @default.
- W1586388615 hasAuthorship W1586388615A5014825654 @default.
- W1586388615 hasAuthorship W1586388615A5040009629 @default.
- W1586388615 hasAuthorship W1586388615A5062632609 @default.
- W1586388615 hasAuthorship W1586388615A5071277762 @default.
- W1586388615 hasAuthorship W1586388615A5074574647 @default.
- W1586388615 hasConcept C115961682 @default.
- W1586388615 hasConcept C119857082 @default.
- W1586388615 hasConcept C142575187 @default.
- W1586388615 hasConcept C153180895 @default.
- W1586388615 hasConcept C154945302 @default.
- W1586388615 hasConcept C155032097 @default.
- W1586388615 hasConcept C2524010 @default.
- W1586388615 hasConcept C33923547 @default.
- W1586388615 hasConcept C41008148 @default.
- W1586388615 hasConcept C50644808 @default.
- W1586388615 hasConcept C75294576 @default.
- W1586388615 hasConcept C81363708 @default.
- W1586388615 hasConcept C94124525 @default.
- W1586388615 hasConcept C95623464 @default.
- W1586388615 hasConceptScore W1586388615C115961682 @default.
- W1586388615 hasConceptScore W1586388615C119857082 @default.
- W1586388615 hasConceptScore W1586388615C142575187 @default.
- W1586388615 hasConceptScore W1586388615C153180895 @default.
- W1586388615 hasConceptScore W1586388615C154945302 @default.
- W1586388615 hasConceptScore W1586388615C155032097 @default.
- W1586388615 hasConceptScore W1586388615C2524010 @default.
- W1586388615 hasConceptScore W1586388615C33923547 @default.
- W1586388615 hasConceptScore W1586388615C41008148 @default.
- W1586388615 hasConceptScore W1586388615C50644808 @default.
- W1586388615 hasConceptScore W1586388615C75294576 @default.
- W1586388615 hasConceptScore W1586388615C81363708 @default.
- W1586388615 hasConceptScore W1586388615C94124525 @default.
- W1586388615 hasConceptScore W1586388615C95623464 @default.
- W1586388615 hasLocation W15863886151 @default.
- W1586388615 hasOpenAccess W1586388615 @default.
- W1586388615 hasPrimaryLocation W15863886151 @default.
- W1586388615 hasRelatedWork W2406522397 @default.
- W1586388615 hasRelatedWork W2726121760 @default.
- W1586388615 hasRelatedWork W2892483709 @default.
- W1586388615 hasRelatedWork W2912288872 @default.
- W1586388615 hasRelatedWork W2969680539 @default.
- W1586388615 hasRelatedWork W2995914718 @default.
- W1586388615 hasRelatedWork W3153891452 @default.
- W1586388615 hasRelatedWork W4214932115 @default.
- W1586388615 hasRelatedWork W4225852842 @default.
- W1586388615 hasRelatedWork W564581980 @default.
- W1586388615 isParatext "false" @default.
- W1586388615 isRetracted "false" @default.
- W1586388615 magId "1586388615" @default.
- W1586388615 workType "book-chapter" @default.