Matches in SemOpenAlex for { <https://semopenalex.org/work/W66095925> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W66095925 abstract "Object category recognition is one of the most difficult problems in computer vision. It involves recognizing objects despite intra-class variations, viewpoint changes and background clutter. The goal of this thesis is to investigate robust invariant local image description and the selection of discriminative features. We show that class-discriminative scale-invariant features achieve excellent results for image-level categorization and object localization. We present solutions for two key problems: (i) we improve the quality of the image description based on a novel scale-invariant keypoint detection method and (ii) we integrate feature filtering techniques into our object models. Our novel scale-invariant detector is based on the idea of a ``maximally stable description'', i.e., the descriptor should be stable even in the presence of minor variations of the detector. The technique performs scale selection based on a region descriptor, here SIFT, and chooses regions for which this descriptor is maximally stable, i.e., the difference between descriptors extracted for consecutive scales reaches a minimum. This scale selection technique is applied to multi-scale Harris and Laplacian points. Experimental results evaluate the performance of our detector and show that it outperforms existing ones in the context of image matching, category and texture classification, as well as object localization. To construct object models based on discriminative features, we first cluster the scale-invariant descriptors and obtain a set of ``visual words''. We then estimate the discriminative information of these clusters based on different feature selection techniques---several of which are traditionally used in text retrieval. We discuss their properties---feature frequency, discriminative power, and redundancy---and analyze their performance in the context of image classification and object localization. We show that each task has different requirements, and indicate which selection techniques are the most appropriate. Experimental results for recognition on challenging large datasets demonstrate the performance of the approach." @default.
- W66095925 created "2016-06-24" @default.
- W66095925 creator A5014229752 @default.
- W66095925 date "2006-01-01" @default.
- W66095925 modified "2023-09-25" @default.
- W66095925 title "Selection of discriminative regions and local descriptors for generic object class recognition" @default.
- W66095925 hasPublicationYear "2006" @default.
- W66095925 type Work @default.
- W66095925 sameAs 66095925 @default.
- W66095925 citedByCount "6" @default.
- W66095925 countsByYear W660959252012 @default.
- W66095925 countsByYear W660959252014 @default.
- W66095925 crossrefType "dissertation" @default.
- W66095925 hasAuthorship W66095925A5014229752 @default.
- W66095925 hasConcept C148483581 @default.
- W66095925 hasConcept C153180895 @default.
- W66095925 hasConcept C154945302 @default.
- W66095925 hasConcept C190470478 @default.
- W66095925 hasConcept C2781238097 @default.
- W66095925 hasConcept C31972630 @default.
- W66095925 hasConcept C33923547 @default.
- W66095925 hasConcept C37914503 @default.
- W66095925 hasConcept C41008148 @default.
- W66095925 hasConcept C52622490 @default.
- W66095925 hasConcept C61265191 @default.
- W66095925 hasConcept C64876066 @default.
- W66095925 hasConcept C94124525 @default.
- W66095925 hasConcept C97931131 @default.
- W66095925 hasConceptScore W66095925C148483581 @default.
- W66095925 hasConceptScore W66095925C153180895 @default.
- W66095925 hasConceptScore W66095925C154945302 @default.
- W66095925 hasConceptScore W66095925C190470478 @default.
- W66095925 hasConceptScore W66095925C2781238097 @default.
- W66095925 hasConceptScore W66095925C31972630 @default.
- W66095925 hasConceptScore W66095925C33923547 @default.
- W66095925 hasConceptScore W66095925C37914503 @default.
- W66095925 hasConceptScore W66095925C41008148 @default.
- W66095925 hasConceptScore W66095925C52622490 @default.
- W66095925 hasConceptScore W66095925C61265191 @default.
- W66095925 hasConceptScore W66095925C64876066 @default.
- W66095925 hasConceptScore W66095925C94124525 @default.
- W66095925 hasConceptScore W66095925C97931131 @default.
- W66095925 hasLocation W660959251 @default.
- W66095925 hasOpenAccess W66095925 @default.
- W66095925 hasPrimaryLocation W660959251 @default.
- W66095925 hasRelatedWork W1528789833 @default.
- W66095925 hasRelatedWork W153051426 @default.
- W66095925 hasRelatedWork W1558630797 @default.
- W66095925 hasRelatedWork W1631454559 @default.
- W66095925 hasRelatedWork W1975427305 @default.
- W66095925 hasRelatedWork W2009853124 @default.
- W66095925 hasRelatedWork W2030946033 @default.
- W66095925 hasRelatedWork W2089678653 @default.
- W66095925 hasRelatedWork W2099580609 @default.
- W66095925 hasRelatedWork W2117489663 @default.
- W66095925 hasRelatedWork W2126227692 @default.
- W66095925 hasRelatedWork W2126384842 @default.
- W66095925 hasRelatedWork W2151103935 @default.
- W66095925 hasRelatedWork W2165406585 @default.
- W66095925 hasRelatedWork W2182103748 @default.
- W66095925 hasRelatedWork W2242314978 @default.
- W66095925 hasRelatedWork W2287352068 @default.
- W66095925 hasRelatedWork W3131713303 @default.
- W66095925 hasRelatedWork W3203942662 @default.
- W66095925 hasRelatedWork W11907932 @default.
- W66095925 isParatext "false" @default.
- W66095925 isRetracted "false" @default.
- W66095925 magId "66095925" @default.
- W66095925 workType "dissertation" @default.