Matches in SemOpenAlex for { <https://semopenalex.org/work/W1968555913> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W1968555913 endingPage "893" @default.
- W1968555913 startingPage "893" @default.
- W1968555913 abstract "The segmentation of silhouettes into parts is a basic, long-standing problem in the comprehension, representation, and analysis of shape. Various approaches have been proposed which utilize two-dimensional shape properties; given that both the stimulus and output are two dimensional, use of two-dimensional analyses makes intuitive sense. The success of such approaches, however, has been limited. We propose a different approach, which models the selection of silhouette parts by first mapping the silhouette to a canonical three-dimensional shape, and then performing a simple and intuitive analysis of this new three-dimensional analogue. As previously described, Puffball inflation provides us with a robust, intuitive, scale invariant three-dimensional shape (Twarog et al. 2012), and a simplified application of the 3D Minima Rule (Hoffman and Richards, 1984), identifies part boundaries that can be projected onto the original silhouette. Using a dataset of human segmentations on 80 real-world silhouettes collected by DeWinter and Wagemans (2006), we present several psychophysical and statistical evaluations comparing the part-line predictions of Puffball to those of two approaches based on minima of negative contour curvature, the Necks and Limbs algorithm (Siddiqi and Kimia, 1995) and the Short Cut Rule (Singh et al., 1999). In each of these evaluations, Puffball part segmentation performs as well as or better than the minima-based approaches; most notably, Puffball identifies part-line endpoints more consistent with human judgments that the competing models. These results suggest that the two-dimensional patterns of part-line segmentations on which existing Minima Rule-based approaches are based, though valid as observations, do not necessarily comprise the computational chain through which such part-line judgments are made. As Puffball part segmentation exhibits many of these same patterns, we propose that these observed two-dimensional patterns are in fact the indirect effects of a three-dimensional computation. Meeting abstract presented at VSS 2014" @default.
- W1968555913 created "2016-06-24" @default.
- W1968555913 creator A5021989698 @default.
- W1968555913 creator A5062577376 @default.
- W1968555913 date "2014-08-22" @default.
- W1968555913 modified "2023-10-18" @default.
- W1968555913 title "Puffball Part Segmentation: Psychophysical and Statistical Evaluation" @default.
- W1968555913 doi "https://doi.org/10.1167/14.10.893" @default.
- W1968555913 hasPublicationYear "2014" @default.
- W1968555913 type Work @default.
- W1968555913 sameAs 1968555913 @default.
- W1968555913 citedByCount "0" @default.
- W1968555913 crossrefType "journal-article" @default.
- W1968555913 hasAuthorship W1968555913A5021989698 @default.
- W1968555913 hasAuthorship W1968555913A5062577376 @default.
- W1968555913 hasBestOaLocation W19685559131 @default.
- W1968555913 hasConcept C134306372 @default.
- W1968555913 hasConcept C153180895 @default.
- W1968555913 hasConcept C154945302 @default.
- W1968555913 hasConcept C182124507 @default.
- W1968555913 hasConcept C186633575 @default.
- W1968555913 hasConcept C190470478 @default.
- W1968555913 hasConcept C195065555 @default.
- W1968555913 hasConcept C197129107 @default.
- W1968555913 hasConcept C198352243 @default.
- W1968555913 hasConcept C23123220 @default.
- W1968555913 hasConcept C2524010 @default.
- W1968555913 hasConcept C31972630 @default.
- W1968555913 hasConcept C33923547 @default.
- W1968555913 hasConcept C37914503 @default.
- W1968555913 hasConcept C41008148 @default.
- W1968555913 hasConcept C58103923 @default.
- W1968555913 hasConcept C89600930 @default.
- W1968555913 hasConceptScore W1968555913C134306372 @default.
- W1968555913 hasConceptScore W1968555913C153180895 @default.
- W1968555913 hasConceptScore W1968555913C154945302 @default.
- W1968555913 hasConceptScore W1968555913C182124507 @default.
- W1968555913 hasConceptScore W1968555913C186633575 @default.
- W1968555913 hasConceptScore W1968555913C190470478 @default.
- W1968555913 hasConceptScore W1968555913C195065555 @default.
- W1968555913 hasConceptScore W1968555913C197129107 @default.
- W1968555913 hasConceptScore W1968555913C198352243 @default.
- W1968555913 hasConceptScore W1968555913C23123220 @default.
- W1968555913 hasConceptScore W1968555913C2524010 @default.
- W1968555913 hasConceptScore W1968555913C31972630 @default.
- W1968555913 hasConceptScore W1968555913C33923547 @default.
- W1968555913 hasConceptScore W1968555913C37914503 @default.
- W1968555913 hasConceptScore W1968555913C41008148 @default.
- W1968555913 hasConceptScore W1968555913C58103923 @default.
- W1968555913 hasConceptScore W1968555913C89600930 @default.
- W1968555913 hasIssue "10" @default.
- W1968555913 hasLocation W19685559131 @default.
- W1968555913 hasOpenAccess W1968555913 @default.
- W1968555913 hasPrimaryLocation W19685559131 @default.
- W1968555913 hasRelatedWork W1582219599 @default.
- W1968555913 hasRelatedWork W1820551162 @default.
- W1968555913 hasRelatedWork W1972015969 @default.
- W1968555913 hasRelatedWork W2048083981 @default.
- W1968555913 hasRelatedWork W2068787934 @default.
- W1968555913 hasRelatedWork W2076010473 @default.
- W1968555913 hasRelatedWork W2110230079 @default.
- W1968555913 hasRelatedWork W2121864739 @default.
- W1968555913 hasRelatedWork W2171787258 @default.
- W1968555913 hasRelatedWork W263122454 @default.
- W1968555913 hasVolume "14" @default.
- W1968555913 isParatext "false" @default.
- W1968555913 isRetracted "false" @default.
- W1968555913 magId "1968555913" @default.
- W1968555913 workType "article" @default.