Matches in SemOpenAlex for { <https://semopenalex.org/work/W6792081> ?p ?o ?g. }
- W6792081 abstract "The task of assigning labels to pixels is central to computer vision. In automatic segmentation an algorithm assigns a label to each pixel where labels connote a shared property across pixels (e.g. color, bounding contour, texture). Recent approaches to image segmentation have formulated this labeling task as partitioning a graph derived from the image. We use spectral segmentation to denote the family of algorithms that seek a partitioning by processing the eigenstructure associated with image graphs. In this thesis we analyze current spectral segmentation algorithms and explain their performance, both practically and theoretically, on the Normalized Cuts (NCut) criterion. Further, we introduce a novel family of spectral graph partitioning methods, spectral rounding, and apply them to image segmentation tasks. Edge separators of a graph are produced by iteratively reweighting the edges until the graph disconnects into the prescribed number of components. At each iteration a small number of eigenvectors with small eigenvalue are computed and used to determine the reweighting. In this way spectral rounding directly produces discrete solutions where as current spectral algorithms must map the continuous eigenvectors to discrete solutions by employing a heuristic geometric separator (e.g. k-means). We show that spectral rounding compares favorably to current spectral approximations on the NCut criterion in natural image segmentation. Quantitative evaluations are performed on multiple image databases including the Berkeley Segmentation Database. These experiments demonstrate that segmentations with improved NCut value (obtained using the SR-Algorithm) are more highly correlated with human hand-segmentations." @default.
- W6792081 created "2016-06-24" @default.
- W6792081 creator A5010457003 @default.
- W6792081 creator A5013103323 @default.
- W6792081 creator A5081509021 @default.
- W6792081 date "2006-01-01" @default.
- W6792081 modified "2023-09-26" @default.
- W6792081 title "Spectral rounding and image segmentation" @default.
- W6792081 cites W1554663460 @default.
- W6792081 cites W1587744656 @default.
- W6792081 cites W1651266332 @default.
- W6792081 cites W1760551737 @default.
- W6792081 cites W1964443764 @default.
- W6792081 cites W1985123706 @default.
- W6792081 cites W1990775521 @default.
- W6792081 cites W1994875376 @default.
- W6792081 cites W2016482013 @default.
- W6792081 cites W2018821242 @default.
- W6792081 cites W2020632401 @default.
- W6792081 cites W2020999234 @default.
- W6792081 cites W2027199101 @default.
- W6792081 cites W2035400420 @default.
- W6792081 cites W2045107949 @default.
- W6792081 cites W2045756072 @default.
- W6792081 cites W2067191022 @default.
- W6792081 cites W2067976091 @default.
- W6792081 cites W2096139825 @default.
- W6792081 cites W2097649450 @default.
- W6792081 cites W2100422696 @default.
- W6792081 cites W2100824854 @default.
- W6792081 cites W2101309634 @default.
- W6792081 cites W2104094303 @default.
- W6792081 cites W2104095591 @default.
- W6792081 cites W2105960416 @default.
- W6792081 cites W2106110775 @default.
- W6792081 cites W2106285343 @default.
- W6792081 cites W2111004121 @default.
- W6792081 cites W2113387946 @default.
- W6792081 cites W2116040950 @default.
- W6792081 cites W2121927366 @default.
- W6792081 cites W2121947440 @default.
- W6792081 cites W2125278290 @default.
- W6792081 cites W2126140058 @default.
- W6792081 cites W2126746199 @default.
- W6792081 cites W2135674549 @default.
- W6792081 cites W2137572914 @default.
- W6792081 cites W2140502500 @default.
- W6792081 cites W2141376824 @default.
- W6792081 cites W2141729166 @default.
- W6792081 cites W2145701440 @default.
- W6792081 cites W2146352414 @default.
- W6792081 cites W2154791445 @default.
- W6792081 cites W2155871590 @default.
- W6792081 cites W2163290928 @default.
- W6792081 cites W2165874743 @default.
- W6792081 cites W2171048379 @default.
- W6792081 cites W2296319761 @default.
- W6792081 cites W2496945004 @default.
- W6792081 cites W2578658712 @default.
- W6792081 cites W2797638056 @default.
- W6792081 hasPublicationYear "2006" @default.
- W6792081 type Work @default.
- W6792081 sameAs 6792081 @default.
- W6792081 citedByCount "1" @default.
- W6792081 crossrefType "journal-article" @default.
- W6792081 hasAuthorship W6792081A5010457003 @default.
- W6792081 hasAuthorship W6792081A5013103323 @default.
- W6792081 hasAuthorship W6792081A5081509021 @default.
- W6792081 hasConcept C111919701 @default.
- W6792081 hasConcept C11413529 @default.
- W6792081 hasConcept C121332964 @default.
- W6792081 hasConcept C124504099 @default.
- W6792081 hasConcept C136625980 @default.
- W6792081 hasConcept C153180895 @default.
- W6792081 hasConcept C154945302 @default.
- W6792081 hasConcept C158693339 @default.
- W6792081 hasConcept C160633673 @default.
- W6792081 hasConcept C25694479 @default.
- W6792081 hasConcept C31972630 @default.
- W6792081 hasConcept C33923547 @default.
- W6792081 hasConcept C41008148 @default.
- W6792081 hasConcept C62520636 @default.
- W6792081 hasConcept C65885262 @default.
- W6792081 hasConcept C89600930 @default.
- W6792081 hasConceptScore W6792081C111919701 @default.
- W6792081 hasConceptScore W6792081C11413529 @default.
- W6792081 hasConceptScore W6792081C121332964 @default.
- W6792081 hasConceptScore W6792081C124504099 @default.
- W6792081 hasConceptScore W6792081C136625980 @default.
- W6792081 hasConceptScore W6792081C153180895 @default.
- W6792081 hasConceptScore W6792081C154945302 @default.
- W6792081 hasConceptScore W6792081C158693339 @default.
- W6792081 hasConceptScore W6792081C160633673 @default.
- W6792081 hasConceptScore W6792081C25694479 @default.
- W6792081 hasConceptScore W6792081C31972630 @default.
- W6792081 hasConceptScore W6792081C33923547 @default.
- W6792081 hasConceptScore W6792081C41008148 @default.
- W6792081 hasConceptScore W6792081C62520636 @default.
- W6792081 hasConceptScore W6792081C65885262 @default.
- W6792081 hasConceptScore W6792081C89600930 @default.