FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2573546209> ?p ?o ?g. }

• W2573546209 endingPage "3330" @default.
• W2573546209 startingPage "3317" @default.
• W2573546209 abstract "In this paper, we present a superpixel segmentation algorithm called linear spectral clustering (LSC), which is capable of producing superpixels with both high boundary adherence and visual compactness for natural images with low computational costs. In LSC, a normalized cuts-based formulation of image segmentation is adopted using a distance metric that measures both the color similarity and the space proximity between image pixels. However, rather than directly using the traditional eigen-based algorithm, we approximate the similarity metric through a deliberately designed kernel function such that pixel values can be explicitly mapped to a high-dimensional feature space. We then apply the conclusion that by appropriately weighting each point in this feature space, the objective functions of the weighted K-means and the normalized cuts share the same optimum points. Consequently, it is possible to optimize the cost function of the normalized cuts by iteratively applying simple K-means clustering in the proposed feature space. LSC possesses linear computational complexity and high memory efficiency, since it avoids both the decomposition of the affinity matrix and the generation of the large kernel matrix. By utilizing the underlying mathematical equivalence between the two types of seemingly different methods, LSC successfully preserves global image structures through efficient local operations. Experimental results show that LSC performs as well as or even better than the state-of-the-art superpixel segmentation algorithms in terms of several commonly used evaluation metrics in image segmentation. The applicability of LSC is further demonstrated in two related computer vision tasks." @default.
• W2573546209 created "2017-01-26" @default.
• W2573546209 creator A5024708084 @default.
• W2573546209 creator A5033870719 @default.
• W2573546209 creator A5060452999 @default.
• W2573546209 date "2017-07-01" @default.
• W2573546209 modified "2023-10-10" @default.
• W2573546209 title "Linear Spectral Clustering Superpixel" @default.
• W2573546209 cites W1563088657 @default.
• W2573546209 cites W1903029394 @default.
• W2573546209 cites W1907409009 @default.
• W2573546209 cites W1970786134 @default.
• W2573546209 cites W1999478155 @default.
• W2573546209 cites W2003060733 @default.
• W2573546209 cites W2037227137 @default.
• W2573546209 cites W2066624635 @default.
• W2573546209 cites W2067191022 @default.
• W2573546209 cites W2101309634 @default.
• W2573546209 cites W2104125540 @default.
• W2573546209 cites W2113137767 @default.
• W2573546209 cites W2115313253 @default.
• W2573546209 cites W2117539524 @default.
• W2573546209 cites W2118246710 @default.
• W2573546209 cites W2119531662 @default.
• W2573546209 cites W2121927366 @default.
• W2573546209 cites W2121947440 @default.
• W2573546209 cites W2124351162 @default.
• W2573546209 cites W2135674549 @default.
• W2573546209 cites W2135957668 @default.
• W2573546209 cites W2143516773 @default.
• W2573546209 cites W2151996626 @default.
• W2573546209 cites W2221898772 @default.
• W2573546209 cites W2293105860 @default.
• W2573546209 cites W2545985378 @default.
• W2573546209 cites W4300293005 @default.
• W2573546209 cites W2002704236 @default.
• W2573546209 doi "https://doi.org/10.1109/tip.2017.2651389" @default.
• W2573546209 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/28092548" @default.
• W2573546209 hasPublicationYear "2017" @default.
• W2573546209 type Work @default.
• W2573546209 sameAs 2573546209 @default.
• W2573546209 citedByCount "135" @default.
• W2573546209 countsByYear W25735462092017 @default.
• W2573546209 countsByYear W25735462092018 @default.
• W2573546209 countsByYear W25735462092019 @default.
• W2573546209 countsByYear W25735462092020 @default.
• W2573546209 countsByYear W25735462092021 @default.
• W2573546209 countsByYear W25735462092022 @default.
• W2573546209 countsByYear W25735462092023 @default.
• W2573546209 crossrefType "journal-article" @default.
• W2573546209 hasAuthorship W2573546209A5024708084 @default.
• W2573546209 hasAuthorship W2573546209A5033870719 @default.
• W2573546209 hasAuthorship W2573546209A5060452999 @default.
• W2573546209 hasConcept C105611402 @default.
• W2573546209 hasConcept C11413529 @default.
• W2573546209 hasConcept C114614502 @default.
• W2573546209 hasConcept C124504099 @default.
• W2573546209 hasConcept C126838900 @default.
• W2573546209 hasConcept C138885662 @default.
• W2573546209 hasConcept C153180895 @default.
• W2573546209 hasConcept C154945302 @default.
• W2573546209 hasConcept C160633673 @default.
• W2573546209 hasConcept C162324750 @default.
• W2573546209 hasConcept C176217482 @default.
• W2573546209 hasConcept C183115368 @default.
• W2573546209 hasConcept C21547014 @default.
• W2573546209 hasConcept C2776401178 @default.
• W2573546209 hasConcept C33923547 @default.
• W2573546209 hasConcept C41008148 @default.
• W2573546209 hasConcept C41895202 @default.
• W2573546209 hasConcept C65885262 @default.
• W2573546209 hasConcept C71924100 @default.
• W2573546209 hasConcept C73555534 @default.
• W2573546209 hasConcept C74193536 @default.
• W2573546209 hasConcept C83665646 @default.
• W2573546209 hasConcept C89600930 @default.
• W2573546209 hasConceptScore W2573546209C105611402 @default.
• W2573546209 hasConceptScore W2573546209C11413529 @default.
• W2573546209 hasConceptScore W2573546209C114614502 @default.
• W2573546209 hasConceptScore W2573546209C124504099 @default.
• W2573546209 hasConceptScore W2573546209C126838900 @default.
• W2573546209 hasConceptScore W2573546209C138885662 @default.
• W2573546209 hasConceptScore W2573546209C153180895 @default.
• W2573546209 hasConceptScore W2573546209C154945302 @default.
• W2573546209 hasConceptScore W2573546209C160633673 @default.
• W2573546209 hasConceptScore W2573546209C162324750 @default.
• W2573546209 hasConceptScore W2573546209C176217482 @default.
• W2573546209 hasConceptScore W2573546209C183115368 @default.
• W2573546209 hasConceptScore W2573546209C21547014 @default.
• W2573546209 hasConceptScore W2573546209C2776401178 @default.
• W2573546209 hasConceptScore W2573546209C33923547 @default.
• W2573546209 hasConceptScore W2573546209C41008148 @default.
• W2573546209 hasConceptScore W2573546209C41895202 @default.
• W2573546209 hasConceptScore W2573546209C65885262 @default.
• W2573546209 hasConceptScore W2573546209C71924100 @default.
• W2573546209 hasConceptScore W2573546209C73555534 @default.
• W2573546209 hasConceptScore W2573546209C74193536 @default.
• W2573546209 hasConceptScore W2573546209C83665646 @default.

• next