Matches in SemOpenAlex for { <https://semopenalex.org/work/W2785333463> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2785333463 abstract "In this paper, an approach is proposed to solve a classic segmentation problem on handwritten touching digit pairs using spectral clustering (SC). SC has appeared in many of the state-of-the-art algorithms on image grouping problems recently, while it is a challenging work to build similarities between each pixel. In this paper, support vector machine (SVM) is used to predict the affinity matrix in SC instead of designing a complex function, hence making it a general approach. Different from traditional methods which focus on finding the cutting points or lines, we treat the handwritten string segmentation as a graph partitioning problem, which enables us to separate those digits connected in a very complicated way. We also introduce a 'second-segmentation' to optimize the segmentation result, and find out that the whole algorithm is similar to a multi-layer perception (MLP). Experiment results show that the proposed approach performs satisfactorily with high correct rate while keeping its own advantages as a general approach." @default.
- W2785333463 created "2018-02-23" @default.
- W2785333463 creator A5035286587 @default.
- W2785333463 creator A5051705800 @default.
- W2785333463 date "2017-11-01" @default.
- W2785333463 modified "2023-10-17" @default.
- W2785333463 title "A General Approach for Handwritten Digits Segmentation Using Spectral Clustering" @default.
- W2785333463 cites W1950520880 @default.
- W2785333463 cites W1986007546 @default.
- W2785333463 cites W1993962865 @default.
- W2785333463 cites W2000145530 @default.
- W2785333463 cites W2004389124 @default.
- W2785333463 cites W2019676475 @default.
- W2785333463 cites W2032487560 @default.
- W2785333463 cites W2038626138 @default.
- W2785333463 cites W2097341236 @default.
- W2785333463 cites W2121947440 @default.
- W2785333463 cites W2123037436 @default.
- W2785333463 cites W2130399251 @default.
- W2785333463 cites W2170697133 @default.
- W2785333463 cites W2171886029 @default.
- W2785333463 doi "https://doi.org/10.1109/icdar.2017.95" @default.
- W2785333463 hasPublicationYear "2017" @default.
- W2785333463 type Work @default.
- W2785333463 sameAs 2785333463 @default.
- W2785333463 citedByCount "6" @default.
- W2785333463 countsByYear W27853334632018 @default.
- W2785333463 countsByYear W27853334632019 @default.
- W2785333463 countsByYear W27853334632020 @default.
- W2785333463 countsByYear W27853334632021 @default.
- W2785333463 countsByYear W27853334632022 @default.
- W2785333463 crossrefType "proceedings-article" @default.
- W2785333463 hasAuthorship W2785333463A5035286587 @default.
- W2785333463 hasAuthorship W2785333463A5051705800 @default.
- W2785333463 hasConcept C105611402 @default.
- W2785333463 hasConcept C124504099 @default.
- W2785333463 hasConcept C153180895 @default.
- W2785333463 hasConcept C154945302 @default.
- W2785333463 hasConcept C28490314 @default.
- W2785333463 hasConcept C41008148 @default.
- W2785333463 hasConcept C73555534 @default.
- W2785333463 hasConcept C89600930 @default.
- W2785333463 hasConceptScore W2785333463C105611402 @default.
- W2785333463 hasConceptScore W2785333463C124504099 @default.
- W2785333463 hasConceptScore W2785333463C153180895 @default.
- W2785333463 hasConceptScore W2785333463C154945302 @default.
- W2785333463 hasConceptScore W2785333463C28490314 @default.
- W2785333463 hasConceptScore W2785333463C41008148 @default.
- W2785333463 hasConceptScore W2785333463C73555534 @default.
- W2785333463 hasConceptScore W2785333463C89600930 @default.
- W2785333463 hasLocation W27853334631 @default.
- W2785333463 hasOpenAccess W2785333463 @default.
- W2785333463 hasPrimaryLocation W27853334631 @default.
- W2785333463 hasRelatedWork W1457719682 @default.
- W2785333463 hasRelatedWork W2005476934 @default.
- W2785333463 hasRelatedWork W2045391057 @default.
- W2785333463 hasRelatedWork W2058042818 @default.
- W2785333463 hasRelatedWork W2152591411 @default.
- W2785333463 hasRelatedWork W2510758617 @default.
- W2785333463 hasRelatedWork W2897195263 @default.
- W2785333463 hasRelatedWork W3127804355 @default.
- W2785333463 hasRelatedWork W3199679192 @default.
- W2785333463 hasRelatedWork W4206076898 @default.
- W2785333463 isParatext "false" @default.
- W2785333463 isRetracted "false" @default.
- W2785333463 magId "2785333463" @default.
- W2785333463 workType "article" @default.