FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2342468814> ?p ?o ?g. }

• W2342468814 endingPage "2836" @default.
• W2342468814 startingPage "2825" @default.
• W2342468814 abstract "The performance of handwriting recognition systems is dependent on the features extracted from the word image. A large body of features exists in the literature, but no method has yet been proposed to identify the most promising of these, other than a straightforward comparison based on the recognition rate. In this paper, we propose a framework for feature set evaluation based on a collaborative setting. We use a weighted vote combination of recurrent neural network (RNN) classifiers, each trained with a particular feature set. This combination is modeled in a probabilistic framework as a mixture model and two methods for weight estimation are described. The main contribution of this paper is to quantify the importance of feature sets through the combination weights, which reflect their strength and complementarity. We chose the RNN classifier because of its state-of-the-art performance. Also, we provide the first feature set benchmark for this classifier. We evaluated several feature sets on the IFN/ENIT and RIMES databases of Arabic and Latin script, respectively. The resulting combination model is competitive with state-of-the-art systems." @default.
• W2342468814 created "2016-06-24" @default.
• W2342468814 creator A5015410834 @default.
• W2342468814 creator A5036208317 @default.
• W2342468814 creator A5059199849 @default.
• W2342468814 date "2016-12-01" @default.
• W2342468814 modified "2023-09-25" @default.
• W2342468814 title "Feature Set Evaluation for Offline Handwriting Recognition Systems: Application to the Recurrent Neural Network Model" @default.
• W2342468814 cites W175300340 @default.
• W2342468814 cites W1963885141 @default.
• W2342468814 cites W1992085455 @default.
• W2342468814 cites W1995574284 @default.
• W2342468814 cites W2004987553 @default.
• W2342468814 cites W2007163663 @default.
• W2342468814 cites W2009463778 @default.
• W2342468814 cites W2010262905 @default.
• W2342468814 cites W2019025183 @default.
• W2342468814 cites W2024996570 @default.
• W2342468814 cites W2025768430 @default.
• W2342468814 cites W2031598510 @default.
• W2342468814 cites W2037429745 @default.
• W2342468814 cites W2039215914 @default.
• W2342468814 cites W2053186076 @default.
• W2342468814 cites W2060365157 @default.
• W2342468814 cites W2071901160 @default.
• W2342468814 cites W2072731835 @default.
• W2342468814 cites W2073567182 @default.
• W2342468814 cites W2084859622 @default.
• W2342468814 cites W2092858021 @default.
• W2342468814 cites W2096827211 @default.
• W2342468814 cites W2101040242 @default.
• W2342468814 cites W2106382595 @default.
• W2342468814 cites W2106986062 @default.
• W2342468814 cites W2112263687 @default.
• W2342468814 cites W2112796928 @default.
• W2342468814 cites W2119605622 @default.
• W2342468814 cites W2122585011 @default.
• W2342468814 cites W2123432324 @default.
• W2342468814 cites W2130451799 @default.
• W2342468814 cites W2133059825 @default.
• W2342468814 cites W2135743131 @default.
• W2342468814 cites W2140280084 @default.
• W2342468814 cites W2141812924 @default.
• W2342468814 cites W2142069714 @default.
• W2342468814 cites W2144533356 @default.
• W2342468814 cites W2149319679 @default.
• W2342468814 cites W2150860957 @default.
• W2342468814 cites W2151103935 @default.
• W2342468814 cites W2151417693 @default.
• W2342468814 cites W2153070015 @default.
• W2342468814 cites W2156301828 @default.
• W2342468814 cites W2161969291 @default.
• W2342468814 cites W2162395775 @default.
• W2342468814 cites W2162838084 @default.
• W2342468814 cites W2164568552 @default.
• W2342468814 cites W2164867695 @default.
• W2342468814 cites W2165712214 @default.
• W2342468814 cites W2168504305 @default.
• W2342468814 cites W2168868236 @default.
• W2342468814 cites W2171927392 @default.
• W2342468814 cites W2303931467 @default.
• W2342468814 cites W4241640108 @default.
• W2342468814 doi "https://doi.org/10.1109/tcyb.2015.2490165" @default.
• W2342468814 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26561491" @default.
• W2342468814 hasPublicationYear "2016" @default.
• W2342468814 type Work @default.
• W2342468814 sameAs 2342468814 @default.
• W2342468814 citedByCount "52" @default.
• W2342468814 countsByYear W23424688142016 @default.
• W2342468814 countsByYear W23424688142017 @default.
• W2342468814 countsByYear W23424688142018 @default.
• W2342468814 countsByYear W23424688142019 @default.
• W2342468814 countsByYear W23424688142020 @default.
• W2342468814 countsByYear W23424688142021 @default.
• W2342468814 countsByYear W23424688142022 @default.
• W2342468814 countsByYear W23424688142023 @default.
• W2342468814 crossrefType "journal-article" @default.
• W2342468814 hasAuthorship W2342468814A5015410834 @default.
• W2342468814 hasAuthorship W2342468814A5036208317 @default.
• W2342468814 hasAuthorship W2342468814A5059199849 @default.
• W2342468814 hasConcept C112640561 @default.
• W2342468814 hasConcept C119857082 @default.
• W2342468814 hasConcept C13280743 @default.
• W2342468814 hasConcept C138885662 @default.
• W2342468814 hasConcept C147168706 @default.
• W2342468814 hasConcept C153180895 @default.
• W2342468814 hasConcept C154945302 @default.
• W2342468814 hasConcept C185798385 @default.
• W2342468814 hasConcept C205649164 @default.
• W2342468814 hasConcept C2776401178 @default.
• W2342468814 hasConcept C41008148 @default.
• W2342468814 hasConcept C41895202 @default.
• W2342468814 hasConcept C50644808 @default.
• W2342468814 hasConcept C52622490 @default.
• W2342468814 hasConcept C95623464 @default.
• W2342468814 hasConceptScore W2342468814C112640561 @default.
• W2342468814 hasConceptScore W2342468814C119857082 @default.
• W2342468814 hasConceptScore W2342468814C13280743 @default.

• next