FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2004192742> ?p ?o ?g. }

• W2004192742 endingPage "1186" @default.
• W2004192742 startingPage "1171" @default.
• W2004192742 abstract "Abstract In pattern recognition applications, the classification power of a system can be improved by combining several classifiers. Obviously performance of the system cannot be improved if the individual classifiers make all the same mistakes, thus it is important to use different features and different structures in the individual classifiers. In this context, we propose a two subnets neural network called CSM net. The first subnet, or similarity layer, is operating as a similarity measure neural network; it is based on the complementary similarity measure method (CSM). The second subnet is a competitive neural network (CNN) based on the winner takes all algorithm (WTA) that is used for the classification. In the proposed neural architecture, the statistical CSM method is analyzed, and implemented in the form of a feed forward neural network, it is named “similarity measure neural network” (SMNN). We show that the resulting SMNN synaptic weights are modified versions of the model patterns used in the training set, and that they can be considered as a memory network. We introduce a relative distance data calculated from the SMNN output, and we use it as a quality measurement tool of the degraded characters, what makes the SMNN classifier very powerful, and very well-suited for features rejections. This relative distance is used by the SMNN and compared to a first rejection threshold to accept, or reject, the incoming characters. In order to guarantee a higher recognition and reliability rates for the cascaded method, the SMNN is combined with a second subnet based on the WTA for classification using a second specific rejection threshold. These two submits combination (CSM net) boost the performance of the SMNN classifier. This is resulting in a robust multiple classifiers that can be used for setting the entire rejection threshold. The experimental results that we introduce are related to the proposed method, but the tests are introduced with various impulse noise levels, as well as the tests with broken and manually corrupted characters, and characters with various levels of additive Gaussian noise. The experiments show the effective ability of the model to yield relevant and robust recognition on poor quality printed checks, and show that the CSM net outperforms the previous works, both in efficiency and accuracy." @default.
• W2004192742 created "2016-06-24" @default.
• W2004192742 creator A5017013876 @default.
• W2004192742 creator A5029060735 @default.
• W2004192742 creator A5051817794 @default.
• W2004192742 creator A5084594076 @default.
• W2004192742 date "2014-07-01" @default.
• W2004192742 modified "2023-09-26" @default.
• W2004192742 title "CSM neural network for degraded printed character optical recognition" @default.
• W2004192742 cites W1965234758 @default.
• W2004192742 cites W1985079464 @default.
• W2004192742 cites W1993119111 @default.
• W2004192742 cites W1994042062 @default.
• W2004192742 cites W1996567568 @default.
• W2004192742 cites W1997312619 @default.
• W2004192742 cites W2016866522 @default.
• W2004192742 cites W2028504087 @default.
• W2004192742 cites W2069456987 @default.
• W2004192742 cites W2078155237 @default.
• W2004192742 cites W2094306970 @default.
• W2004192742 cites W2101409571 @default.
• W2004192742 cites W2101927907 @default.
• W2004192742 cites W2107768760 @default.
• W2004192742 cites W2111822866 @default.
• W2004192742 cites W2119349747 @default.
• W2004192742 cites W2122970629 @default.
• W2004192742 cites W2133577140 @default.
• W2004192742 cites W2145035083 @default.
• W2004192742 cites W2149470434 @default.
• W2004192742 doi "https://doi.org/10.1016/j.jvcir.2014.04.002" @default.
• W2004192742 hasPublicationYear "2014" @default.
• W2004192742 type Work @default.
• W2004192742 sameAs 2004192742 @default.
• W2004192742 citedByCount "6" @default.
• W2004192742 countsByYear W20041927422015 @default.
• W2004192742 countsByYear W20041927422016 @default.
• W2004192742 countsByYear W20041927422017 @default.
• W2004192742 countsByYear W20041927422018 @default.
• W2004192742 countsByYear W20041927422019 @default.
• W2004192742 crossrefType "journal-article" @default.
• W2004192742 hasAuthorship W2004192742A5017013876 @default.
• W2004192742 hasAuthorship W2004192742A5029060735 @default.
• W2004192742 hasAuthorship W2004192742A5051817794 @default.
• W2004192742 hasAuthorship W2004192742A5084594076 @default.
• W2004192742 hasConcept C115961682 @default.
• W2004192742 hasConcept C153180895 @default.
• W2004192742 hasConcept C154945302 @default.
• W2004192742 hasConcept C2524010 @default.
• W2004192742 hasConcept C2780861071 @default.
• W2004192742 hasConcept C28490314 @default.
• W2004192742 hasConcept C2987247673 @default.
• W2004192742 hasConcept C33923547 @default.
• W2004192742 hasConcept C41008148 @default.
• W2004192742 hasConcept C50644808 @default.
• W2004192742 hasConcept C546480517 @default.
• W2004192742 hasConceptScore W2004192742C115961682 @default.
• W2004192742 hasConceptScore W2004192742C153180895 @default.
• W2004192742 hasConceptScore W2004192742C154945302 @default.
• W2004192742 hasConceptScore W2004192742C2524010 @default.
• W2004192742 hasConceptScore W2004192742C2780861071 @default.
• W2004192742 hasConceptScore W2004192742C28490314 @default.
• W2004192742 hasConceptScore W2004192742C2987247673 @default.
• W2004192742 hasConceptScore W2004192742C33923547 @default.
• W2004192742 hasConceptScore W2004192742C41008148 @default.
• W2004192742 hasConceptScore W2004192742C50644808 @default.
• W2004192742 hasConceptScore W2004192742C546480517 @default.
• W2004192742 hasIssue "5" @default.
• W2004192742 hasLocation W20041927421 @default.
• W2004192742 hasOpenAccess W2004192742 @default.
• W2004192742 hasPrimaryLocation W20041927421 @default.
• W2004192742 hasRelatedWork W1766151705 @default.
• W2004192742 hasRelatedWork W1998599144 @default.
• W2004192742 hasRelatedWork W2023503483 @default.
• W2004192742 hasRelatedWork W2105354826 @default.
• W2004192742 hasRelatedWork W2118744957 @default.
• W2004192742 hasRelatedWork W2130515063 @default.
• W2004192742 hasRelatedWork W2175121793 @default.
• W2004192742 hasRelatedWork W2188691566 @default.
• W2004192742 hasRelatedWork W2484546353 @default.
• W2004192742 hasRelatedWork W2075186610 @default.
• W2004192742 hasVolume "25" @default.
• W2004192742 isParatext "false" @default.
• W2004192742 isRetracted "false" @default.
• W2004192742 magId "2004192742" @default.
• W2004192742 workType "article" @default.