Matches in SemOpenAlex for { <https://semopenalex.org/work/W2114790400> ?p ?o ?g. }
- W2114790400 abstract "This paper presents a hybrid MLP-SVM method for cursive characters recognition. Specialized Support Vector Machines (SVMs) are introduced to significantly improve the performance of Multilayer Perceptron (MLP) in the local areas around the surfaces of separation between each pair of characters in the space of input patterns. This hybrid architecture is based on the observation that when using MLPs in the task of handwritten characters recognition, the correct class is almost always one of the two maximum outputs of the MLP. The second observation is that most of the errors consist of pairs of classes in which the characters have similarities (e.g. (U, V), (m, n), (O, Q), among others). Specialized local SVMs are introduced to detect the correct class among these two classification hypotheses. The hybrid MLP-SVM recognizer showed improvement, significant, in performance in terms of recognition rate compared with an MLP for a task of character recognition." @default.
- W2114790400 created "2016-06-24" @default.
- W2114790400 creator A5049490188 @default.
- W2114790400 creator A5062553332 @default.
- W2114790400 creator A5086345001 @default.
- W2114790400 date "2011-07-01" @default.
- W2114790400 modified "2023-09-23" @default.
- W2114790400 title "A MLP-SVM hybrid model for cursive handwriting recognition" @default.
- W2114790400 cites W101663867 @default.
- W2114790400 cites W1514142084 @default.
- W2114790400 cites W1566962711 @default.
- W2114790400 cites W1570688454 @default.
- W2114790400 cites W1587362683 @default.
- W2114790400 cites W1595901008 @default.
- W2114790400 cites W1608179252 @default.
- W2114790400 cites W1765205881 @default.
- W2114790400 cites W1987778768 @default.
- W2114790400 cites W1995930498 @default.
- W2114790400 cites W2003333103 @default.
- W2114790400 cites W2004734544 @default.
- W2114790400 cites W2017787659 @default.
- W2114790400 cites W2024986448 @default.
- W2114790400 cites W2039905248 @default.
- W2114790400 cites W2055075080 @default.
- W2114790400 cites W2056763477 @default.
- W2114790400 cites W2077151522 @default.
- W2114790400 cites W2087136607 @default.
- W2114790400 cites W2087347434 @default.
- W2114790400 cites W2091250638 @default.
- W2114790400 cites W2098154993 @default.
- W2114790400 cites W2101286420 @default.
- W2114790400 cites W2101435584 @default.
- W2114790400 cites W2102734279 @default.
- W2114790400 cites W2105809105 @default.
- W2114790400 cites W2107704060 @default.
- W2114790400 cites W2114450867 @default.
- W2114790400 cites W2119761601 @default.
- W2114790400 cites W2121145809 @default.
- W2114790400 cites W2124776405 @default.
- W2114790400 cites W2125838338 @default.
- W2114790400 cites W2126297944 @default.
- W2114790400 cites W2127222719 @default.
- W2114790400 cites W2128446254 @default.
- W2114790400 cites W2140042332 @default.
- W2114790400 cites W2140494000 @default.
- W2114790400 cites W2142069714 @default.
- W2114790400 cites W2143908786 @default.
- W2114790400 cites W2148603752 @default.
- W2114790400 cites W2149298154 @default.
- W2114790400 cites W2149319679 @default.
- W2114790400 cites W2150884987 @default.
- W2114790400 cites W2152249014 @default.
- W2114790400 cites W2153635508 @default.
- W2114790400 cites W2162395775 @default.
- W2114790400 cites W2165313956 @default.
- W2114790400 cites W2169304450 @default.
- W2114790400 cites W2170275199 @default.
- W2114790400 cites W2562429148 @default.
- W2114790400 cites W2799061466 @default.
- W2114790400 cites W2945935110 @default.
- W2114790400 cites W3119651796 @default.
- W2114790400 doi "https://doi.org/10.1109/ijcnn.2011.6033309" @default.
- W2114790400 hasPublicationYear "2011" @default.
- W2114790400 type Work @default.
- W2114790400 sameAs 2114790400 @default.
- W2114790400 citedByCount "15" @default.
- W2114790400 countsByYear W21147904002012 @default.
- W2114790400 countsByYear W21147904002013 @default.
- W2114790400 countsByYear W21147904002014 @default.
- W2114790400 countsByYear W21147904002015 @default.
- W2114790400 countsByYear W21147904002016 @default.
- W2114790400 countsByYear W21147904002017 @default.
- W2114790400 countsByYear W21147904002018 @default.
- W2114790400 countsByYear W21147904002019 @default.
- W2114790400 countsByYear W21147904002021 @default.
- W2114790400 crossrefType "proceedings-article" @default.
- W2114790400 hasAuthorship W2114790400A5049490188 @default.
- W2114790400 hasAuthorship W2114790400A5062553332 @default.
- W2114790400 hasAuthorship W2114790400A5086345001 @default.
- W2114790400 hasConcept C112640561 @default.
- W2114790400 hasConcept C12267149 @default.
- W2114790400 hasConcept C153180895 @default.
- W2114790400 hasConcept C154945302 @default.
- W2114790400 hasConcept C179717631 @default.
- W2114790400 hasConcept C2778943297 @default.
- W2114790400 hasConcept C2779386606 @default.
- W2114790400 hasConcept C28490314 @default.
- W2114790400 hasConcept C41008148 @default.
- W2114790400 hasConcept C50644808 @default.
- W2114790400 hasConcept C52622490 @default.
- W2114790400 hasConcept C60908668 @default.
- W2114790400 hasConceptScore W2114790400C112640561 @default.
- W2114790400 hasConceptScore W2114790400C12267149 @default.
- W2114790400 hasConceptScore W2114790400C153180895 @default.
- W2114790400 hasConceptScore W2114790400C154945302 @default.
- W2114790400 hasConceptScore W2114790400C179717631 @default.
- W2114790400 hasConceptScore W2114790400C2778943297 @default.
- W2114790400 hasConceptScore W2114790400C2779386606 @default.
- W2114790400 hasConceptScore W2114790400C28490314 @default.
- W2114790400 hasConceptScore W2114790400C41008148 @default.