FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3166229457> ?p ?o ?g. }

• W3166229457 endingPage "55" @default.
• W3166229457 startingPage "41" @default.
• W3166229457 abstract "<abstract> Handwritten grapheme recognition is popular research in computer vision and now widespread in the commercial industry due to its large number of applications in document analysis and recognition. Bengali grapheme classification is a complex task as it has 49 letters and 18 potential diacritics with almost 13,000 possible variations. Bengali is now the fifth most spoken native language and the seventh most spoken language by the total number of speakers in the world. Having set a bigger scope, this paper deals with the recognition of Bengali handwritten script letters. A class of deep Convolutional Neural Networks (CNNs) with encoder-decoder is used to classify handwritten letters. We use several serial non-linear layers as the encoders and a corresponding set of decoders that work as a pixel-wise classifier for letter recognition. The key idea is to encode images by convolution and decode them by deconvolution so that the max-pooling and up-sampling layers can correctly identify grapheme pixel-by-pixel. In this study, almost 200,840 grapheme images were analyzed, including root, vowels, and consonants. A large number of variations make additional complexity in recognition and may lead the model into over-fitting or under-fitting. We introduce regularization techniques to reduce the over-fitting in the fully connected layers. The results suggest that CNN with encoder-decoder can recognize complex grapheme characters with higher precision than traditional CNN. Experimental results show that the images' augmentation helps the model train better and improves its accuracy and loss. </abstract>" @default.
• W3166229457 created "2021-06-22" @default.
• W3166229457 creator A5038957808 @default.
• W3166229457 creator A5046199069 @default.
• W3166229457 creator A5078191901 @default.
• W3166229457 date "2021-01-01" @default.
• W3166229457 modified "2023-09-24" @default.
• W3166229457 title "A convolution neural network with encoder-decoder applied to the study of Bengali letters classification" @default.
• W3166229457 cites W1954775015 @default.
• W3166229457 cites W1963855343 @default.
• W3166229457 cites W1973408529 @default.
• W3166229457 cites W1978426462 @default.
• W3166229457 cites W1994065256 @default.
• W3166229457 cites W1998582365 @default.
• W3166229457 cites W2004089144 @default.
• W3166229457 cites W2014056170 @default.
• W3166229457 cites W2094266213 @default.
• W3166229457 cites W2127472764 @default.
• W3166229457 cites W2129011250 @default.
• W3166229457 cites W2140001071 @default.
• W3166229457 cites W2142069714 @default.
• W3166229457 cites W2150477941 @default.
• W3166229457 cites W2409558506 @default.
• W3166229457 cites W2467139031 @default.
• W3166229457 cites W2561176188 @default.
• W3166229457 cites W2589608290 @default.
• W3166229457 cites W2592549397 @default.
• W3166229457 cites W2789876780 @default.
• W3166229457 cites W2796822032 @default.
• W3166229457 cites W2809598685 @default.
• W3166229457 cites W2901083258 @default.
• W3166229457 cites W2914337210 @default.
• W3166229457 cites W2940047913 @default.
• W3166229457 cites W2954027944 @default.
• W3166229457 cites W2963410977 @default.
• W3166229457 cites W2981052729 @default.
• W3166229457 cites W3009270141 @default.
• W3166229457 cites W3036010799 @default.
• W3166229457 cites W3081407480 @default.
• W3166229457 cites W3097969440 @default.
• W3166229457 cites W3108724972 @default.
• W3166229457 cites W3110648344 @default.
• W3166229457 cites W3131403268 @default.
• W3166229457 cites W3131485931 @default.
• W3166229457 cites W4239212332 @default.
• W3166229457 doi "https://doi.org/10.3934/bdia.2021004" @default.
• W3166229457 hasPublicationYear "2021" @default.
• W3166229457 type Work @default.
• W3166229457 sameAs 3166229457 @default.
• W3166229457 citedByCount "0" @default.
• W3166229457 crossrefType "journal-article" @default.
• W3166229457 hasAuthorship W3166229457A5038957808 @default.
• W3166229457 hasAuthorship W3166229457A5046199069 @default.
• W3166229457 hasAuthorship W3166229457A5078191901 @default.
• W3166229457 hasBestOaLocation W31662294571 @default.
• W3166229457 hasConcept C111919701 @default.
• W3166229457 hasConcept C118505674 @default.
• W3166229457 hasConcept C121332964 @default.
• W3166229457 hasConcept C153180895 @default.
• W3166229457 hasConcept C154945302 @default.
• W3166229457 hasConcept C160633673 @default.
• W3166229457 hasConcept C19235068 @default.
• W3166229457 hasConcept C2776779415 @default.
• W3166229457 hasConcept C28490314 @default.
• W3166229457 hasConcept C30080830 @default.
• W3166229457 hasConcept C41008148 @default.
• W3166229457 hasConcept C45347329 @default.
• W3166229457 hasConcept C50644808 @default.
• W3166229457 hasConcept C62520636 @default.
• W3166229457 hasConcept C81363708 @default.
• W3166229457 hasConcept C95623464 @default.
• W3166229457 hasConceptScore W3166229457C111919701 @default.
• W3166229457 hasConceptScore W3166229457C118505674 @default.
• W3166229457 hasConceptScore W3166229457C121332964 @default.
• W3166229457 hasConceptScore W3166229457C153180895 @default.
• W3166229457 hasConceptScore W3166229457C154945302 @default.
• W3166229457 hasConceptScore W3166229457C160633673 @default.
• W3166229457 hasConceptScore W3166229457C19235068 @default.
• W3166229457 hasConceptScore W3166229457C2776779415 @default.
• W3166229457 hasConceptScore W3166229457C28490314 @default.
• W3166229457 hasConceptScore W3166229457C30080830 @default.
• W3166229457 hasConceptScore W3166229457C41008148 @default.
• W3166229457 hasConceptScore W3166229457C45347329 @default.
• W3166229457 hasConceptScore W3166229457C50644808 @default.
• W3166229457 hasConceptScore W3166229457C62520636 @default.
• W3166229457 hasConceptScore W3166229457C81363708 @default.
• W3166229457 hasConceptScore W3166229457C95623464 @default.
• W3166229457 hasIssue "0" @default.
• W3166229457 hasLocation W31662294571 @default.
• W3166229457 hasOpenAccess W3166229457 @default.
• W3166229457 hasPrimaryLocation W31662294571 @default.
• W3166229457 hasRelatedWork W12014881 @default.
• W3166229457 hasRelatedWork W13625503 @default.
• W3166229457 hasRelatedWork W14456953 @default.
• W3166229457 hasRelatedWork W14579021 @default.
• W3166229457 hasRelatedWork W2582698 @default.
• W3166229457 hasRelatedWork W6364285 @default.
• W3166229457 hasRelatedWork W7120470 @default.

• next