FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2907983487> ?p ?o ?g. }

• W2907983487 abstract "Recognizing Bangla compound characters is a challenging problem due to its high curly nature. In this paper, we propose a convolutional neural network (CNN) architecture to recognize handwritten Bangla compound characters. The learning of proposed architecture is done in two phase. In the first phase, a CNN is trained in an unsupervised way to minimize the reconstruction loss. Afterward, these weights are used to initialize the starting layers of second CNN to reduce the recognition loss through supervised learning. The effectiveness of the proposed model is validated on compound character dataset CMATERdb 3.1.3.3, which consists of 171 different character classes. It achieves recognition results of 93.90% and 97.37 % in top 1 and top 2 choices. The recognition performance outperforms state-of-the-art method for handwritten Bangla compound characters by a margin of 3.57%." @default.
• W2907983487 created "2019-01-11" @default.
• W2907983487 creator A5032100914 @default.
• W2907983487 creator A5036208317 @default.
• W2907983487 creator A5070077567 @default.
• W2907983487 date "2017-12-01" @default.
• W2907983487 modified "2023-09-25" @default.
• W2907983487 title "A two phase trained Convolutional Neural Network for Handwritten Bangla Compound Character Recognition" @default.
• W2907983487 cites W1686810756 @default.
• W2907983487 cites W178119708 @default.
• W2907983487 cites W1836465849 @default.
• W2907983487 cites W1972624583 @default.
• W2907983487 cites W1989725585 @default.
• W2907983487 cites W2016018404 @default.
• W2907983487 cites W2038235322 @default.
• W2907983487 cites W2081266874 @default.
• W2907983487 cites W2097117768 @default.
• W2907983487 cites W2106382161 @default.
• W2907983487 cites W2125792038 @default.
• W2907983487 cites W2130851192 @default.
• W2907983487 cites W2133059825 @default.
• W2907983487 cites W2138309322 @default.
• W2907983487 cites W2163605009 @default.
• W2907983487 cites W2166494748 @default.
• W2907983487 cites W2177066871 @default.
• W2907983487 cites W2282186389 @default.
• W2907983487 cites W2324044936 @default.
• W2907983487 cites W2338128728 @default.
• W2907983487 cites W2474199164 @default.
• W2907983487 cites W2592852541 @default.
• W2907983487 cites W6908809 @default.
• W2907983487 cites W137719152 @default.
• W2907983487 doi "https://doi.org/10.1109/icapr.2017.8592983" @default.
• W2907983487 hasPublicationYear "2017" @default.
• W2907983487 type Work @default.
• W2907983487 sameAs 2907983487 @default.
• W2907983487 citedByCount "2" @default.
• W2907983487 countsByYear W29079834872019 @default.
• W2907983487 countsByYear W29079834872020 @default.
• W2907983487 crossrefType "proceedings-article" @default.
• W2907983487 hasAuthorship W2907983487A5032100914 @default.
• W2907983487 hasAuthorship W2907983487A5036208317 @default.
• W2907983487 hasAuthorship W2907983487A5070077567 @default.
• W2907983487 hasConcept C108583219 @default.
• W2907983487 hasConcept C115961682 @default.
• W2907983487 hasConcept C119857082 @default.
• W2907983487 hasConcept C121144440 @default.
• W2907983487 hasConcept C153180895 @default.
• W2907983487 hasConcept C154945302 @default.
• W2907983487 hasConcept C17649283 @default.
• W2907983487 hasConcept C19235068 @default.
• W2907983487 hasConcept C2524010 @default.
• W2907983487 hasConcept C2780861071 @default.
• W2907983487 hasConcept C28490314 @default.
• W2907983487 hasConcept C2987247673 @default.
• W2907983487 hasConcept C33923547 @default.
• W2907983487 hasConcept C41008148 @default.
• W2907983487 hasConcept C44868376 @default.
• W2907983487 hasConcept C50644808 @default.
• W2907983487 hasConcept C774472 @default.
• W2907983487 hasConcept C81363708 @default.
• W2907983487 hasConceptScore W2907983487C108583219 @default.
• W2907983487 hasConceptScore W2907983487C115961682 @default.
• W2907983487 hasConceptScore W2907983487C119857082 @default.
• W2907983487 hasConceptScore W2907983487C121144440 @default.
• W2907983487 hasConceptScore W2907983487C153180895 @default.
• W2907983487 hasConceptScore W2907983487C154945302 @default.
• W2907983487 hasConceptScore W2907983487C17649283 @default.
• W2907983487 hasConceptScore W2907983487C19235068 @default.
• W2907983487 hasConceptScore W2907983487C2524010 @default.
• W2907983487 hasConceptScore W2907983487C2780861071 @default.
• W2907983487 hasConceptScore W2907983487C28490314 @default.
• W2907983487 hasConceptScore W2907983487C2987247673 @default.
• W2907983487 hasConceptScore W2907983487C33923547 @default.
• W2907983487 hasConceptScore W2907983487C41008148 @default.
• W2907983487 hasConceptScore W2907983487C44868376 @default.
• W2907983487 hasConceptScore W2907983487C50644808 @default.
• W2907983487 hasConceptScore W2907983487C774472 @default.
• W2907983487 hasConceptScore W2907983487C81363708 @default.
• W2907983487 hasLocation W29079834871 @default.
• W2907983487 hasOpenAccess W2907983487 @default.
• W2907983487 hasPrimaryLocation W29079834871 @default.
• W2907983487 hasRelatedWork W1963855343 @default.
• W2907983487 hasRelatedWork W2024801809 @default.
• W2907983487 hasRelatedWork W2127679938 @default.
• W2907983487 hasRelatedWork W2776151222 @default.
• W2907983487 hasRelatedWork W2777699623 @default.
• W2907983487 hasRelatedWork W2795084411 @default.
• W2907983487 hasRelatedWork W2811354442 @default.
• W2907983487 hasRelatedWork W2890316187 @default.
• W2907983487 hasRelatedWork W2912824652 @default.
• W2907983487 hasRelatedWork W2939633972 @default.
• W2907983487 hasRelatedWork W2979533666 @default.
• W2907983487 hasRelatedWork W2979811101 @default.
• W2907983487 hasRelatedWork W2995191530 @default.
• W2907983487 hasRelatedWork W3013903454 @default.
• W2907983487 hasRelatedWork W3094464553 @default.
• W2907983487 hasRelatedWork W3127945299 @default.
• W2907983487 hasRelatedWork W3139768462 @default.
• W2907983487 hasRelatedWork W3151571032 @default.

• next