Matches in SemOpenAlex for { <https://semopenalex.org/work/W2786326074> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2786326074 abstract "We propose a hierarchical CNN model for the recognition of confusable similar handwritten Chinese characters, which are automatically extracted from a large character set by utilizing a classifier's recognition result. The proposed hierarchical CNN model takes advantage of deep networks and traditional hierarchical methods, and consists of two stages, which are expected to differentiate inter-group characters and intra-group characters, respectively. Different from traditional ways of expanding depth and/or width of general sole classifier CNNs, we explore the way of designing multiple parallel CNN classifiers to capture critical regions of similar characters. Each classifier along with their feature extraction layers is trained only with a group of similar characters so that the subtle shape difference can be captured. Totally, 368 similar characters (categorized into 172 groups) are extracted from 3755 frequently used Chinese characters. Experimental results on these similar characters demonstrate the superiority of the proposed method to the expanded CNN models." @default.
- W2786326074 created "2018-02-23" @default.
- W2786326074 creator A5013039708 @default.
- W2786326074 creator A5080280424 @default.
- W2786326074 date "2017-11-01" @default.
- W2786326074 modified "2023-09-27" @default.
- W2786326074 title "Similar Handwritten Chinese Character Recognition Using Hierarchical CNN Model" @default.
- W2786326074 cites W1967517149 @default.
- W2786326074 cites W1978964824 @default.
- W2786326074 cites W2017424643 @default.
- W2786326074 cites W2041117400 @default.
- W2786326074 cites W2051740882 @default.
- W2786326074 cites W2077365163 @default.
- W2786326074 cites W2097117768 @default.
- W2786326074 cites W2112796928 @default.
- W2786326074 cites W2119305530 @default.
- W2786326074 cites W2131665084 @default.
- W2786326074 cites W2139881793 @default.
- W2786326074 cites W2145536544 @default.
- W2786326074 cites W2163605009 @default.
- W2786326074 cites W2170866695 @default.
- W2786326074 cites W2241038878 @default.
- W2786326074 cites W2368991465 @default.
- W2786326074 cites W2577821093 @default.
- W2786326074 cites W2916727894 @default.
- W2786326074 doi "https://doi.org/10.1109/icdar.2017.104" @default.
- W2786326074 hasPublicationYear "2017" @default.
- W2786326074 type Work @default.
- W2786326074 sameAs 2786326074 @default.
- W2786326074 citedByCount "7" @default.
- W2786326074 countsByYear W27863260742018 @default.
- W2786326074 countsByYear W27863260742019 @default.
- W2786326074 countsByYear W27863260742020 @default.
- W2786326074 countsByYear W27863260742021 @default.
- W2786326074 crossrefType "proceedings-article" @default.
- W2786326074 hasAuthorship W2786326074A5013039708 @default.
- W2786326074 hasAuthorship W2786326074A5080280424 @default.
- W2786326074 hasConcept C115961682 @default.
- W2786326074 hasConcept C124101348 @default.
- W2786326074 hasConcept C144986985 @default.
- W2786326074 hasConcept C153180895 @default.
- W2786326074 hasConcept C154945302 @default.
- W2786326074 hasConcept C2524010 @default.
- W2786326074 hasConcept C2780861071 @default.
- W2786326074 hasConcept C2781051154 @default.
- W2786326074 hasConcept C2987247673 @default.
- W2786326074 hasConcept C33923547 @default.
- W2786326074 hasConcept C41008148 @default.
- W2786326074 hasConcept C52622490 @default.
- W2786326074 hasConcept C95623464 @default.
- W2786326074 hasConceptScore W2786326074C115961682 @default.
- W2786326074 hasConceptScore W2786326074C124101348 @default.
- W2786326074 hasConceptScore W2786326074C144986985 @default.
- W2786326074 hasConceptScore W2786326074C153180895 @default.
- W2786326074 hasConceptScore W2786326074C154945302 @default.
- W2786326074 hasConceptScore W2786326074C2524010 @default.
- W2786326074 hasConceptScore W2786326074C2780861071 @default.
- W2786326074 hasConceptScore W2786326074C2781051154 @default.
- W2786326074 hasConceptScore W2786326074C2987247673 @default.
- W2786326074 hasConceptScore W2786326074C33923547 @default.
- W2786326074 hasConceptScore W2786326074C41008148 @default.
- W2786326074 hasConceptScore W2786326074C52622490 @default.
- W2786326074 hasConceptScore W2786326074C95623464 @default.
- W2786326074 hasLocation W27863260741 @default.
- W2786326074 hasOpenAccess W2786326074 @default.
- W2786326074 hasPrimaryLocation W27863260741 @default.
- W2786326074 hasRelatedWork W110699664 @default.
- W2786326074 hasRelatedWork W1602483886 @default.
- W2786326074 hasRelatedWork W1978774908 @default.
- W2786326074 hasRelatedWork W2018887828 @default.
- W2786326074 hasRelatedWork W2048307847 @default.
- W2786326074 hasRelatedWork W2052873705 @default.
- W2786326074 hasRelatedWork W2064377028 @default.
- W2786326074 hasRelatedWork W2096286511 @default.
- W2786326074 hasRelatedWork W2125792038 @default.
- W2786326074 hasRelatedWork W2187081581 @default.
- W2786326074 hasRelatedWork W2241038878 @default.
- W2786326074 hasRelatedWork W2752533414 @default.
- W2786326074 hasRelatedWork W2797468254 @default.
- W2786326074 hasRelatedWork W2997872943 @default.
- W2786326074 hasRelatedWork W3028834392 @default.
- W2786326074 hasRelatedWork W3040347307 @default.
- W2786326074 hasRelatedWork W3109674756 @default.
- W2786326074 hasRelatedWork W3127945299 @default.
- W2786326074 hasRelatedWork W3134611004 @default.
- W2786326074 hasRelatedWork W3196149871 @default.
- W2786326074 isParatext "false" @default.
- W2786326074 isRetracted "false" @default.
- W2786326074 magId "2786326074" @default.
- W2786326074 workType "article" @default.