Matches in SemOpenAlex for { <https://semopenalex.org/work/W3140300872> ?p ?o ?g. }
- W3140300872 endingPage "59627" @default.
- W3140300872 startingPage "59612" @default.
- W3140300872 abstract "This paper presents a novel Arabic Sign Language (ArSL) recognition system, using selected 2D hands and body key points from successive video frames. The system recognizes the recorded video signs, for both signer dependent and signer independent modes, using the concatenation of a 3D CNN skeleton network and a 2D point convolution network. To accomplish this, we built a new ArSL video-based sign database. We will present the detailed methodology of recording the new dataset, which comprises 80 static and dynamic signs that were repeated five times by 40 signers. The signs include Arabic alphabet, numbers, and some daily use signs. To facilitate building an online sign recognition system, we introduce the inverse efficiency score to find a sufficient optimal number of successive frames for the recognition decision, in order to cope with a near real-time automatic ArSL system, where tradeoff between accuracy and speed is crucial to avoid delayed sign classification. For the dependent mode, best results were obtained for dynamic signs with an accuracy of 98.39%, and 88.89% for the static signs, and for the independent mode, we obtained for the dynamic signs an accuracy of 96.69%, and 86.34% for the static signs. When both the static and dynamic signs were mixed and the system trained with all the signs, accuracies of 89.62% and 88.09% were obtained in the signer dependent and signer independent modes respectively." @default.
- W3140300872 created "2021-04-13" @default.
- W3140300872 creator A5006481522 @default.
- W3140300872 creator A5023424035 @default.
- W3140300872 creator A5043253462 @default.
- W3140300872 creator A5046817902 @default.
- W3140300872 creator A5047566160 @default.
- W3140300872 creator A5060389647 @default.
- W3140300872 creator A5069689023 @default.
- W3140300872 creator A5081962715 @default.
- W3140300872 date "2021-01-01" @default.
- W3140300872 modified "2023-10-12" @default.
- W3140300872 title "Arabic Sign Language Recognition System Using 2D Hands and Body Skeleton Data" @default.
- W3140300872 cites W1943054406 @default.
- W3140300872 cites W1969724184 @default.
- W3140300872 cites W1986228573 @default.
- W3140300872 cites W2023656757 @default.
- W3140300872 cites W2079802959 @default.
- W3140300872 cites W2083587404 @default.
- W3140300872 cites W2091781370 @default.
- W3140300872 cites W2126721694 @default.
- W3140300872 cites W2135909638 @default.
- W3140300872 cites W2159736522 @default.
- W3140300872 cites W2168392347 @default.
- W3140300872 cites W2240672634 @default.
- W3140300872 cites W2241299476 @default.
- W3140300872 cites W2302259492 @default.
- W3140300872 cites W2316731179 @default.
- W3140300872 cites W2405404034 @default.
- W3140300872 cites W2467634805 @default.
- W3140300872 cites W2511227366 @default.
- W3140300872 cites W2514067481 @default.
- W3140300872 cites W2552900565 @default.
- W3140300872 cites W2588652674 @default.
- W3140300872 cites W2590076343 @default.
- W3140300872 cites W2743239999 @default.
- W3140300872 cites W2747305119 @default.
- W3140300872 cites W2762032368 @default.
- W3140300872 cites W2766329439 @default.
- W3140300872 cites W2767899514 @default.
- W3140300872 cites W2783942756 @default.
- W3140300872 cites W2792060773 @default.
- W3140300872 cites W2792531223 @default.
- W3140300872 cites W2904518066 @default.
- W3140300872 cites W2906679066 @default.
- W3140300872 cites W2908550133 @default.
- W3140300872 cites W2914489644 @default.
- W3140300872 cites W2917550689 @default.
- W3140300872 cites W2918549176 @default.
- W3140300872 cites W2962730651 @default.
- W3140300872 cites W2963738673 @default.
- W3140300872 cites W3020922019 @default.
- W3140300872 cites W3022200071 @default.
- W3140300872 cites W3024516740 @default.
- W3140300872 cites W3028504508 @default.
- W3140300872 cites W3034765865 @default.
- W3140300872 cites W3035531123 @default.
- W3140300872 cites W3093820501 @default.
- W3140300872 cites W3106327734 @default.
- W3140300872 cites W4234939993 @default.
- W3140300872 doi "https://doi.org/10.1109/access.2021.3069714" @default.
- W3140300872 hasPublicationYear "2021" @default.
- W3140300872 type Work @default.
- W3140300872 sameAs 3140300872 @default.
- W3140300872 citedByCount "16" @default.
- W3140300872 countsByYear W31403008722021 @default.
- W3140300872 countsByYear W31403008722022 @default.
- W3140300872 countsByYear W31403008722023 @default.
- W3140300872 crossrefType "journal-article" @default.
- W3140300872 hasAuthorship W3140300872A5006481522 @default.
- W3140300872 hasAuthorship W3140300872A5023424035 @default.
- W3140300872 hasAuthorship W3140300872A5043253462 @default.
- W3140300872 hasAuthorship W3140300872A5046817902 @default.
- W3140300872 hasAuthorship W3140300872A5047566160 @default.
- W3140300872 hasAuthorship W3140300872A5060389647 @default.
- W3140300872 hasAuthorship W3140300872A5069689023 @default.
- W3140300872 hasAuthorship W3140300872A5081962715 @default.
- W3140300872 hasBestOaLocation W31403008721 @default.
- W3140300872 hasConcept C134306372 @default.
- W3140300872 hasConcept C138885662 @default.
- W3140300872 hasConcept C139676723 @default.
- W3140300872 hasConcept C153180895 @default.
- W3140300872 hasConcept C154945302 @default.
- W3140300872 hasConcept C18969341 @default.
- W3140300872 hasConcept C199360897 @default.
- W3140300872 hasConcept C204321447 @default.
- W3140300872 hasConcept C28490314 @default.
- W3140300872 hasConcept C31972630 @default.
- W3140300872 hasConcept C33923547 @default.
- W3140300872 hasConcept C41008148 @default.
- W3140300872 hasConcept C41895202 @default.
- W3140300872 hasConcept C522192633 @default.
- W3140300872 hasConcept C96455323 @default.
- W3140300872 hasConceptScore W3140300872C134306372 @default.
- W3140300872 hasConceptScore W3140300872C138885662 @default.
- W3140300872 hasConceptScore W3140300872C139676723 @default.
- W3140300872 hasConceptScore W3140300872C153180895 @default.
- W3140300872 hasConceptScore W3140300872C154945302 @default.