Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003258286> ?p ?o ?g. }
- W3003258286 abstract "In the field of online handwritten signature verification, it is challenging to verify handwritten signature in a writer-independent scenario. In recent years, many researchers have been applying deep neural network methods to the signature verification task. However, these methods have not outperformed traditional methods, especially when the training samples are limited. In this paper, we propose a novel stroke-based bidirectional RNN architecture. The main idea is to split the signature into multiple patches using strokes. Concatenation of query and reference signature pairs are used as input. The proposed method uses two LSTM RNN networks to extract different features. The first one extracts the features of the strokes and the latter extracts the global features of the whole signatures. The results on the BiosecureID dataset demonstrate that our proposed method can reduce the EER by 33.05%, from 5.6% to 3.75% with fewer features and less training samples. Besides, we find that the proposed stroke based RNN network is 5x faster in training and testing time than Non stroke-based RNN network." @default.
- W3003258286 created "2020-02-07" @default.
- W3003258286 creator A5014808139 @default.
- W3003258286 creator A5043330057 @default.
- W3003258286 creator A5050803462 @default.
- W3003258286 creator A5064418389 @default.
- W3003258286 creator A5065037360 @default.
- W3003258286 creator A5077729205 @default.
- W3003258286 creator A5078315542 @default.
- W3003258286 date "2019-09-01" @default.
- W3003258286 modified "2023-10-10" @default.
- W3003258286 title "A Stroke-Based RNN for Writer-Independent Online Signature Verification" @default.
- W3003258286 cites W1523003285 @default.
- W3003258286 cites W1955055330 @default.
- W3003258286 cites W1968527039 @default.
- W3003258286 cites W1997460147 @default.
- W3003258286 cites W2053297268 @default.
- W3003258286 cites W2053438338 @default.
- W3003258286 cites W2055925964 @default.
- W3003258286 cites W2059529849 @default.
- W3003258286 cites W2064675550 @default.
- W3003258286 cites W2080936997 @default.
- W3003258286 cites W2082199161 @default.
- W3003258286 cites W2102882759 @default.
- W3003258286 cites W2105881518 @default.
- W3003258286 cites W2109255472 @default.
- W3003258286 cites W2127589108 @default.
- W3003258286 cites W2132012710 @default.
- W3003258286 cites W2133656308 @default.
- W3003258286 cites W2137775294 @default.
- W3003258286 cites W2140842482 @default.
- W3003258286 cites W2142069714 @default.
- W3003258286 cites W2149340496 @default.
- W3003258286 cites W2170942820 @default.
- W3003258286 cites W2505608010 @default.
- W3003258286 cites W2560609153 @default.
- W3003258286 cites W2766047310 @default.
- W3003258286 cites W2783471871 @default.
- W3003258286 cites W2790266980 @default.
- W3003258286 cites W2883497455 @default.
- W3003258286 cites W2889254994 @default.
- W3003258286 cites W2911424601 @default.
- W3003258286 cites W4229757486 @default.
- W3003258286 doi "https://doi.org/10.1109/icdar.2019.00090" @default.
- W3003258286 hasPublicationYear "2019" @default.
- W3003258286 type Work @default.
- W3003258286 sameAs 3003258286 @default.
- W3003258286 citedByCount "14" @default.
- W3003258286 countsByYear W30032582862021 @default.
- W3003258286 countsByYear W30032582862022 @default.
- W3003258286 countsByYear W30032582862023 @default.
- W3003258286 crossrefType "proceedings-article" @default.
- W3003258286 hasAuthorship W3003258286A5014808139 @default.
- W3003258286 hasAuthorship W3003258286A5043330057 @default.
- W3003258286 hasAuthorship W3003258286A5050803462 @default.
- W3003258286 hasAuthorship W3003258286A5064418389 @default.
- W3003258286 hasAuthorship W3003258286A5065037360 @default.
- W3003258286 hasAuthorship W3003258286A5077729205 @default.
- W3003258286 hasAuthorship W3003258286A5078315542 @default.
- W3003258286 hasConcept C112640561 @default.
- W3003258286 hasConcept C114614502 @default.
- W3003258286 hasConcept C119857082 @default.
- W3003258286 hasConcept C147168706 @default.
- W3003258286 hasConcept C153180895 @default.
- W3003258286 hasConcept C154945302 @default.
- W3003258286 hasConcept C162324750 @default.
- W3003258286 hasConcept C187736073 @default.
- W3003258286 hasConcept C2524010 @default.
- W3003258286 hasConcept C2779696439 @default.
- W3003258286 hasConcept C2780451532 @default.
- W3003258286 hasConcept C28490314 @default.
- W3003258286 hasConcept C33923547 @default.
- W3003258286 hasConcept C41008148 @default.
- W3003258286 hasConcept C50644808 @default.
- W3003258286 hasConcept C52622490 @default.
- W3003258286 hasConcept C87619178 @default.
- W3003258286 hasConceptScore W3003258286C112640561 @default.
- W3003258286 hasConceptScore W3003258286C114614502 @default.
- W3003258286 hasConceptScore W3003258286C119857082 @default.
- W3003258286 hasConceptScore W3003258286C147168706 @default.
- W3003258286 hasConceptScore W3003258286C153180895 @default.
- W3003258286 hasConceptScore W3003258286C154945302 @default.
- W3003258286 hasConceptScore W3003258286C162324750 @default.
- W3003258286 hasConceptScore W3003258286C187736073 @default.
- W3003258286 hasConceptScore W3003258286C2524010 @default.
- W3003258286 hasConceptScore W3003258286C2779696439 @default.
- W3003258286 hasConceptScore W3003258286C2780451532 @default.
- W3003258286 hasConceptScore W3003258286C28490314 @default.
- W3003258286 hasConceptScore W3003258286C33923547 @default.
- W3003258286 hasConceptScore W3003258286C41008148 @default.
- W3003258286 hasConceptScore W3003258286C50644808 @default.
- W3003258286 hasConceptScore W3003258286C52622490 @default.
- W3003258286 hasConceptScore W3003258286C87619178 @default.
- W3003258286 hasLocation W30032582861 @default.
- W3003258286 hasOpenAccess W3003258286 @default.
- W3003258286 hasPrimaryLocation W30032582861 @default.
- W3003258286 hasRelatedWork W1901876059 @default.
- W3003258286 hasRelatedWork W1909427334 @default.
- W3003258286 hasRelatedWork W2070451454 @default.
- W3003258286 hasRelatedWork W2108136919 @default.