On-line one stroke character recognition using directional features

Autor:	Al, Murad, Amato, Ariel, Sánchez, Gemma, Gonzàlez, Jordi
Přispěvatelé:	Institut de Robòtica i Informàtica Industrial
Jazyk:	angličtina
Rok vydání:	2007
Předmět:	Visió per ordinador Computer vision Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo [Àrees temàtiques de la UPC] Pattern recognition::Computer vision [Classificació INSPEC]
Zdroj:	UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) Digital.CSIC. Repositorio Institucional del CSIC instname Recercat. Dipósit de la Recerca de Catalunya Universitat Jaume I Advances in Pattern Recognition ISBN: 9781846289446
Popis:	Presentado al International Workshop on Advances in Pattern Recognition celebrado en 2007 en Plymouth (U.K.). This paper presents a method based on directional features for recognizing on-line characters represented by one-stroke. A new alphabet is proposed, and each character is represented as a vector of directional angles. This vector is then considered as a path in a decision tree in order to reach the character. The advantages of this method lie in its computational efficiency and robustness to noise.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f98d39a084a3729356843f1410ea4a3a http://hdl.handle.net/2117/2765 Zobrazit plný text záznamu