Parametrized SOMs for Hand Posture Reconstruction

التفاصيل البيبلوغرافية
العنوان: Parametrized SOMs for Hand Posture Reconstruction
المؤلفون: Nölker, Claudia, Ritter, Helge, Amari, Shun-Ichi, Giles, C. Lee, Gori, Marco, Piuri, Vincenzo
بيانات النشر: IEEE
سنة النشر: 2000
المجموعة: PUB - Publications at Bielefeld University
الوصف: Nölker C, Ritter H. Parametrized SOMs for Hand Posture Reconstruction. In: Amari S-I, Giles CL, Gori M, Piuri V, eds. Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN 2000). Vol 4 . Los Alamitos, CA: IEEE; 2000: 139-144. ; This paper describes the use of neural network for gesture recognition based on finger tips, a system that recognizes continuous hand postures from video images. Our approach yields a full identification of all finger joint angles. This allows a full reconstruction of the 3D hand shape, using an artificial hand model with 16 segments and 20 joint angles. The focus of the present paper is how to employ a parametrised SOM neural network for the inverse kinematics task to compute the angles of a hand model out of 3D positions of the fingertips. We show that this type of neural net does not only achieve excellent results from very few training examples, but also can be applied to uncommon data structures
نوع الوثيقة: conference object
report
اللغة: English
العلاقة: info:eu-repo/semantics/altIdentifier/issn/1098-7576; info:eu-repo/semantics/altIdentifier/isbn/0-7695-0619-4; https://pub.uni-bielefeld.de/record/2714768Test
الإتاحة: https://doi.org/10.1109/IJCNN.2000.860763Test
https://pub.uni-bielefeld.de/record/2714768Test
حقوق: info:eu-repo/semantics/closedAccess
رقم الانضمام: edsbas.95849E78
قاعدة البيانات: BASE
ResultId 1
Header edsbas
BASE
edsbas.95849E78
743
3
Conference
conference
743.024353027344
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsbas&AN=edsbas.95849E78&custid=s6537998&authtype=sso
FullText Array ( [Availability] => 0 )
Array ( [0] => Array ( [Url] => https://doi.org/10.1109/IJCNN.2000.860763# [Name] => EDS - BASE [Category] => fullText [Text] => View record in BASE [MouseOverText] => View record in BASE ) )
Items Array ( [Name] => Title [Label] => Title [Group] => Ti [Data] => Parametrized SOMs for Hand Posture Reconstruction )
Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22Nölker%2C+Claudia%22">Nölker, Claudia</searchLink><br /><searchLink fieldCode="AR" term="%22Ritter%2C+Helge%22">Ritter, Helge</searchLink><br /><searchLink fieldCode="AR" term="%22Amari%2C+Shun-Ichi%22">Amari, Shun-Ichi</searchLink><br /><searchLink fieldCode="AR" term="%22Giles%2C+C%2E+Lee%22">Giles, C. Lee</searchLink><br /><searchLink fieldCode="AR" term="%22Gori%2C+Marco%22">Gori, Marco</searchLink><br /><searchLink fieldCode="AR" term="%22Piuri%2C+Vincenzo%22">Piuri, Vincenzo</searchLink> )
Array ( [Name] => Publisher [Label] => Publisher Information [Group] => PubInfo [Data] => IEEE )
Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2000 )
Array ( [Name] => Subset [Label] => Collection [Group] => HoldingsInfo [Data] => PUB - Publications at Bielefeld University )
Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => Nölker C, Ritter H. Parametrized SOMs for Hand Posture Reconstruction. In: Amari S-I, Giles CL, Gori M, Piuri V, eds. Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN 2000). Vol 4 . Los Alamitos, CA: IEEE; 2000: 139-144. ; This paper describes the use of neural network for gesture recognition based on finger tips, a system that recognizes continuous hand postures from video images. Our approach yields a full identification of all finger joint angles. This allows a full reconstruction of the 3D hand shape, using an artificial hand model with 16 segments and 20 joint angles. The focus of the present paper is how to employ a parametrised SOM neural network for the inverse kinematics task to compute the angles of a hand model out of 3D positions of the fingertips. We show that this type of neural net does not only achieve excellent results from very few training examples, but also can be applied to uncommon data structures )
Array ( [Name] => TypeDocument [Label] => Document Type [Group] => TypDoc [Data] => conference object<br />report )
Array ( [Name] => Language [Label] => Language [Group] => Lang [Data] => English )
Array ( [Name] => NoteTitleSource [Label] => Relation [Group] => SrcInfo [Data] => info:eu-repo/semantics/altIdentifier/issn/1098-7576; info:eu-repo/semantics/altIdentifier/isbn/0-7695-0619-4; https://pub.uni-bielefeld.de/record/2714768 )
Array ( [Name] => URL [Label] => Availability [Group] => URL [Data] => https://doi.org/10.1109/IJCNN.2000.860763<br />https://pub.uni-bielefeld.de/record/2714768 )
Array ( [Name] => Copyright [Label] => Rights [Group] => Cpyrght [Data] => info:eu-repo/semantics/closedAccess )
Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsbas.95849E78 )
RecordInfo Array ( [BibEntity] => Array ( [Languages] => Array ( [0] => Array ( [Text] => English ) ) [Titles] => Array ( [0] => Array ( [TitleFull] => Parametrized SOMs for Hand Posture Reconstruction [Type] => main ) ) ) [BibRelationships] => Array ( [HasContributorRelationships] => Array ( [0] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Nölker, Claudia ) ) ) [1] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Ritter, Helge ) ) ) [2] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Amari, Shun-Ichi ) ) ) [3] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Giles, C. Lee ) ) ) [4] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Gori, Marco ) ) ) [5] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Piuri, Vincenzo ) ) ) ) [IsPartOfRelationships] => Array ( [0] => Array ( [BibEntity] => Array ( [Dates] => Array ( [0] => Array ( [D] => 01 [M] => 01 [Type] => published [Y] => 2000 ) ) [Identifiers] => Array ( [0] => Array ( [Type] => issn-locals [Value] => edsbas ) ) ) ) ) ) )
IllustrationInfo