Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Last Update2015: (UTC)
Metadata Last Update2020: (UTC) administrator
Citation KeyCardenasCháv:2015:FiSpRe
TitleFinger Spelling Recognition from Depth data using Direction Cosines and Histogram of Cumulative Magnitudes
Access Date2022, Jan. 19
Number of Files1
Size1876 KiB
Context area
Author1 Cardenas, Edwin Jonathan Escobedo
2 Chávez, Guillermo Cámara
Affiliation1 Federal University of Ouro Preto
2 Federal University of Ouro Preto
EditorPapa, João Paulo
Sander, Pedro Vieira
Marroquim, Ricardo Guerra
Farrell, Ryan
Conference NameConference on Graphics, Patterns and Images, 28 (SIBGRAPI)
Conference LocationSalvador
DateAug. 26-29, 2015
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2015-06-19 21:16:30 :: -> administrator ::
2020-02-19 02:14:03 :: administrator -> :: 2015
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Content TypeExternal Contribution
KeywordsFinger spelling recognition
depth information
points cloud
directional cosines
support vector machine (SVM)
AbstractIn this paper, we propose a new approach for finger spelling recognition using depth information captured by Kinect sensor. We only use depth information to characterize hand configurations corresponding to alphabet letters. First, we use depth data to generate a binary hand mask which is used to segment the hand area from background. Then, the major hand axis is determined and aligned with Y axis in order to achieve rotation invariance. Later, we convert the depth data in a 3D point cloud. The point cloud is divided into subregions and in each one, using direction cosines, we calculated three histograms of cumulative magnitudes Hx, Hy and Hz corresponding to each axis. Finally, these histograms were concatenated and used as input to our Support Vector Machine (SVM) classifier. The performance of this approach is quantitatively and qualitatively evaluated on a dataset of real images of American Sign Language (ASL) hand shapes. The dataset used is composed of 60000 depth images. According to our experiments, our approach has an accuracy rate of 99.37%, outperforming other state-of-the-art methods. > SDLA > SIBGRAPI 2015 > Finger Spelling Recognition...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 19/06/2015 18:16 0.7 KiB 
Conditions of access and use area
data URL
zipped data URL
Target FilePID3771875.pdf
Update Permissionnot transferred
Allied materials area
Next Higher Units8JMKD3MGPBW34M/3K24PF8
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume