1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPBW34M/3JMP57H |
Repository | sid.inpe.br/sibgrapi/2015/06.19.22.01 |
Last Update | 2015:06.19.22.01.36 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2015/06.19.22.01.36 |
Metadata Last Update | 2022:06.14.00.08.13 (UTC) administrator |
DOI | 10.1109/SIBGRAPI.2015.17 |
Citation Key | JacquesJrMuss:2015:ImHeHu |
Title | Improved head-shoulder human contour estimation through clusters of learned shape models |
Format | On-line |
Year | 2015 |
Access Date | 2024, May 05 |
Number of Files | 1 |
Size | 4654 KiB |
|
2. Context | |
Author | 1 Jacques Junior, Julio Cezar Silveira 2 Musse, Soraia Raupp |
Affiliation | 1 Pontifícia Universidade Católica do Rio Grande do Sul 2 Pontifícia Universidade Católica do Rio Grande do Sul |
Editor | Papa, João Paulo Sander, Pedro Vieira Marroquim, Ricardo Guerra Farrell, Ryan |
e-Mail Address | juliojj@gmail.com |
Conference Name | Conference on Graphics, Patterns and Images, 28 (SIBGRAPI) |
Conference Location | Salvador, BA, Brazil |
Date | 26-29 Aug. 2015 |
Publisher | IEEE Computer Society |
Publisher City | Los Alamitos |
Book Title | Proceedings |
Tertiary Type | Full Paper |
History (UTC) | 2015-06-19 22:01:36 :: juliojj@gmail.com -> administrator :: 2022-06-14 00:08:13 :: administrator -> :: 2015 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Version Type | finaldraft |
Keywords | human head-shoulder estimation omega-shaped region human segmentation |
Abstract | In this paper we propose a clustering-based learning approach to improve an existing model for human head-shoulder contour estimation. The contour estimation is guided by a learned head-shoulder shape model, initialized automatically by a face detector. A dataset with labeled data is used to create the headshoulder shape model and to quantitatively analyze the results. In the proposed approach, geometric features are firstly extracted from the learning dataset. Then, the number of shape models to be learned is obtained by an unsupervised clustering algorithm. In the segmentation stage, different graphs with an omega-like shape are built around the detected face, related to each learned shape model. A path with maximal cost, related to each graph, defines a initial estimative of the head-shoulder contour. The final estimation is given by the path with maximum average energy. Experimental results indicate that the proposed technique outperformed the original model, which is based on a single shape model, learned in a more simple way. In addition, it achieved comparable accuracy to other state-of-the-art models. |
Arrangement 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2015 > Improved head-shoulder human... |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > Improved head-shoulder human... |
doc Directory Content | access |
source Directory Content | there are no files |
agreement Directory Content | |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/8JMKD3MGPBW34M/3JMP57H |
zipped data URL | http://urlib.net/zip/8JMKD3MGPBW34M/3JMP57H |
Language | en |
Target File | sib2015-camera-ready-pdf-express.pdf |
User Group | juliojj@gmail.com |
Visibility | shown |
Update Permission | not transferred |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPBW34M/3K24PF8 8JMKD3MGPEW34M/4742MCS |
Citing Item List | sid.inpe.br/sibgrapi/2015/08.03.22.49 9 |
Host Collection | sid.inpe.br/banon/2001/03.30.15.38 |
|
6. Notes | |
Empty Fields | archivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume |
|