1. Identity statement | |
Reference Type | Slides (Audiovisual Material) |
Site | mtc-m21b.sid.inpe.br |
Holder Code | isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S |
Identifier | 83LX3pFwXQZ3qyBY/RL3kk |
Repository | dpi.inpe.br/ismm@80/2007/10.14.17.43 |
Last Update | 2007:10.14.17.43.32 (UTC) administrator |
Metadata Repository | dpi.inpe.br/ismm@80/2007/10.14.17.43.33 |
Metadata Last Update | 2021:09.16.02.55.17 (UTC) administrator |
Citation Key | PapaFalMirSuzMas:2007:DeRoPa |
Title | Design of robust pattern classifiers based on optimum-path forests |
Short Title | Slides |
Format | Printed, On-line. |
Year | 2007 |
Access Date | 2024, May 19 |
Secondary Type | CI |
Number of Files | 1 |
Size | 528 KiB |
|
2. Context | |
Author | 1 Papa, João Paulo 2 Falcão, Alexandre X. 3 Miranda, Paulo A. V. 4 Suzuki, Celso T. N. 5 Mascarenhas, Nelson D. A. |
e-Mail Address | afalcao@ic.unicamp.br |
Conference Name | International Symposium on Mathematical Morphology, 8 (ISMM). |
Conference Location | Rio de Janeiro |
Date | Oct. 2007 |
Publisher | Instituto Nacional de Pesquisas Espaciais (INPE) |
Publisher City | São José dos Campos |
Tertiary Type | Full Paper |
Progress | Camera-ready paper submission |
History (UTC) | 2021-09-16 02:55:17 :: administrator -> afalcao@ic.unicamp.br :: 2007 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Keywords | supervised classifiers image foresting transform image analysis pattern recognition |
Abstract | We present a supervised pattern classifier based on optimum path forest. The samples in a training set are nodes of a complete graph, whose arcs are weighted by the distances between sample feature vectors. The training builds a classifier from key samples (prototypes) of all classes, where each prototype defines an optimum path tree whose nodes are its strongest connected samples. The optimum paths are also considered to label unseen test samples with the classes of their strongest connected prototypes. We show how to find prototypes with none classification errors in the training set and propose a learning algorithm to improve accuracy over an evaluation set. The method is robust to outliers, handles non-separable classes, and can outperform support vector machines. |
Area | SRE |
Subject | Morphological pattern recognition |
Session | including |
Type | Watershed segmentation |
Arrangement | Design of robust... > Slides |
doc Directory Content | access |
source Directory Content | there are no files |
agreement Directory Content | there are no files |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/83LX3pFwXQZ3qyBY/RL3kk |
zipped data URL | http://urlib.net/zip/83LX3pFwXQZ3qyBY/RL3kk |
Language | en |
Target File | papa_opf.pdf |
User Group | afalcao@ic.unicamp.br administrator |
Visibility | shown |
|
5. Allied materials | |
Mirror Repository | iconet.com.br/banon/2007/01.10.09.37 |
Next Higher Units | 83LX3pFwXQZ3qyBY/PKn22 |
Host Collection | dpi.inpe.br/hermes2@80/2006/05.03.12.24 sid.inpe.br/mtc-m21b/2013/09.26.14.25.20 |
|
6. Notes | |
Mark | 1 |
Empty Fields | affiliation archivingpolicy archivist booktitle callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi electronicmailaddress group isbn issn label lineage nextedition notes numberofslides orcid parameterlist parentrepositories previousedition previouslowerunit project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark sponsor tertiarymark url versiontype volume |
|