1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 6qtX3pFwXQZG2LgkFdY/URfSG |
Repository | sid.inpe.br/sibgrapi@80/2008/07.23.17.43 |
Last Update | 2008:09.23.13.10.04 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi@80/2008/07.23.17.43.49 |
Metadata Last Update | 2022:06.14.00.13.50 (UTC) administrator |
DOI | 10.1109/SIBGRAPI.2008.35 |
Citation Key | RibeiroHash:2008:NeTrAl |
Title | A New Training Algorithm for Pattern Recognition Technique Based on Straight Line Segments |
Format | Printed, On-line. |
Year | 2008 |
Access Date | 2024, May 02 |
Number of Files | 1 |
Size | 1077 KiB |
|
2. Context | |
Author | 1 Ribeiro, Joao Henrique Burckas 2 Hashimoto, Ronaldo Fumio |
Affiliation | 1 Institute of Mathematics and Statistics - University of Sao Paulo 2 Institute of Mathematics and Statistics - University of Sao Paulo |
Editor | Jung, Cláudio Rosito Walter, Marcelo |
e-Mail Address | ronaldo@ime.usp.br |
Conference Name | Brazilian Symposium on Computer Graphics and Image Processing, 21 (SIBGRAPI) |
Conference Location | Campo Grande, MS, Brazil |
Date | 12-15 Oct. 2008 |
Publisher | IEEE Computer Society |
Publisher City | Los Alamitos |
Book Title | Proceedings |
Tertiary Type | Full Paper |
History (UTC) | 2008-09-23 13:10:04 :: ronaldo@ime.usp.br -> administrator :: 2009-08-13 20:39:01 :: administrator -> ronaldo@ime.usp.br :: 2010-08-28 20:03:23 :: ronaldo@ime.usp.br -> administrator :: 2022-06-14 00:13:50 :: administrator -> :: 2008 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Version Type | finaldraft |
Keywords | Straight Line Segments Machine Learning Pattern Recognition Classification Support Vector Machine |
Abstract | Recently, a new Pattern Recognition technique based on straight line segments (SLSs) was presented. The key issue in this new technique is to find a function based on distances between points and two sets of SLSs that minimizes a certain error or risk criterion. An algorithm for solving this optimization problem is called training algorithm. Although this technique seems to be very promising, the first presented training algorithm is based on a heuristic. In fact, the search for this best function is a hard nonlinear optimization problem. In this paper, we present a new and improved training algorithm for the SLS technique based on gradient descent optimization method. We have applied this new training algorithm to artificial and public data sets and their results confirm the improvement of this methodology.. |
Arrangement 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2008 > A New Training... |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > A New Training... |
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/6qtX3pFwXQZG2LgkFdY/URfSG |
zipped data URL | http://urlib.net/zip/6qtX3pFwXQZG2LgkFdY/URfSG |
Language | en |
Target File | sibgrapi2008_sls.pdf |
User Group | ronaldo@ime.usp.br administrator |
Visibility | shown |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPEW34M/46SG4TH 8JMKD3MGPEW34M/4742MCS |
Citing Item List | sid.inpe.br/sibgrapi/2022/05.14.04.55 2 |
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 documentstage 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 |
|