| 1. Identity statement | |
| Reference Type | Conference Paper (Conference Proceedings) |
| Site | sibgrapi.sid.inpe.br |
| Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
| Identifier | 6qtX3pFwXQZeBBx/wpAfU |
| Repository | sid.inpe.br/banon/2002/12.09.09.58 |
| Last Update | 2002:11.28.02.00.00 (UTC) administrator |
| Metadata Repository | sid.inpe.br/banon/2002/12.09.09.58.54 |
| Metadata Last Update | 2022:06.14.00.12.31 (UTC) administrator |
| DOI | 10.1109/SIBGRAPI.2001.963074 |
| Citation Key | GomesFish:2001:LeExPr |
| Title | Learning and extracting primal-sketch features in a log-polar image representation  |
| Year | 2001 |
| Access Date | 2024, Apr. 29 |
| Number of Files | 1 |
| Size | 734 KiB |
| 2. Context | |
| Author | 1 Gomes, Herman Martins 2 Fisher, Robert B. |
| Editor | Borges, Leandro Díbio Wu, Shin-Ting |
| Conference Name | Brazilian Symposium on Computer Graphics and Image Processing, 14 (SIBGRAPI) |
| Conference Location | Florianópolis, SC, Brazil |
| Date | 15-18 Oct. 2001 |
| Publisher | IEEE Computer Society |
| Publisher City | Los Alamitos |
| Pages | 338-345 |
| Book Title | Proceedings |
| Tertiary Type | Full Paper |
| Organization | SBC - Brazilian Computer Society |
| History (UTC) | 2008-07-17 14:10:55 :: administrator -> banon :: 2008-08-26 15:22:04 :: banon -> administrator :: 2009-08-13 20:37:21 :: administrator -> banon :: 2010-08-28 20:00:14 :: banon -> administrator :: 2022-06-14 00:12:31 :: administrator -> :: 2001 |
| 3. Content and structure | |
| Is the master or a copy? | is the master |
| Content Stage | completed |
| Transferable | 1 |
| Version Type | finaldraft |
| Keywords | feature extraction primal-sketch log-polar neural networks PCA |
| Abstract | This paper presents a novel and more successful learning based approach to extracting low level features in a retina-like (log-polar) image representation. The low level features (edges, bars, blobs and ends) are based on Marr's primal sketch hypothesis for the human visual system [10]. The feature extraction process used a neural network that learns examples of the features in a window of receptive fields of the image representation. An architecture designed to encode the feature's class, position, orientation and contrast has been proposed and tested. Success depended on the incorporation of a function to normalises the feature's orientation and a PCA pre-processing module to produce better separation in the feature space. |
| Arrangement 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2001 > Learning and extracting... |
| Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > Learning and extracting... |
| 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/6qtX3pFwXQZeBBx/wpAfU |
| zipped data URL | http://urlib.net/zip/6qtX3pFwXQZeBBx/wpAfU |
| Language | en |
| Target File | 338-345.pdf |
| User Group | administrator |
| Visibility | shown |
| 5. Allied materials | |
| Next Higher Units | 8JMKD3MGPEW34M/46Q6TJ5 8JMKD3MGPEW34M/4742MCS |
| Citing Item List | sid.inpe.br/sibgrapi/2022/04.29.19.35 7 |
| Host Collection | sid.inpe.br/banon/2001/03.30.15.38 |
| 6. Notes | |
| Notes | The conference was held in Florianópolis, SC, Brazil, from October 15 to 18. |
| Empty Fields | affiliation archivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage e-mailaddress edition electronicmailaddress format group isbn issn label lineage mark mirrorrepository nextedition numberofvolumes orcid parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume |