Training PDMS on models: the case of deformable superellipses
Abstract: "This paper addresses the following problem: How can we make a complicated mathematical shape model simpler while keeping a comparable level of representational power? The proposed solution is to use the original model itself -- which represents a class of shapes -- to train a Point D...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Edinburgh
1996
|
| Schriftenreihe: | University <Edinburgh> / Department of Artificial Intelligence: DAI research paper
8189 |
| Schlagworte: | |
| Zusammenfassung: | Abstract: "This paper addresses the following problem: How can we make a complicated mathematical shape model simpler while keeping a comparable level of representational power? The proposed solution is to use the original model itself -- which represents a class of shapes -- to train a Point Distribution Model. In this paper the idea is applied to the case of deformable superellipses." |
| Beschreibung: | [10] S. |
Internformat
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV011050091 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | t | ||
| 008 | 961111s1996 |||| 00||| engod | ||
| 035 | |a (OCoLC)36466380 | ||
| 035 | |a (DE-599)BVBBV011050091 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-91G | ||
| 100 | 1 | |a Pilu, Maurizio |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Training PDMS on models |b the case of deformable superellipses |c Pilu, M. ; Fitzgibbon, A. W. ; Fisher, R. B. |
| 264 | 1 | |a Edinburgh |c 1996 | |
| 300 | |a [10] S. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a University <Edinburgh> / Department of Artificial Intelligence: DAI research paper |v 8189 | |
| 520 | 3 | |a Abstract: "This paper addresses the following problem: How can we make a complicated mathematical shape model simpler while keeping a comparable level of representational power? The proposed solution is to use the original model itself -- which represents a class of shapes -- to train a Point Distribution Model. In this paper the idea is applied to the case of deformable superellipses." | |
| 650 | 7 | |a Pattern recognition, image processing and remote sensing |2 sigle | |
| 650 | 4 | |a Computer graphics | |
| 650 | 4 | |a Computer vision | |
| 650 | 4 | |a Ellipse | |
| 650 | 4 | |a Machine learning | |
| 700 | 1 | |a Fitzgibbon, Andrew W. |e Verfasser |4 aut | |
| 700 | 1 | |a Fisher, Robert B. |e Verfasser |4 aut | |
| 810 | 2 | |a Department of Artificial Intelligence: DAI research paper |t University <Edinburgh> |v 8189 |w (DE-604)BV010450646 |9 8189 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-007400488 | ||
Datensatz im Suchindex
| _version_ | 1804125539928113152 |
|---|---|
| any_adam_object | |
| author | Pilu, Maurizio Fitzgibbon, Andrew W. Fisher, Robert B. |
| author_facet | Pilu, Maurizio Fitzgibbon, Andrew W. Fisher, Robert B. |
| author_role | aut aut aut |
| author_sort | Pilu, Maurizio |
| author_variant | m p mp a w f aw awf r b f rb rbf |
| building | Verbundindex |
| bvnumber | BV011050091 |
| ctrlnum | (OCoLC)36466380 (DE-599)BVBBV011050091 |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01635nam a2200361 cb4500</leader><controlfield tag="001">BV011050091</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">961111s1996 |||| 00||| engod</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)36466380</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV011050091</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-91G</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Pilu, Maurizio</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Training PDMS on models</subfield><subfield code="b">the case of deformable superellipses</subfield><subfield code="c">Pilu, M. ; Fitzgibbon, A. W. ; Fisher, R. B.</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Edinburgh</subfield><subfield code="c">1996</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">[10] S.</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">University <Edinburgh> / Department of Artificial Intelligence: DAI research paper</subfield><subfield code="v">8189</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "This paper addresses the following problem: How can we make a complicated mathematical shape model simpler while keeping a comparable level of representational power? The proposed solution is to use the original model itself -- which represents a class of shapes -- to train a Point Distribution Model. In this paper the idea is applied to the case of deformable superellipses."</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Pattern recognition, image processing and remote sensing</subfield><subfield code="2">sigle</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Computer graphics</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Computer vision</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Ellipse</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Fitzgibbon, Andrew W.</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Fisher, Robert B.</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="810" ind1="2" ind2=" "><subfield code="a">Department of Artificial Intelligence: DAI research paper</subfield><subfield code="t">University <Edinburgh></subfield><subfield code="v">8189</subfield><subfield code="w">(DE-604)BV010450646</subfield><subfield code="9">8189</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-007400488</subfield></datafield></record></collection> |
| id | DE-604.BV011050091 |
| illustrated | Not Illustrated |
| indexdate | 2024-07-09T18:03:10Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-007400488 |
| oclc_num | 36466380 |
| open_access_boolean | |
| owner | DE-91G DE-BY-TUM |
| owner_facet | DE-91G DE-BY-TUM |
| physical | [10] S. |
| publishDate | 1996 |
| publishDateSearch | 1996 |
| publishDateSort | 1996 |
| record_format | marc |
| series2 | University <Edinburgh> / Department of Artificial Intelligence: DAI research paper |
| spelling | Pilu, Maurizio Verfasser aut Training PDMS on models the case of deformable superellipses Pilu, M. ; Fitzgibbon, A. W. ; Fisher, R. B. Edinburgh 1996 [10] S. txt rdacontent n rdamedia nc rdacarrier University <Edinburgh> / Department of Artificial Intelligence: DAI research paper 8189 Abstract: "This paper addresses the following problem: How can we make a complicated mathematical shape model simpler while keeping a comparable level of representational power? The proposed solution is to use the original model itself -- which represents a class of shapes -- to train a Point Distribution Model. In this paper the idea is applied to the case of deformable superellipses." Pattern recognition, image processing and remote sensing sigle Computer graphics Computer vision Ellipse Machine learning Fitzgibbon, Andrew W. Verfasser aut Fisher, Robert B. Verfasser aut Department of Artificial Intelligence: DAI research paper University <Edinburgh> 8189 (DE-604)BV010450646 8189 |
| spellingShingle | Pilu, Maurizio Fitzgibbon, Andrew W. Fisher, Robert B. Training PDMS on models the case of deformable superellipses Pattern recognition, image processing and remote sensing sigle Computer graphics Computer vision Ellipse Machine learning |
| title | Training PDMS on models the case of deformable superellipses |
| title_auth | Training PDMS on models the case of deformable superellipses |
| title_exact_search | Training PDMS on models the case of deformable superellipses |
| title_full | Training PDMS on models the case of deformable superellipses Pilu, M. ; Fitzgibbon, A. W. ; Fisher, R. B. |
| title_fullStr | Training PDMS on models the case of deformable superellipses Pilu, M. ; Fitzgibbon, A. W. ; Fisher, R. B. |
| title_full_unstemmed | Training PDMS on models the case of deformable superellipses Pilu, M. ; Fitzgibbon, A. W. ; Fisher, R. B. |
| title_short | Training PDMS on models |
| title_sort | training pdms on models the case of deformable superellipses |
| title_sub | the case of deformable superellipses |
| topic | Pattern recognition, image processing and remote sensing sigle Computer graphics Computer vision Ellipse Machine learning |
| topic_facet | Pattern recognition, image processing and remote sensing Computer graphics Computer vision Ellipse Machine learning |
| volume_link | (DE-604)BV010450646 |
| work_keys_str_mv | AT pilumaurizio trainingpdmsonmodelsthecaseofdeformablesuperellipses AT fitzgibbonandreww trainingpdmsonmodelsthecaseofdeformablesuperellipses AT fisherrobertb trainingpdmsonmodelsthecaseofdeformablesuperellipses |