Visuelles Erkennen von Objekten mit Ausprägungsvarianzen:
Computer, vision, computer vision, variances representation, hierarchy, layer, concept. - Computational visual object recognition has a big potential of application not only in the domain of automation technology, where visual object recognition is already established. A lot of other applications ar...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Abschlussarbeit Elektronisch E-Book |
| Sprache: | German |
| Veröffentlicht: |
2011
|
| Schlagworte: | |
| Online-Zugang: | kostenfrei |
| Zusammenfassung: | Computer, vision, computer vision, variances representation, hierarchy, layer, concept. - Computational visual object recognition has a big potential of application not only in the domain of automation technology, where visual object recognition is already established. A lot of other applications are imaginable, if more from the biological visual capabilities could be implemented. A special challenge consists in the recognition of real world objects having changing appearance. A universal object recognition system has to cope with that. However until now, it is unclear, which principles of functionality are used by biological object recognition. Scientific findings about that are still incomplete and allow no direct reproduction. Based on these findings, the only way to proceed is to assume principles of functionality and validate them in computational object recognition systems. In this contribution an explicit representation of changing appearance is investigated. For this purpose an object recognition system is built, which realises some new processing properties. The analysis of visual context is not realized with rigid filter masks as usual. Here context analysis is done by a new developed diffusion technique. The technique needs no pre-processing. A layer-wise representation of part objects with increasing complexity is built. For that no reduction of resolution is needed on the layers. A detection of a part object can depend on an arbitrary set of representations of underlying layers and not only from the one direct underlying. The evaluation of the object recognition system shows, that the explicit coding of changing appearance can be applied successfully. |
| Beschreibung: | 1 Online-Ressource |
Internformat
MARC
| LEADER | 00000nmm a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV041629021 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 006 | a m||| 00||| | ||
| 007 | cr|uuu---uuuuu | ||
| 008 | 140205s2011 |||| o||u| ||||||ger d | ||
| 035 | |a (OCoLC)873445858 | ||
| 035 | |a (DE-599)GBV680535403 | ||
| 040 | |a DE-604 |b ger | ||
| 041 | 0 | |a ger | |
| 049 | |a DE-384 |a DE-473 |a DE-703 |a DE-1051 |a DE-824 |a DE-29 |a DE-12 |a DE-91 |a DE-19 |a DE-1049 |a DE-92 |a DE-739 |a DE-898 |a DE-355 |a DE-706 |a DE-20 |a DE-1102 | ||
| 100 | 1 | |a Teichert, Jens |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Visuelles Erkennen von Objekten mit Ausprägungsvarianzen |c von Jens Teichert |
| 264 | 1 | |c 2011 | |
| 300 | |a 1 Online-Ressource | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b c |2 rdamedia | ||
| 338 | |b cr |2 rdacarrier | ||
| 502 | |a Bremen, Univ., Diss., 2011 | ||
| 520 | 8 | |a Computer, vision, computer vision, variances representation, hierarchy, layer, concept. - Computational visual object recognition has a big potential of application not only in the domain of automation technology, where visual object recognition is already established. A lot of other applications are imaginable, if more from the biological visual capabilities could be implemented. A special challenge consists in the recognition of real world objects having changing appearance. A universal object recognition system has to cope with that. However until now, it is unclear, which principles of functionality are used by biological object recognition. Scientific findings about that are still incomplete and allow no direct reproduction. Based on these findings, the only way to proceed is to assume principles of functionality and validate them in computational object recognition systems. In this contribution an explicit representation of changing appearance is investigated. For this purpose an object recognition system is built, which realises some new processing properties. The analysis of visual context is not realized with rigid filter masks as usual. Here context analysis is done by a new developed diffusion technique. The technique needs no pre-processing. A layer-wise representation of part objects with increasing complexity is built. For that no reduction of resolution is needed on the layers. A detection of a part object can depend on an arbitrary set of representations of underlying layers and not only from the one direct underlying. The evaluation of the object recognition system shows, that the explicit coding of changing appearance can be applied successfully. | |
| 655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
| 856 | 4 | 0 | |u https://nbn-resolving.org/urn:nbn:de:gbv:46-00102388-11 |x Verlag |z kostenfrei |3 Volltext |
| 912 | |a ebook | ||
| 999 | |a oai:aleph.bib-bvb.de:BVB01-027069975 | ||
Datensatz im Suchindex
| _version_ | 1804151846685638656 |
|---|---|
| any_adam_object | |
| author | Teichert, Jens |
| author_facet | Teichert, Jens |
| author_role | aut |
| author_sort | Teichert, Jens |
| author_variant | j t jt |
| building | Verbundindex |
| bvnumber | BV041629021 |
| collection | ebook |
| ctrlnum | (OCoLC)873445858 (DE-599)GBV680535403 |
| format | Thesis Electronic eBook |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02756nmm a2200313 c 4500</leader><controlfield tag="001">BV041629021</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="006">a m||| 00||| </controlfield><controlfield tag="007">cr|uuu---uuuuu</controlfield><controlfield tag="008">140205s2011 |||| o||u| ||||||ger d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)873445858</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)GBV680535403</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">ger</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-384</subfield><subfield code="a">DE-473</subfield><subfield code="a">DE-703</subfield><subfield code="a">DE-1051</subfield><subfield code="a">DE-824</subfield><subfield code="a">DE-29</subfield><subfield code="a">DE-12</subfield><subfield code="a">DE-91</subfield><subfield code="a">DE-19</subfield><subfield code="a">DE-1049</subfield><subfield code="a">DE-92</subfield><subfield code="a">DE-739</subfield><subfield code="a">DE-898</subfield><subfield code="a">DE-355</subfield><subfield code="a">DE-706</subfield><subfield code="a">DE-20</subfield><subfield code="a">DE-1102</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Teichert, Jens</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Visuelles Erkennen von Objekten mit Ausprägungsvarianzen</subfield><subfield code="c">von Jens Teichert</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2011</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">1 Online-Ressource</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">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="502" ind1=" " ind2=" "><subfield code="a">Bremen, Univ., Diss., 2011</subfield></datafield><datafield tag="520" ind1="8" ind2=" "><subfield code="a">Computer, vision, computer vision, variances representation, hierarchy, layer, concept. - Computational visual object recognition has a big potential of application not only in the domain of automation technology, where visual object recognition is already established. A lot of other applications are imaginable, if more from the biological visual capabilities could be implemented. A special challenge consists in the recognition of real world objects having changing appearance. A universal object recognition system has to cope with that. However until now, it is unclear, which principles of functionality are used by biological object recognition. Scientific findings about that are still incomplete and allow no direct reproduction. Based on these findings, the only way to proceed is to assume principles of functionality and validate them in computational object recognition systems. In this contribution an explicit representation of changing appearance is investigated. For this purpose an object recognition system is built, which realises some new processing properties. The analysis of visual context is not realized with rigid filter masks as usual. Here context analysis is done by a new developed diffusion technique. The technique needs no pre-processing. A layer-wise representation of part objects with increasing complexity is built. For that no reduction of resolution is needed on the layers. A detection of a part object can depend on an arbitrary set of representations of underlying layers and not only from the one direct underlying. The evaluation of the object recognition system shows, that the explicit coding of changing appearance can be applied successfully.</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4113937-9</subfield><subfield code="a">Hochschulschrift</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://nbn-resolving.org/urn:nbn:de:gbv:46-00102388-11</subfield><subfield code="x">Verlag</subfield><subfield code="z">kostenfrei</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ebook</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-027069975</subfield></datafield></record></collection> |
| genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
| genre_facet | Hochschulschrift |
| id | DE-604.BV041629021 |
| illustrated | Not Illustrated |
| indexdate | 2024-07-10T01:01:19Z |
| institution | BVB |
| language | German |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-027069975 |
| oclc_num | 873445858 |
| open_access_boolean | 1 |
| owner | DE-384 DE-473 DE-BY-UBG DE-703 DE-1051 DE-824 DE-29 DE-12 DE-91 DE-BY-TUM DE-19 DE-BY-UBM DE-1049 DE-92 DE-739 DE-898 DE-BY-UBR DE-355 DE-BY-UBR DE-706 DE-20 DE-1102 |
| owner_facet | DE-384 DE-473 DE-BY-UBG DE-703 DE-1051 DE-824 DE-29 DE-12 DE-91 DE-BY-TUM DE-19 DE-BY-UBM DE-1049 DE-92 DE-739 DE-898 DE-BY-UBR DE-355 DE-BY-UBR DE-706 DE-20 DE-1102 |
| physical | 1 Online-Ressource |
| psigel | ebook |
| publishDate | 2011 |
| publishDateSearch | 2011 |
| publishDateSort | 2011 |
| record_format | marc |
| spelling | Teichert, Jens Verfasser aut Visuelles Erkennen von Objekten mit Ausprägungsvarianzen von Jens Teichert 2011 1 Online-Ressource txt rdacontent c rdamedia cr rdacarrier Bremen, Univ., Diss., 2011 Computer, vision, computer vision, variances representation, hierarchy, layer, concept. - Computational visual object recognition has a big potential of application not only in the domain of automation technology, where visual object recognition is already established. A lot of other applications are imaginable, if more from the biological visual capabilities could be implemented. A special challenge consists in the recognition of real world objects having changing appearance. A universal object recognition system has to cope with that. However until now, it is unclear, which principles of functionality are used by biological object recognition. Scientific findings about that are still incomplete and allow no direct reproduction. Based on these findings, the only way to proceed is to assume principles of functionality and validate them in computational object recognition systems. In this contribution an explicit representation of changing appearance is investigated. For this purpose an object recognition system is built, which realises some new processing properties. The analysis of visual context is not realized with rigid filter masks as usual. Here context analysis is done by a new developed diffusion technique. The technique needs no pre-processing. A layer-wise representation of part objects with increasing complexity is built. For that no reduction of resolution is needed on the layers. A detection of a part object can depend on an arbitrary set of representations of underlying layers and not only from the one direct underlying. The evaluation of the object recognition system shows, that the explicit coding of changing appearance can be applied successfully. (DE-588)4113937-9 Hochschulschrift gnd-content https://nbn-resolving.org/urn:nbn:de:gbv:46-00102388-11 Verlag kostenfrei Volltext |
| spellingShingle | Teichert, Jens Visuelles Erkennen von Objekten mit Ausprägungsvarianzen |
| subject_GND | (DE-588)4113937-9 |
| title | Visuelles Erkennen von Objekten mit Ausprägungsvarianzen |
| title_auth | Visuelles Erkennen von Objekten mit Ausprägungsvarianzen |
| title_exact_search | Visuelles Erkennen von Objekten mit Ausprägungsvarianzen |
| title_full | Visuelles Erkennen von Objekten mit Ausprägungsvarianzen von Jens Teichert |
| title_fullStr | Visuelles Erkennen von Objekten mit Ausprägungsvarianzen von Jens Teichert |
| title_full_unstemmed | Visuelles Erkennen von Objekten mit Ausprägungsvarianzen von Jens Teichert |
| title_short | Visuelles Erkennen von Objekten mit Ausprägungsvarianzen |
| title_sort | visuelles erkennen von objekten mit auspragungsvarianzen |
| topic_facet | Hochschulschrift |
| url | https://nbn-resolving.org/urn:nbn:de:gbv:46-00102388-11 |
| work_keys_str_mv | AT teichertjens visuelleserkennenvonobjektenmitauspragungsvarianzen |