An information theory perspective on computational vision
Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the comple...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Yuille, Alan [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2010 |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: Frontiers of electrical and electronic engineering in China - Berlin : Heidelberg : Springer, 2006, 5(2010), 3 vom: 05. Aug., Seite 329-346 |
|---|---|
| Übergeordnetes Werk: |
volume:5 ; year:2010 ; number:3 ; day:05 ; month:08 ; pages:329-346 |
| Links: |
|---|
| DOI / URN: |
10.1007/s11460-010-0107-x |
|---|
| Katalog-ID: |
SPR019849419 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR019849419 | ||
| 003 | DE-627 | ||
| 005 | 20220111071949.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 201006s2010 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s11460-010-0107-x |2 doi | |
| 035 | |a (DE-627)SPR019849419 | ||
| 035 | |a (SPR)s11460-010-0107-x-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 620 |q ASE |
| 084 | |a 53.00 |2 bkl | ||
| 100 | 1 | |a Yuille, Alan |e verfasserin |4 aut | |
| 245 | 1 | 3 | |a An information theory perspective on computational vision |
| 264 | 1 | |c 2010 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues. | ||
| 650 | 4 | |a computer vision |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a pattern recognition |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a information theory |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a minimum description length |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Markov random field (MRF) model |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a stochastic grammars |7 (dpeaa)DE-He213 | |
| 773 | 0 | 8 | |i Enthalten in |t Frontiers of electrical and electronic engineering in China |d Berlin : Heidelberg : Springer, 2006 |g 5(2010), 3 vom: 05. Aug., Seite 329-346 |w (DE-627)510464297 |w (DE-600)2230606-7 |x 1673-3584 |7 nnns |
| 773 | 1 | 8 | |g volume:5 |g year:2010 |g number:3 |g day:05 |g month:08 |g pages:329-346 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1007/s11460-010-0107-x |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 912 | |a GBV_ILN_20 | ||
| 912 | |a GBV_ILN_40 | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_73 | ||
| 912 | |a GBV_ILN_74 | ||
| 912 | |a GBV_ILN_90 | ||
| 912 | |a GBV_ILN_110 | ||
| 912 | |a GBV_ILN_120 | ||
| 912 | |a GBV_ILN_161 | ||
| 912 | |a GBV_ILN_293 | ||
| 912 | |a GBV_ILN_702 | ||
| 912 | |a GBV_ILN_2005 | ||
| 912 | |a GBV_ILN_2014 | ||
| 912 | |a GBV_ILN_2018 | ||
| 912 | |a GBV_ILN_2190 | ||
| 936 | b | k | |a 53.00 |q ASE |
| 951 | |a AR | ||
| 952 | |d 5 |j 2010 |e 3 |b 05 |c 08 |h 329-346 | ||
| author_variant |
a y ay |
|---|---|
| matchkey_str |
article:16733584:2010----::nnomtoterprpcienop |
| hierarchy_sort_str |
2010 |
| bklnumber |
53.00 |
| publishDate |
2010 |
| allfields |
10.1007/s11460-010-0107-x doi (DE-627)SPR019849419 (SPR)s11460-010-0107-x-e DE-627 ger DE-627 rakwb eng 620 ASE 53.00 bkl Yuille, Alan verfasserin aut An information theory perspective on computational vision 2010 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues. computer vision (dpeaa)DE-He213 pattern recognition (dpeaa)DE-He213 information theory (dpeaa)DE-He213 minimum description length (dpeaa)DE-He213 Markov random field (MRF) model (dpeaa)DE-He213 stochastic grammars (dpeaa)DE-He213 Enthalten in Frontiers of electrical and electronic engineering in China Berlin : Heidelberg : Springer, 2006 5(2010), 3 vom: 05. Aug., Seite 329-346 (DE-627)510464297 (DE-600)2230606-7 1673-3584 nnns volume:5 year:2010 number:3 day:05 month:08 pages:329-346 https://dx.doi.org/10.1007/s11460-010-0107-x lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_40 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_110 GBV_ILN_120 GBV_ILN_161 GBV_ILN_293 GBV_ILN_702 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2190 53.00 ASE AR 5 2010 3 05 08 329-346 |
| spelling |
10.1007/s11460-010-0107-x doi (DE-627)SPR019849419 (SPR)s11460-010-0107-x-e DE-627 ger DE-627 rakwb eng 620 ASE 53.00 bkl Yuille, Alan verfasserin aut An information theory perspective on computational vision 2010 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues. computer vision (dpeaa)DE-He213 pattern recognition (dpeaa)DE-He213 information theory (dpeaa)DE-He213 minimum description length (dpeaa)DE-He213 Markov random field (MRF) model (dpeaa)DE-He213 stochastic grammars (dpeaa)DE-He213 Enthalten in Frontiers of electrical and electronic engineering in China Berlin : Heidelberg : Springer, 2006 5(2010), 3 vom: 05. Aug., Seite 329-346 (DE-627)510464297 (DE-600)2230606-7 1673-3584 nnns volume:5 year:2010 number:3 day:05 month:08 pages:329-346 https://dx.doi.org/10.1007/s11460-010-0107-x lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_40 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_110 GBV_ILN_120 GBV_ILN_161 GBV_ILN_293 GBV_ILN_702 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2190 53.00 ASE AR 5 2010 3 05 08 329-346 |
| allfields_unstemmed |
10.1007/s11460-010-0107-x doi (DE-627)SPR019849419 (SPR)s11460-010-0107-x-e DE-627 ger DE-627 rakwb eng 620 ASE 53.00 bkl Yuille, Alan verfasserin aut An information theory perspective on computational vision 2010 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues. computer vision (dpeaa)DE-He213 pattern recognition (dpeaa)DE-He213 information theory (dpeaa)DE-He213 minimum description length (dpeaa)DE-He213 Markov random field (MRF) model (dpeaa)DE-He213 stochastic grammars (dpeaa)DE-He213 Enthalten in Frontiers of electrical and electronic engineering in China Berlin : Heidelberg : Springer, 2006 5(2010), 3 vom: 05. Aug., Seite 329-346 (DE-627)510464297 (DE-600)2230606-7 1673-3584 nnns volume:5 year:2010 number:3 day:05 month:08 pages:329-346 https://dx.doi.org/10.1007/s11460-010-0107-x lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_40 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_110 GBV_ILN_120 GBV_ILN_161 GBV_ILN_293 GBV_ILN_702 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2190 53.00 ASE AR 5 2010 3 05 08 329-346 |
| allfieldsGer |
10.1007/s11460-010-0107-x doi (DE-627)SPR019849419 (SPR)s11460-010-0107-x-e DE-627 ger DE-627 rakwb eng 620 ASE 53.00 bkl Yuille, Alan verfasserin aut An information theory perspective on computational vision 2010 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues. computer vision (dpeaa)DE-He213 pattern recognition (dpeaa)DE-He213 information theory (dpeaa)DE-He213 minimum description length (dpeaa)DE-He213 Markov random field (MRF) model (dpeaa)DE-He213 stochastic grammars (dpeaa)DE-He213 Enthalten in Frontiers of electrical and electronic engineering in China Berlin : Heidelberg : Springer, 2006 5(2010), 3 vom: 05. Aug., Seite 329-346 (DE-627)510464297 (DE-600)2230606-7 1673-3584 nnns volume:5 year:2010 number:3 day:05 month:08 pages:329-346 https://dx.doi.org/10.1007/s11460-010-0107-x lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_40 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_110 GBV_ILN_120 GBV_ILN_161 GBV_ILN_293 GBV_ILN_702 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2190 53.00 ASE AR 5 2010 3 05 08 329-346 |
| allfieldsSound |
10.1007/s11460-010-0107-x doi (DE-627)SPR019849419 (SPR)s11460-010-0107-x-e DE-627 ger DE-627 rakwb eng 620 ASE 53.00 bkl Yuille, Alan verfasserin aut An information theory perspective on computational vision 2010 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues. computer vision (dpeaa)DE-He213 pattern recognition (dpeaa)DE-He213 information theory (dpeaa)DE-He213 minimum description length (dpeaa)DE-He213 Markov random field (MRF) model (dpeaa)DE-He213 stochastic grammars (dpeaa)DE-He213 Enthalten in Frontiers of electrical and electronic engineering in China Berlin : Heidelberg : Springer, 2006 5(2010), 3 vom: 05. Aug., Seite 329-346 (DE-627)510464297 (DE-600)2230606-7 1673-3584 nnns volume:5 year:2010 number:3 day:05 month:08 pages:329-346 https://dx.doi.org/10.1007/s11460-010-0107-x lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_40 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_110 GBV_ILN_120 GBV_ILN_161 GBV_ILN_293 GBV_ILN_702 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2190 53.00 ASE AR 5 2010 3 05 08 329-346 |
| language |
English |
| source |
Enthalten in Frontiers of electrical and electronic engineering in China 5(2010), 3 vom: 05. Aug., Seite 329-346 volume:5 year:2010 number:3 day:05 month:08 pages:329-346 |
| sourceStr |
Enthalten in Frontiers of electrical and electronic engineering in China 5(2010), 3 vom: 05. Aug., Seite 329-346 volume:5 year:2010 number:3 day:05 month:08 pages:329-346 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
computer vision pattern recognition information theory minimum description length Markov random field (MRF) model stochastic grammars |
| dewey-raw |
620 |
| isfreeaccess_bool |
false |
| container_title |
Frontiers of electrical and electronic engineering in China |
| authorswithroles_txt_mv |
Yuille, Alan @@aut@@ |
| publishDateDaySort_date |
2010-08-05T00:00:00Z |
| hierarchy_top_id |
510464297 |
| dewey-sort |
3620 |
| id |
SPR019849419 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR019849419</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20220111071949.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">201006s2010 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11460-010-0107-x</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR019849419</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s11460-010-0107-x-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">620</subfield><subfield code="q">ASE</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">53.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Yuille, Alan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="3"><subfield code="a">An information theory perspective on computational vision</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2010</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">computer vision</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">pattern recognition</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">information theory</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">minimum description length</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Markov random field (MRF) model</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">stochastic grammars</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Frontiers of electrical and electronic engineering in China</subfield><subfield code="d">Berlin : Heidelberg : Springer, 2006</subfield><subfield code="g">5(2010), 3 vom: 05. Aug., Seite 329-346</subfield><subfield code="w">(DE-627)510464297</subfield><subfield code="w">(DE-600)2230606-7</subfield><subfield code="x">1673-3584</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:5</subfield><subfield code="g">year:2010</subfield><subfield code="g">number:3</subfield><subfield code="g">day:05</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:329-346</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s11460-010-0107-x</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_120</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">53.00</subfield><subfield code="q">ASE</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">5</subfield><subfield code="j">2010</subfield><subfield code="e">3</subfield><subfield code="b">05</subfield><subfield code="c">08</subfield><subfield code="h">329-346</subfield></datafield></record></collection>
|
| author |
Yuille, Alan |
| spellingShingle |
Yuille, Alan ddc 620 bkl 53.00 misc computer vision misc pattern recognition misc information theory misc minimum description length misc Markov random field (MRF) model misc stochastic grammars An information theory perspective on computational vision |
| authorStr |
Yuille, Alan |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)510464297 |
| format |
electronic Article |
| dewey-ones |
620 - Engineering & allied operations |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
springer |
| remote_str |
true |
| illustrated |
Not Illustrated |
| issn |
1673-3584 |
| topic_title |
620 ASE 53.00 bkl An information theory perspective on computational vision computer vision (dpeaa)DE-He213 pattern recognition (dpeaa)DE-He213 information theory (dpeaa)DE-He213 minimum description length (dpeaa)DE-He213 Markov random field (MRF) model (dpeaa)DE-He213 stochastic grammars (dpeaa)DE-He213 |
| topic |
ddc 620 bkl 53.00 misc computer vision misc pattern recognition misc information theory misc minimum description length misc Markov random field (MRF) model misc stochastic grammars |
| topic_unstemmed |
ddc 620 bkl 53.00 misc computer vision misc pattern recognition misc information theory misc minimum description length misc Markov random field (MRF) model misc stochastic grammars |
| topic_browse |
ddc 620 bkl 53.00 misc computer vision misc pattern recognition misc information theory misc minimum description length misc Markov random field (MRF) model misc stochastic grammars |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
Frontiers of electrical and electronic engineering in China |
| hierarchy_parent_id |
510464297 |
| dewey-tens |
620 - Engineering |
| hierarchy_top_title |
Frontiers of electrical and electronic engineering in China |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)510464297 (DE-600)2230606-7 |
| title |
An information theory perspective on computational vision |
| ctrlnum |
(DE-627)SPR019849419 (SPR)s11460-010-0107-x-e |
| title_full |
An information theory perspective on computational vision |
| author_sort |
Yuille, Alan |
| journal |
Frontiers of electrical and electronic engineering in China |
| journalStr |
Frontiers of electrical and electronic engineering in China |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology |
| recordtype |
marc |
| publishDateSort |
2010 |
| contenttype_str_mv |
txt |
| container_start_page |
329 |
| author_browse |
Yuille, Alan |
| container_volume |
5 |
| class |
620 ASE 53.00 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Yuille, Alan |
| doi_str_mv |
10.1007/s11460-010-0107-x |
| dewey-full |
620 |
| title_sort |
information theory perspective on computational vision |
| title_auth |
An information theory perspective on computational vision |
| abstract |
Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues. |
| abstractGer |
Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues. |
| abstract_unstemmed |
Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_40 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_110 GBV_ILN_120 GBV_ILN_161 GBV_ILN_293 GBV_ILN_702 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2018 GBV_ILN_2190 |
| container_issue |
3 |
| title_short |
An information theory perspective on computational vision |
| url |
https://dx.doi.org/10.1007/s11460-010-0107-x |
| remote_bool |
true |
| ppnlink |
510464297 |
| mediatype_str_mv |
c |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s11460-010-0107-x |
| up_date |
2024-07-04T03:07:08.361Z |
| _version_ |
1803616180882112512 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR019849419</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20220111071949.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">201006s2010 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11460-010-0107-x</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR019849419</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s11460-010-0107-x-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">620</subfield><subfield code="q">ASE</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">53.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Yuille, Alan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="3"><subfield code="a">An information theory perspective on computational vision</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2010</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">computer vision</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">pattern recognition</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">information theory</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">minimum description length</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Markov random field (MRF) model</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">stochastic grammars</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Frontiers of electrical and electronic engineering in China</subfield><subfield code="d">Berlin : Heidelberg : Springer, 2006</subfield><subfield code="g">5(2010), 3 vom: 05. Aug., Seite 329-346</subfield><subfield code="w">(DE-627)510464297</subfield><subfield code="w">(DE-600)2230606-7</subfield><subfield code="x">1673-3584</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:5</subfield><subfield code="g">year:2010</subfield><subfield code="g">number:3</subfield><subfield code="g">day:05</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:329-346</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s11460-010-0107-x</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_120</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">53.00</subfield><subfield code="q">ASE</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">5</subfield><subfield code="j">2010</subfield><subfield code="e">3</subfield><subfield code="b">05</subfield><subfield code="c">08</subfield><subfield code="h">329-346</subfield></datafield></record></collection>
|
| score |
7.4013987 |