A model of visual recognition and categorization

To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of these factors, by learning to interpolat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Philosophical transactions of the Royal Society of London. Series B. Biological sciences Jg. 352; H. 1358; S. 1191
Hauptverfasser: Edelman, S, Duvdevani-Bar, S
Format: Journal Article
Sprache:Englisch
Veröffentlicht: England 29.08.1997
Schlagworte:
ISSN:0962-8436
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of these factors, by learning to interpolate between stored views of the target object, taken under representative combinations of viewing conditions. Daily life situations, however, typically require categorization, rather than recognition, of objects. Due to the open-ended character of both natural and artificial categories, categorization cannot rely on interpolation between stored examples. Nonetheless, knowledge of several representative members, or prototypes, of each of the categories of interest can still provide the necessary computational substrate for the categorization of new instances. The resulting representational scheme based on similarities to prototypes appears to be computationally viable, and is readily mapped onto the mechanisms of biological vision revealed by recent psychophysical and physiological studies.
AbstractList To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of these factors, by learning to interpolate between stored views of the target object, taken under representative combinations of viewing conditions. Daily life situations, however, typically require categorization, rather than recognition, of objects. Due to the open-ended character of both natural and artificial categories, categorization cannot rely on interpolation between stored examples. Nonetheless, knowledge of several representative members, or prototypes, of each of the categories of interest can still provide the necessary computational substrate for the categorization of new instances. The resulting representational scheme based on similarities to prototypes appears to be computationally viable, and is readily mapped onto the mechanisms of biological vision revealed by recent psychophysical and physiological studies.
To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of these factors, by learning to interpolate between stored views of the target object, taken under representative combinations of viewing conditions. Daily life situations, however, typically require categorization, rather than recognition, of objects. Due to the open-ended character of both natural and artificial categories, categorization cannot rely on interpolation between stored examples. Nonetheless, knowledge of several representative members, or prototypes, of each of the categories of interest can still provide the necessary computational substrate for the categorization of new instances. The resulting representational scheme based on similarities to prototypes appears to be computationally viable, and is readily mapped onto the mechanisms of biological vision revealed by recent psychophysical and physiological studies.To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of these factors, by learning to interpolate between stored views of the target object, taken under representative combinations of viewing conditions. Daily life situations, however, typically require categorization, rather than recognition, of objects. Due to the open-ended character of both natural and artificial categories, categorization cannot rely on interpolation between stored examples. Nonetheless, knowledge of several representative members, or prototypes, of each of the categories of interest can still provide the necessary computational substrate for the categorization of new instances. The resulting representational scheme based on similarities to prototypes appears to be computationally viable, and is readily mapped onto the mechanisms of biological vision revealed by recent psychophysical and physiological studies.
Author Duvdevani-Bar, S
Edelman, S
Author_xml – sequence: 1
  givenname: S
  surname: Edelman
  fullname: Edelman, S
  email: edelman@ai.mit.edu
  organization: Center for Biological and Computational Learning, Massachusetts Institute of Technology, Cambridge 02142, USA. edelman@ai.mit.edu
– sequence: 2
  givenname: S
  surname: Duvdevani-Bar
  fullname: Duvdevani-Bar, S
BackLink https://www.ncbi.nlm.nih.gov/pubmed/9304686$$D View this record in MEDLINE/PubMed
BookMark eNotj0FLwzAYhnOYzG169Sbk5K31a5KmyXEMncLAy-4lab6MSpvMpBX014u60wMvDy88a7IIMSAhdxWUFWj1mPJky0rrpoQK2IKsQEtWKMHlNVnn_A4Aum7Ekiw1ByGVXBHY0jE6HGj09LPPsxlowi6eQj_1MVATHO3MhKeY-m_zO92QK2-GjLcXbsjx-em4eykOb_vX3fZQdLISU6GBg2ECbGPBo6x8bZipme-808orLl0jleVKWKgt2o4LpqRXzIFCYIxtyMP_7TnFjxnz1I597nAYTMA457bRTDfqT7y_iLMd0bXn1I8mfbWXQvYDklVR9A
CitedBy_id crossref_primary_10_1016_j_imavis_2007_08_014
crossref_primary_10_1016_j_imavis_2003_07_007
crossref_primary_10_1088_0954_898X_8_3_003
crossref_primary_10_1016_j_jecp_2014_01_009
crossref_primary_10_1108_03684920410514562
crossref_primary_10_1016_S0042_6989_01_00073_6
crossref_primary_10_1037_0033_295X_109_1_156
crossref_primary_10_1016_j_actpsy_2011_06_007
crossref_primary_10_1016_S0031_9384_00_00407_8
crossref_primary_10_1162_089976600300015574
crossref_primary_10_1162_089976600300015772
crossref_primary_10_1037_0033_295X_110_1_29
crossref_primary_10_1371_journal_pcbi_1008981
crossref_primary_10_1016_j_neunet_2007_04_027
crossref_primary_10_1207_s15516709cog2701_3
crossref_primary_10_1207_s15516709cog2602_3
crossref_primary_10_1038_nrn3747
crossref_primary_10_1016_j_tins_2024_08_008
crossref_primary_10_1068_pmkwar
crossref_primary_10_1111_1467_9280_03439
crossref_primary_10_1088_1742_6596_1982_1_012003
crossref_primary_10_1086_727427
crossref_primary_10_1016_S0893_6080_01_00027_2
crossref_primary_10_1007_s10670_017_9951_x
crossref_primary_10_1038_nature02156
crossref_primary_10_1109_34_888719
crossref_primary_10_1152_jn_00168_2006
crossref_primary_10_1016_j_cub_2008_03_036
crossref_primary_10_1016_S0042_6989_99_00134_0
crossref_primary_10_1016_S0042_6989_00_00002_X
crossref_primary_10_1037_0096_1523_27_5_1090
crossref_primary_10_1016_j_cub_2017_01_046
crossref_primary_10_1016_S1364_6613_97_01090_5
crossref_primary_10_1080_02643290244000149
crossref_primary_10_1016_j_visres_2005_02_021
crossref_primary_10_1016_S0001_6918_01_00019_1
crossref_primary_10_1093_cercor_bhk022
crossref_primary_10_1097_01_wno_0000189826_62010_48
crossref_primary_10_1109_72_750575
crossref_primary_10_1016_S0278_2626_03_00184_2
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1098/rstb.1997.0102
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Medicine
Sciences (General)
Biology
ExternalDocumentID 9304686
Genre Journal Article
GroupedDBID ---
-~X
0R~
29O
2WC
4.4
53G
AACGO
AANCE
ABBHK
ABPLY
ABTLG
ABXSQ
ACHIC
ACPRK
ACQIA
ACRPL
ACSFO
ADBBV
ADNMO
ADULT
AEUPB
AEXZC
AFRAH
AGPVY
AJZGM
ALMA_UNASSIGNED_HOLDINGS
ALMYZ
AOIJS
AQVQM
AS~
BGBPD
BTFSW
CAG
CGR
COF
CUY
CVF
DCCCD
DOOOF
E3Z
EBS
ECM
EIF
EJD
F5P
GX1
H13
HGD
HQ3
HTVGU
HYE
HZ~
IPSME
JAAYA
JBMMH
JENOY
JHFFW
JKQEH
JLS
JLXEF
JPM
JSG
JSODD
JST
K-O
KQ8
MRS
MV1
MVM
NPM
O9-
OK1
OP1
ROL
RPM
RRY
SA0
TN5
V1E
WOQ
YNT
~02
7X8
ADQXQ
AGQPQ
ID FETCH-LOGICAL-c614t-9030a240b7b0fe61f5a2a52fcfd98f836d768b384b05bebc34286f82d08e0222
IEDL.DBID 7X8
ISICitedReferencesCount 65
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=10_1098_rstb_1997_0102&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0962-8436
IngestDate Thu Jul 10 23:38:02 EDT 2025
Wed Feb 19 01:13:45 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1358
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c614t-9030a240b7b0fe61f5a2a52fcfd98f836d768b384b05bebc34286f82d08e0222
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://www.ncbi.nlm.nih.gov/pmc/articles/1692007
PMID 9304686
PQID 79297822
PQPubID 23479
ParticipantIDs proquest_miscellaneous_79297822
pubmed_primary_9304686
PublicationCentury 1900
PublicationDate 1997-08-29
PublicationDateYYYYMMDD 1997-08-29
PublicationDate_xml – month: 08
  year: 1997
  text: 1997-08-29
  day: 29
PublicationDecade 1990
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Philosophical transactions of the Royal Society of London. Series B. Biological sciences
PublicationTitleAlternate Philos Trans R Soc Lond B Biol Sci
PublicationYear 1997
References 8833438 - Annu Rev Neurosci. 1996;19:109-39
7583105 - Curr Biol. 1995 May 1;5(5):552-63
8658144 - Science. 1996 Jun 14;272(5268):1665-8
3338267 - Cogn Psychol. 1988 Jan;20(1):38-64
1729718 - Proc Natl Acad Sci U S A. 1992 Jan 1;89(1):60-4
2300170 - Nature. 1990 Jan 18;343(6255):263-6
3575582 - Psychol Rev. 1987 Apr;94(2):115-47
17776454 - Science. 1990 Feb 23;247(4945):978-82
1525549 - Curr Opin Neurobiol. 1992 Aug;2(4):502-5
8876260 - Proc Natl Acad Sci U S A. 1996 Oct 15;93(21):12046-50
24223 - Proc R Soc Lond B Biol Sci. 1978 Feb 23;200(1140):269-94
6734136 - Cogn Psychol. 1984 Apr;16(2):243-75
2752709 - Cognition. 1989 Aug;32(3):193-254
2587799 - Q J Exp Psychol A. 1989 Nov;41(4):797-827
17837406 - Science. 1980 Oct 24;210(4468):390-8
9161020 - Neural Comput. 1997 May 15;9(4):701-20
References_xml – reference: 3575582 - Psychol Rev. 1987 Apr;94(2):115-47
– reference: 24223 - Proc R Soc Lond B Biol Sci. 1978 Feb 23;200(1140):269-94
– reference: 17837406 - Science. 1980 Oct 24;210(4468):390-8
– reference: 1729718 - Proc Natl Acad Sci U S A. 1992 Jan 1;89(1):60-4
– reference: 9161020 - Neural Comput. 1997 May 15;9(4):701-20
– reference: 1525549 - Curr Opin Neurobiol. 1992 Aug;2(4):502-5
– reference: 2587799 - Q J Exp Psychol A. 1989 Nov;41(4):797-827
– reference: 3338267 - Cogn Psychol. 1988 Jan;20(1):38-64
– reference: 6734136 - Cogn Psychol. 1984 Apr;16(2):243-75
– reference: 7583105 - Curr Biol. 1995 May 1;5(5):552-63
– reference: 8876260 - Proc Natl Acad Sci U S A. 1996 Oct 15;93(21):12046-50
– reference: 2300170 - Nature. 1990 Jan 18;343(6255):263-6
– reference: 8658144 - Science. 1996 Jun 14;272(5268):1665-8
– reference: 2752709 - Cognition. 1989 Aug;32(3):193-254
– reference: 8833438 - Annu Rev Neurosci. 1996;19:109-39
– reference: 17776454 - Science. 1990 Feb 23;247(4945):978-82
SSID ssj0009574
Score 1.8015108
SecondaryResourceType review_article
Snippet To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 1191
SubjectTerms Animals
Cognition - physiology
Form Perception - physiology
Humans
Neural Networks (Computer)
Pattern Recognition, Automated
Pattern Recognition, Visual - physiology
Primates
Title A model of visual recognition and categorization
URI https://www.ncbi.nlm.nih.gov/pubmed/9304686
https://www.proquest.com/docview/79297822
Volume 352
WOSCitedRecordID wos10_1098_rstb_1997_0102&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07TwMxDLYKBcTCo1BRnhkYYDh6vUeSk5BQhagYaNWhQt2qPFGXu8K1lfj3OPdALIiB5bZcIsvOZ8f2Z4BrFTBmKI88hG_tRUL6nqQi9qxRJkA41rLoen99YaMRn06TcQPu614YV1ZZ34nFRa0z5d7IuwwXOjR7WLx7bmaUy61WAzQ2oBmiI-N0mk35D8rdkoM5oWjzkUtSVpSNvIuOlXR9euzOUar97lwWIDPY_9_xDmCvci5Jv9SGQ2iYtAXb5bjJzxbsDKtEegsOK5vOyU1FPH17BH6fFINxSGbJep6v8Fff9UVZSkSqiaufesOdy-bNY5gMniaPz141UcFTCMNLL0GTFojhkknfGtqzsQhEHFhldcItD6nG6EOGPJJ-LI1UIQYn1PJA-9y4yLANm2mWmhMgSvZMbJgwvqGRsBFPeonGTUIb-0KquANXtZxmqLAuCyFSk63yWS2pDrRLUc8WJa_GLHFZWk5P_1x6Brsli6xrIDmHpkVLNRewpdbLef5xWagBfkfj4ReQpLxR
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+model+of+visual+recognition+and+categorization&rft.jtitle=Philosophical+transactions+of+the+Royal+Society+of+London.+Series+B.+Biological+sciences&rft.au=Edelman%2C+S&rft.au=Duvdevani-Bar%2C+S&rft.date=1997-08-29&rft.issn=0962-8436&rft.volume=352&rft.issue=1358&rft.spage=1191&rft_id=info:doi/10.1098%2Frstb.1997.0102&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0962-8436&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0962-8436&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0962-8436&client=summon