Discriminative Learning and Recognition of Image Set Classes Using Canonical Correlations

We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object's appearance due to changing camera pose and lighting conditions. canonical correlations (also known as principal or canonical angles), which can be thought of as the...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on pattern analysis and machine intelligence Vol. 29; no. 6; pp. 1005 - 1018
Main Authors Tae-Kyun Kim, Kittler, J., Cipolla, R.
Format Journal Article
LanguageEnglish
Published Los Alamitos, CA IEEE 01.06.2007
IEEE Computer Society
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Online AccessGet full text
ISSN0162-8828
2160-9292
1939-3539
DOI10.1109/TPAMI.2007.1037

Cover

Abstract We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object's appearance due to changing camera pose and lighting conditions. canonical correlations (also known as principal or canonical angles), which can be thought of as the angles between two d-dimensional subspaces, have recently attracted attention for image set matching. Canonical correlations offer many benefits in accuracy, efficiency, and robustness compared to the two main classical methods: parametric distribution-based and nonparametric sample-based matching of sets. Here, this is first demonstrated experimentally for reasonably sized data sets using existing methods exploiting canonical correlations. Motivated by their proven effectiveness, a novel discriminative learning method over sets is proposed for set classification. Specifically, inspired by classical linear discriminant analysis (LDA), we develop a linear discriminant function that maximizes the canonical correlations of within-class sets and minimizes the canonical correlations of between-class sets. Image sets transformed by the discriminant function are then compared by the canonical correlations. Classical orthogonal subspace method (OSM) is also investigated for the similar purpose and compared with the proposed method. The proposed method is evaluated on various object recognition problems using face image sets with arbitrary motion captured under different illuminations and image sets of 500 general objects taken at different views. The method is also applied to object category recognition using ETH-80 database. The proposed method is shown to outperform the state-of-the-art methods in terms of accuracy and efficiency
AbstractList We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object's appearance due to changing camera pose and lighting conditions. canonical correlations (also known as principal or canonical angles), which can be thought of as the angles between two d-dimensional subspaces, have recently attracted attention for image set matching. Canonical correlations offer many benefits in accuracy, efficiency, and robustness compared to the two main classical methods: parametric distribution-based and nonparametric sample-based matching of sets. Here, this is first demonstrated experimentally for reasonably sized data sets using existing methods exploiting canonical correlations. Motivated by their proven effectiveness, a novel discriminative learning method over sets is proposed for set classification. Specifically, inspired by classical linear discriminant analysis (LDA), we develop a linear discriminant function that maximizes the canonical correlations of within-class sets and minimizes the canonical correlations of between-class sets. Image sets transformed by the discriminant function are then compared by the canonical correlations. Classical orthogonal subspace method (OSM) is also investigated for the similar purpose and compared with the proposed method. The proposed method is evaluated on various object recognition problems using face image sets with arbitrary motion captured under different illuminations and image sets of 500 general objects taken at different views. The method is also applied to object category recognition using ETH-80 database. The proposed method is shown to outperform the state-of-the-art methods in terms of accuracy and efficiency
We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object's appearance due to changing camera pose and lighting conditions. Canonical Correlations (also known as principal or canonical angles), which can be thought of as the angles between two d-dimensional subspaces, have recently attracted attention for image set matching. Canonical correlations offer many benefits in accuracy, efficiency, and robustness compared to the two main classical methods: parametric distribution-based and nonparametric sample-based matching of sets. Here, this is first demonstrated experimentally for reasonably sized data sets using existing methods exploiting canonical correlations. Motivated by their proven effectiveness, a novel discriminative learning method over sets is proposed for set classification. Specifically, inspired by classical Linear Discriminant Analysis (LDA), we develop a linear discriminant function that maximizes the canonical correlations of within-class sets and minimizes the canonical correlations of between-class sets. Image sets transformed by the discriminant function are then compared by the canonical correlations. Classical orthogonal subspace method (OSM) is also investigated for the similar purpose and compared with the proposed method. The proposed method is evaluated on various object recognition problems using face image sets with arbitrary motion captured under different illuminations and image sets of 500 general objects taken at different views. The method is also applied to object category recognition using ETH-80 database. The proposed method is shown to outperform the state-of-the-art methods in terms of accuracy and efficiency.
We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object's appearance due to changing camera pose and lighting conditions. Canonical Correlations (also known as principal or canonical angles), which can be thought of as the angles between two d-dimensional subspaces, have recently attracted attention for image set matching. Canonical correlations offer many benefits in accuracy, efficiency, and robustness compared to the two main classical methods: parametric distribution-based and nonparametric sample-based matching of sets. Here, this is first demonstrated experimentally for reasonably sized data sets using existing methods exploiting canonical correlations. Motivated by their proven effectiveness, a novel discriminative learning method over sets is proposed for set classification. Specifically, inspired by classical Linear Discriminant Analysis (LDA), we develop a linear discriminant function that maximizes the canonical correlations of within-class sets and minimizes the canonical correlations of between-class sets. Image sets transformed by the discriminant function are then compared by the canonical correlations. Classical orthogonal subspace method (OSM) is also investigated for the similar purpose and compared with the proposed method. The proposed method is evaluated on various object recognition problems using face image sets with arbitrary motion captured under different illuminations and image sets of 500 general objects taken at different views. The method is also applied to object category recognition using ETH-80 database. The proposed method is shown to outperform the state-of-the-art methods in terms of accuracy and efficiency.We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object's appearance due to changing camera pose and lighting conditions. Canonical Correlations (also known as principal or canonical angles), which can be thought of as the angles between two d-dimensional subspaces, have recently attracted attention for image set matching. Canonical correlations offer many benefits in accuracy, efficiency, and robustness compared to the two main classical methods: parametric distribution-based and nonparametric sample-based matching of sets. Here, this is first demonstrated experimentally for reasonably sized data sets using existing methods exploiting canonical correlations. Motivated by their proven effectiveness, a novel discriminative learning method over sets is proposed for set classification. Specifically, inspired by classical Linear Discriminant Analysis (LDA), we develop a linear discriminant function that maximizes the canonical correlations of within-class sets and minimizes the canonical correlations of between-class sets. Image sets transformed by the discriminant function are then compared by the canonical correlations. Classical orthogonal subspace method (OSM) is also investigated for the similar purpose and compared with the proposed method. The proposed method is evaluated on various object recognition problems using face image sets with arbitrary motion captured under different illuminations and image sets of 500 general objects taken at different views. The method is also applied to object category recognition using ETH-80 database. The proposed method is shown to outperform the state-of-the-art methods in terms of accuracy and efficiency.
We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object's appearance due to changing camera pose and lighting conditions. canonical correlations (also known as principal [abstract truncated by publisher].
Specifically, inspired by classical linear discriminant analysis (LDA), we develop a linear discriminant function that maximizes the canonical correlations of within-class sets and minimizes the canonical correlations of between-class sets.
Author Kittler, J.
Tae-Kyun Kim
Cipolla, R.
Author_xml – sequence: 1
  surname: Tae-Kyun Kim
  fullname: Tae-Kyun Kim
  organization: Dept. of Eng., Cambridge Univ
– sequence: 2
  givenname: J.
  surname: Kittler
  fullname: Kittler, J.
– sequence: 3
  givenname: R.
  surname: Cipolla
  fullname: Cipolla, R.
BackLink http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=18734283$$DView record in Pascal Francis
https://www.ncbi.nlm.nih.gov/pubmed/17431299$$D View this record in MEDLINE/PubMed
BookMark eNqF0ktr3DAUBWBREppJ2nUXhWIKaVaeXL1saRncRwamtLTJoisjy9eDgkdOJE-h_z7yzDSBLJKVN9_RlXXPMTnwg0dC3lGYUwr6_OrnxffFnAGUcwq8fEVmjBaQa6bZAZkBLViuFFNH5DjGGwAqJPDX5IiWglOm9Yz8-eyiDW7tvBndX8yWaIJ3fpUZ32a_0A4r70Y3-GzossXarDD7jWNW9SZGjNl1nGhl0q2cNX1WDSFgb6ZAfEMOO9NHfLv_npDrr1-uqst8-ePborpY5lZyPuYowArdKWSiLQ1rpNCGWsV1y1qlWyhUw0AyoZFqa1grGyiMZUpKq2zXUH5Cznbn3obhboNxrNfpl7DvjcdhE2sNvKBCKf2iVAoKqSRVSX56VpbAleBQvAi5EJQWmif48Qm8GTbBp4epVTEZvh37YY82zRrb-jYtxoR_9f91JXC6Byam9-6C8dbFR6dKLpiapp3vnA1DjAG7RwL1VJx6W5x6Kk49FScl5JOEdeN2kWMwrn8m936Xc4j4MEWkEmpJ-T0nRMzZ
CODEN ITPIDJ
CitedBy_id crossref_primary_10_1016_j_imavis_2016_03_010
crossref_primary_10_1016_j_knosys_2022_109667
crossref_primary_10_1109_LSP_2008_2010819
crossref_primary_10_1016_j_ins_2012_09_008
crossref_primary_10_1016_j_jvcir_2014_08_006
crossref_primary_10_1109_TIP_2019_2954176
crossref_primary_10_1007_s13042_019_00941_6
crossref_primary_10_1016_j_neucom_2019_06_066
crossref_primary_10_1016_j_sigpro_2018_10_018
crossref_primary_10_1109_TCSVT_2011_2181452
crossref_primary_10_1109_TCSVT_2016_2538520
crossref_primary_10_1109_TPAMI_2015_2408358
crossref_primary_10_1016_j_procs_2015_07_316
crossref_primary_10_1016_j_patcog_2017_01_035
crossref_primary_10_1109_ACCESS_2018_2794357
crossref_primary_10_1109_TIP_2019_2913511
crossref_primary_10_1109_TIP_2011_2169972
crossref_primary_10_1109_TIP_2016_2616297
crossref_primary_10_1109_LSP_2014_2319817
crossref_primary_10_1007_s11760_017_1198_0
crossref_primary_10_1007_s00138_016_0772_8
crossref_primary_10_1109_TPAMI_2017_2776154
crossref_primary_10_1016_j_patrec_2017_09_026
crossref_primary_10_1016_j_jvcir_2014_01_009
crossref_primary_10_1016_j_neucom_2016_04_067
crossref_primary_10_1016_j_neucom_2023_01_084
crossref_primary_10_1016_j_mlwa_2022_100407
crossref_primary_10_1007_s11042_023_14433_x
crossref_primary_10_1631_jzus_C1200032
crossref_primary_10_1016_j_imavis_2011_08_002
crossref_primary_10_1016_j_patcog_2016_10_004
crossref_primary_10_1587_transinf_2014EDP7057
crossref_primary_10_1109_TPAMI_2014_2339851
crossref_primary_10_1016_j_neucom_2007_11_006
crossref_primary_10_1016_j_patcog_2021_108190
crossref_primary_10_1109_TPAMI_2008_167
crossref_primary_10_1155_2011_790598
crossref_primary_10_1109_TIP_2017_2746993
crossref_primary_10_1016_j_cviu_2017_03_004
crossref_primary_10_1016_j_neucom_2022_10_040
crossref_primary_10_3390_app13074209
crossref_primary_10_1109_TII_2022_3148289
crossref_primary_10_1016_j_neucom_2013_01_012
crossref_primary_10_1016_j_neucom_2016_01_051
crossref_primary_10_1016_j_patrec_2015_09_008
crossref_primary_10_1109_TIP_2017_2765820
crossref_primary_10_1109_TKDE_2019_2958342
crossref_primary_10_1080_07038992_2015_1089161
crossref_primary_10_1016_j_knosys_2021_107799
crossref_primary_10_1016_j_engappai_2019_03_016
crossref_primary_10_1007_s11042_015_3090_7
crossref_primary_10_1007_s10994_013_5380_5
crossref_primary_10_1016_j_amc_2017_07_058
crossref_primary_10_1109_TMM_2022_3173535
crossref_primary_10_1109_TSP_2012_2203816
crossref_primary_10_1016_j_neucom_2024_127523
crossref_primary_10_1109_TIFS_2016_2569061
crossref_primary_10_1016_j_knosys_2023_110590
crossref_primary_10_1016_j_imavis_2016_07_003
crossref_primary_10_1016_j_patrec_2018_11_009
crossref_primary_10_1109_TMM_2008_921847
crossref_primary_10_1109_TPAMI_2024_3466315
crossref_primary_10_1007_s11042_019_08408_0
crossref_primary_10_1016_j_jvcir_2018_05_016
crossref_primary_10_1016_j_chaos_2015_11_038
crossref_primary_10_1109_ACCESS_2019_2947548
crossref_primary_10_1016_j_imavis_2016_07_008
crossref_primary_10_3390_s19225051
crossref_primary_10_3233_THC_174534
crossref_primary_10_1007_s13042_021_01336_2
crossref_primary_10_1016_j_patrec_2009_06_002
crossref_primary_10_1016_j_asoc_2018_08_010
crossref_primary_10_1109_TNNLS_2018_2844866
crossref_primary_10_1016_j_neucom_2014_06_015
crossref_primary_10_1109_TPAMI_2011_283
crossref_primary_10_1371_journal_pone_0176598
crossref_primary_10_1109_TIP_2023_3240863
crossref_primary_10_1016_j_patcog_2014_05_011
crossref_primary_10_1145_2037661_2037666
crossref_primary_10_3390_math12142164
crossref_primary_10_1007_s11263_018_1088_0
crossref_primary_10_1016_j_neucom_2016_12_004
crossref_primary_10_1631_FITEE_1601764
crossref_primary_10_1109_TNNLS_2020_2980059
crossref_primary_10_1007_s11263_017_1000_3
crossref_primary_10_1109_TIP_2007_914203
crossref_primary_10_1109_TPAMI_2011_52
crossref_primary_10_1016_j_jvcir_2014_09_004
crossref_primary_10_1109_TIT_2022_3207686
crossref_primary_10_1016_j_cam_2022_114953
crossref_primary_10_1109_TPAMI_2008_154
crossref_primary_10_1080_2150704X_2015_1062156
crossref_primary_10_1016_j_neucom_2019_12_026
crossref_primary_10_1109_TKDE_2018_2872063
crossref_primary_10_1109_LSP_2016_2577601
crossref_primary_10_1016_j_neucom_2015_10_004
crossref_primary_10_1016_j_patcog_2017_11_020
crossref_primary_10_1016_j_eswa_2023_120558
crossref_primary_10_1016_j_ins_2017_01_001
crossref_primary_10_1016_j_eswa_2019_06_062
crossref_primary_10_1007_s11063_020_10276_x
crossref_primary_10_1109_TCSVT_2017_2772026
crossref_primary_10_1109_TPAMI_2015_2505311
crossref_primary_10_1016_j_eswa_2019_05_025
crossref_primary_10_1049_htl_2018_5024
crossref_primary_10_1016_j_eswa_2020_114559
crossref_primary_10_1137_130919222
crossref_primary_10_1016_j_cviu_2017_04_008
crossref_primary_10_1109_TIP_2017_2745106
crossref_primary_10_1109_TIFS_2014_2324277
crossref_primary_10_1109_TIP_2015_2466106
crossref_primary_10_1016_j_jvcir_2013_02_002
crossref_primary_10_1016_j_imavis_2016_06_005
crossref_primary_10_1007_s00521_019_04419_y
crossref_primary_10_1007_s10851_015_0629_1
crossref_primary_10_1016_j_neucom_2014_07_049
crossref_primary_10_1109_MIS_2016_26
crossref_primary_10_1007_s11063_014_9358_5
crossref_primary_10_1016_j_dsp_2020_102809
crossref_primary_10_1142_S0218001408006685
crossref_primary_10_1016_j_jvcir_2019_102660
crossref_primary_10_1109_TMM_2012_2228476
crossref_primary_10_1016_j_neucom_2016_07_075
crossref_primary_10_1007_s11042_015_3070_y
crossref_primary_10_1016_j_patcog_2016_09_043
crossref_primary_10_3390_app10217827
crossref_primary_10_1109_TCBB_2016_2603987
crossref_primary_10_1016_j_ins_2019_12_041
crossref_primary_10_1142_S2737480724410061
crossref_primary_10_1007_s00521_023_09159_8
crossref_primary_10_1016_j_patcog_2010_07_012
crossref_primary_10_1109_LGRS_2017_2765341
crossref_primary_10_1080_13682199_2023_2225372
crossref_primary_10_1007_s10489_020_01730_3
crossref_primary_10_1109_TNNLS_2022_3212703
crossref_primary_10_1007_s11263_010_0381_3
crossref_primary_10_1016_j_patcog_2010_02_007
crossref_primary_10_1109_ACCESS_2015_2485400
crossref_primary_10_1109_TIP_2015_2393057
crossref_primary_10_1016_j_micpro_2020_103096
crossref_primary_10_1186_1687_6180_2014_15
crossref_primary_10_1016_j_neucom_2016_05_013
crossref_primary_10_1016_j_patcog_2017_02_005
crossref_primary_10_1016_j_patcog_2017_02_007
crossref_primary_10_1016_j_sigpro_2014_08_046
crossref_primary_10_1109_JSTARS_2015_2513481
crossref_primary_10_1109_JPROC_2020_2989782
crossref_primary_10_1109_TIP_2023_3261758
crossref_primary_10_1016_j_asoc_2019_105630
crossref_primary_10_1016_j_patrec_2015_03_008
crossref_primary_10_1109_TIP_2018_2882225
crossref_primary_10_1016_j_neucom_2016_01_113
crossref_primary_10_1007_s13042_017_0782_5
crossref_primary_10_1016_j_neucom_2015_07_027
crossref_primary_10_1016_j_neucom_2011_11_006
crossref_primary_10_1016_j_neucom_2017_05_099
crossref_primary_10_1109_TIFS_2009_2026455
crossref_primary_10_1016_j_eswa_2022_119062
crossref_primary_10_1080_1931308X_2013_799313
crossref_primary_10_1016_j_inffus_2017_09_001
crossref_primary_10_1007_s40314_021_01482_x
crossref_primary_10_1016_j_neucom_2016_01_126
crossref_primary_10_4018_IJDCF_2016100103
crossref_primary_10_1109_TKDE_2012_92
crossref_primary_10_1016_j_neucom_2019_03_010
crossref_primary_10_1109_JSEN_2020_3004581
crossref_primary_10_1016_j_jocs_2016_10_016
crossref_primary_10_1109_TNNLS_2020_2978508
crossref_primary_10_1016_j_jvcir_2015_12_001
crossref_primary_10_1109_TIP_2015_2493448
crossref_primary_10_1016_j_cviu_2008_02_003
crossref_primary_10_1109_TNNLS_2023_3276796
crossref_primary_10_1007_s11063_019_10133_6
crossref_primary_10_1016_j_jvcir_2018_02_004
crossref_primary_10_1109_JSTARS_2018_2868142
crossref_primary_10_4018_IJISMD_313577
crossref_primary_10_1109_TPAMI_2008_200
crossref_primary_10_1016_j_neucom_2016_08_002
crossref_primary_10_1109_TBDATA_2024_3366084
crossref_primary_10_1016_j_eswa_2019_112886
crossref_primary_10_1109_TNNLS_2020_3044176
crossref_primary_10_1145_3708498
crossref_primary_10_1109_TIM_2021_3134333
crossref_primary_10_1109_TPAMI_2014_2353635
crossref_primary_10_5772_54002
crossref_primary_10_1016_j_patcog_2020_107500
crossref_primary_10_1109_ACCESS_2017_2733718
crossref_primary_10_1016_j_patcog_2013_10_012
crossref_primary_10_3233_JIFS_181347
crossref_primary_10_1109_TPAMI_2015_2414422
crossref_primary_10_1016_j_patcog_2015_03_016
crossref_primary_10_1109_TCSVT_2014_2351094
crossref_primary_10_1007_s00530_019_00629_5
crossref_primary_10_1109_TIP_2022_3219235
crossref_primary_10_1016_j_neucom_2013_12_015
crossref_primary_10_1007_s11263_015_0833_x
crossref_primary_10_1016_j_bspc_2021_102780
crossref_primary_10_1016_j_patcog_2015_03_011
crossref_primary_10_1109_TIP_2022_3212284
crossref_primary_10_1109_TIFS_2016_2601060
crossref_primary_10_1016_j_patcog_2020_107754
crossref_primary_10_4018_JGIM_2017100107
crossref_primary_10_1007_s11263_014_0720_x
crossref_primary_10_1109_TIP_2013_2282996
crossref_primary_10_1109_JSTSP_2015_2419593
crossref_primary_10_1007_s00521_016_2758_x
crossref_primary_10_1007_s11042_017_5076_0
crossref_primary_10_1109_TCSVT_2015_2412831
crossref_primary_10_1007_s11042_018_6045_y
crossref_primary_10_1109_TIP_2016_2577885
crossref_primary_10_1109_TNNLS_2015_2504724
crossref_primary_10_1016_j_patcog_2019_107028
crossref_primary_10_1007_s00521_018_3367_7
crossref_primary_10_1049_ipr2_12131
crossref_primary_10_1109_TSMCB_2011_2169056
crossref_primary_10_1109_TCSVT_2013_2280098
crossref_primary_10_1016_j_padiff_2024_100820
crossref_primary_10_1016_j_patcog_2010_11_004
crossref_primary_10_1016_j_knosys_2018_10_043
crossref_primary_10_1109_TIP_2024_3419414
crossref_primary_10_1016_j_neucom_2013_12_004
crossref_primary_10_1016_j_patcog_2017_03_001
crossref_primary_10_1016_j_neucom_2014_10_113
crossref_primary_10_1109_TNNLS_2013_2288062
crossref_primary_10_1016_j_bspc_2018_08_010
crossref_primary_10_1186_s13640_020_00507_5
crossref_primary_10_1007_s10515_017_0220_7
crossref_primary_10_1016_j_neucom_2024_127372
crossref_primary_10_1016_j_ins_2017_08_004
crossref_primary_10_1109_TIP_2022_3193758
crossref_primary_10_1109_TIP_2009_2038621
crossref_primary_10_1109_TCYB_2020_2984489
crossref_primary_10_1016_j_patrec_2020_10_015
crossref_primary_10_1142_S0218213013500309
crossref_primary_10_1007_s11767_011_0535_7
crossref_primary_10_1007_s11432_019_3019_3
crossref_primary_10_1109_TIP_2015_2463223
crossref_primary_10_1109_TIP_2018_2866688
crossref_primary_10_1109_TKDE_2009_126
crossref_primary_10_1016_j_imavis_2016_04_003
crossref_primary_10_1016_j_knosys_2015_01_016
crossref_primary_10_1587_transinf_E97_D_1855
crossref_primary_10_1109_TIP_2012_2206039
crossref_primary_10_1109_TMM_2015_2510509
crossref_primary_10_1109_TIP_2015_2445293
crossref_primary_10_1007_s00521_020_05089_x
crossref_primary_10_1109_TIP_2020_3040847
crossref_primary_10_1016_j_ins_2018_02_062
crossref_primary_10_1016_j_eswa_2021_114916
crossref_primary_10_4018_IJIIT_2018100105
crossref_primary_10_1016_j_neucom_2018_09_090
crossref_primary_10_1016_j_patrec_2013_07_004
crossref_primary_10_1016_j_patrec_2020_05_018
crossref_primary_10_1016_j_patcog_2013_09_009
crossref_primary_10_1016_j_neucom_2018_04_073
crossref_primary_10_1016_j_patcog_2019_107123
crossref_primary_10_1109_THMS_2017_2681425
crossref_primary_10_1109_TCSVT_2022_3206865
crossref_primary_10_1007_s11042_018_6071_9
crossref_primary_10_1109_TIFS_2010_2077627
crossref_primary_10_1109_TMM_2012_2234731
crossref_primary_10_1016_j_patcog_2011_02_011
crossref_primary_10_1007_s11042_018_6578_0
crossref_primary_10_1016_j_patrec_2017_04_005
crossref_primary_10_1109_TCSVT_2015_2469571
crossref_primary_10_1007_s11042_020_08989_1
crossref_primary_10_1109_TCSVT_2014_2309834
crossref_primary_10_1007_s11042_022_12435_9
crossref_primary_10_1016_j_compchemeng_2018_06_017
crossref_primary_10_1109_ACCESS_2018_2841855
crossref_primary_10_1016_j_image_2011_05_002
crossref_primary_10_1109_TIP_2017_2713940
crossref_primary_10_1109_TCSVT_2014_2367357
crossref_primary_10_1109_TIP_2015_2426413
crossref_primary_10_1016_j_ins_2021_08_093
crossref_primary_10_1016_j_jvcir_2021_103045
crossref_primary_10_1109_TMM_2018_2866222
crossref_primary_10_1007_s11042_018_6006_5
Cites_doi 10.1109/CVPR.2005.151
10.1109/AFGR.1998.670971
10.1007/11527923_8
10.1109/cvpr.2003.1211369
10.1109/TPAMI.2005.58
10.21236/ada415962
10.1023/B:VISI.0000013087.49260.fb
10.1007/11744078_20
10.1109/AFGR.1998.670968
10.1109/AFGR.2004.1301539
10.1109/TIT.1974.1055174
10.1007/3-540-47977-5_56
10.1007/11008941_21
10.1090/S0025-5718-1973-0348991-3
10.5244/C.14.25
10.1007/978-3-642-69878-1
10.1162/0899766042321814
10.5244/C.19.58
10.6028/NIST.IR.6965
10.1109/34.598228
10.1002/0471200611
10.1007/11612704_32
10.1016/S1077-3142(03)00080-8
10.1109/CVPR.2003.1211497
10.2307/2333955
10.1038/44565
10.1016/S0167-8655(03)00117-X
10.1109/AFGR.2004.1301634
10.1023/B:VISI.0000042993.50813.60
10.1109/CVPR.2003.1211373
10.1109/AFGR.2002.4527207
10.1109/AFGR.2000.840629
ContentType Journal Article
Copyright 2007 INIST-CNRS
Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2007
Copyright_xml – notice: 2007 INIST-CNRS
– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2007
DBID 97E
RIA
RIE
AAYXX
CITATION
IQODW
CGR
CUY
CVF
ECM
EIF
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
F28
FR3
7X8
DOI 10.1109/TPAMI.2007.1037
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
Pascal-Francis
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
Engineering Research Database
ANTE: Abstracts in New Technology & Engineering
MEDLINE - Academic
DatabaseTitleList Technology Research Database

MEDLINE
MEDLINE - Academic
Technology Research Database
Technology Research Database
Technology Research Database
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 3
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
Applied Sciences
EISSN 2160-9292
1939-3539
EndPage 1018
ExternalDocumentID 2333971531
17431299
18734283
10_1109_TPAMI_2007_1037
4160951
Genre orig-research
Research Support, Non-U.S. Gov't
Journal Article
GroupedDBID ---
-DZ
-~X
.DC
0R~
29I
4.4
53G
5GY
5VS
6IK
97E
9M8
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
ADRHT
AENEX
AETEA
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
FA8
HZ~
H~9
IBMZZ
ICLAB
IEDLZ
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNI
RNS
RXW
RZB
TAE
TN5
UHB
VH1
XJT
~02
AAYXX
CITATION
IQODW
RIG
AAYOK
CGR
CUY
CVF
ECM
EIF
NPM
PKN
RIC
Z5M
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
F28
FR3
7X8
ID FETCH-LOGICAL-c533t-e40c49f8e24d7a2b549a1c839d2d89d068b205249e19ca2d5b06ac2855c8cfb13
IEDL.DBID RIE
ISSN 0162-8828
IngestDate Thu Oct 02 04:07:11 EDT 2025
Sat Sep 27 19:04:43 EDT 2025
Wed Oct 01 13:52:41 EDT 2025
Thu Oct 02 11:52:05 EDT 2025
Mon Jun 30 06:15:39 EDT 2025
Wed Feb 19 01:43:08 EST 2025
Mon Jul 21 09:14:20 EDT 2025
Wed Oct 01 06:41:36 EDT 2025
Thu Apr 24 23:03:49 EDT 2025
Tue Aug 26 16:42:03 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 6
Keywords Image recognition
Image processing
Canonical correlation
Discriminant function
Correlation method
Parametric method
Canonical analysis
Image matching
Vector space
Lighting
Classification
Facies
principal angles
Database
Illumination
orthogonal subspace method
Robustness
linear discriminant analysis
Pattern analysis
Computer vision
Discriminant analysis
Motion estimation
Face recognition
Subspace method
Pattern recognition
canonical correlation analysis
Object recognition
Luminance
Correlation analysis
Artificial intelligence
image sets
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
CC BY 4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c533t-e40c49f8e24d7a2b549a1c839d2d89d068b205249e19ca2d5b06ac2855c8cfb13
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
PMID 17431299
PQID 864116318
PQPubID 23500
PageCount 14
ParticipantIDs pascalfrancis_primary_18734283
crossref_primary_10_1109_TPAMI_2007_1037
pubmed_primary_17431299
proquest_miscellaneous_34411693
proquest_miscellaneous_903614889
proquest_journals_864116318
proquest_miscellaneous_880658518
ieee_primary_4160951
proquest_miscellaneous_70384306
crossref_citationtrail_10_1109_TPAMI_2007_1037
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2007-06-01
PublicationDateYYYYMMDD 2007-06-01
PublicationDate_xml – month: 06
  year: 2007
  text: 2007-06-01
  day: 01
PublicationDecade 2000
PublicationPlace Los Alamitos, CA
PublicationPlace_xml – name: Los Alamitos, CA
– name: United States
– name: New York
PublicationTitle IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev TPAMI
PublicationTitleAlternate IEEE Trans Pattern Anal Mach Intell
PublicationYear 2007
Publisher IEEE
IEEE Computer Society
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: IEEE Computer Society
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref35
ref12
ref34
ref37
ref36
ref31
ref11
ref33
ref10
Kozakaya (ref27) 2004; 45
ref2
ref1
ref17
ref39
ref38
ref19
ref18
(ref40) 2005
Gittins (ref5) 1985
ref24
ref26
ref25
ref20
ref22
Phillips (ref16) 2003
ref21
Wang (ref30)
Via (ref32)
Oja (ref4) 1983
ref28
ref29
ref8
ref7
ref9
ref3
Lee (ref15) 2001
ref6
Duda (ref14) 2000
Wolf (ref23) 2003; 4
References_xml – ident: ref34
  doi: 10.1109/CVPR.2005.151
– start-page: 556
  year: 2001
  ident: ref15
  article-title: Algorithms for Non-Negative Matirx Factorization
  publication-title: Advances in Neural Information Processing Systems
– ident: ref9
  doi: 10.1109/AFGR.1998.670971
– volume-title: Proc. 13th European Signal Processing Conf.
  ident: ref32
  article-title: Canonical Correlation Analysis (CCA) Algorithms for Multiple Data Sets: Application to Blind SIMO Equalization
– ident: ref37
  doi: 10.1007/11527923_8
– ident: ref20
  doi: 10.1109/cvpr.2003.1211369
– ident: ref35
  doi: 10.1109/TPAMI.2005.58
– ident: ref13
  doi: 10.21236/ada415962
– ident: ref31
  doi: 10.1023/B:VISI.0000013087.49260.fb
– volume: 45
  start-page: 951
  issue: 3
  year: 2004
  ident: ref27
  article-title: Development and Evaluation of Face Recognition System Using Constrained Mutual Subspace Method
  publication-title: IPSJ J.
– ident: ref38
  doi: 10.1007/11744078_20
– ident: ref8
  doi: 10.1109/AFGR.1998.670968
– volume-title: Pattern Classification
  year: 2000
  ident: ref14
– ident: ref29
  doi: 10.1109/AFGR.2004.1301539
– start-page: 259
  volume-title: Proc. Computer Vision and Pattern Recognition Conf.
  ident: ref30
  article-title: Random Sampling LDA for Face Recognition
– ident: ref3
  doi: 10.1109/TIT.1974.1055174
– ident: ref17
  doi: 10.1007/3-540-47977-5_56
– ident: ref24
  doi: 10.1007/11008941_21
– ident: ref2
  doi: 10.1090/S0025-5718-1973-0348991-3
– ident: ref11
  doi: 10.5244/C.14.25
– volume-title: Canonical Analysis: A Review with Applications in Ecology
  year: 1985
  ident: ref5
  doi: 10.1007/978-3-642-69878-1
– ident: ref26
  doi: 10.1162/0899766042321814
– ident: ref36
  doi: 10.5244/C.19.58
– volume-title: Facial Recognition Vendor Test 2002: Evaluation Report
  year: 2003
  ident: ref16
  doi: 10.6028/NIST.IR.6965
– ident: ref7
  doi: 10.1109/34.598228
– ident: ref6
  doi: 10.1002/0471200611
– ident: ref39
  doi: 10.1007/11612704_32
– ident: ref21
  doi: 10.1016/S1077-3142(03)00080-8
– ident: ref25
  doi: 10.1109/CVPR.2003.1211497
– ident: ref1
  doi: 10.2307/2333955
– ident: ref10
  doi: 10.1038/44565
– ident: ref19
  doi: 10.1016/S0167-8655(03)00117-X
– year: 2005
  ident: ref40
  article-title: Facepass
– volume: 4
  start-page: 913
  issue: 10
  year: 2003
  ident: ref23
  article-title: Learning over Sets Using Kernel Principal Angles
  publication-title: J. Machine Learning Research
– ident: ref28
  doi: 10.1109/AFGR.2004.1301634
– ident: ref33
  doi: 10.1023/B:VISI.0000042993.50813.60
– volume-title: Subspace Methods of Pattern Recognition
  year: 1983
  ident: ref4
– ident: ref22
  doi: 10.1109/CVPR.2003.1211373
– ident: ref18
  doi: 10.1109/AFGR.2002.4527207
– ident: ref12
  doi: 10.1109/AFGR.2000.840629
SSID ssj0014503
Score 2.4642856
Snippet We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object's appearance due to changing...
Specifically, inspired by classical linear discriminant analysis (LDA), we develop a linear discriminant function that maximizes the canonical correlations of...
SourceID proquest
pubmed
pascalfrancis
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1005
SubjectTerms Algorithms
Applied sciences
Artificial Intelligence
Cameras
canonical correlation
canonical correlation analysis
Cluster Analysis
Computer science; control theory; systems
Computer vision
Correlation
Correlation analysis
Discriminant Analysis
Exact sciences and technology
Face recognition
Illumination
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image recognition
image sets
Information Storage and Retrieval - methods
Learning
Lighting
Linear discriminant analysis
Matching
Methods
Neural networks
Numerical Analysis, Computer-Assisted
Object recognition
orthogonal subspace method
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
principal angles
Recognition
Reproducibility of Results
Robustness
Sensitivity and Specificity
Signal Processing, Computer-Assisted
Statistics as Topic
Studies
Subtraction Technique
Vectors
Title Discriminative Learning and Recognition of Image Set Classes Using Canonical Correlations
URI https://ieeexplore.ieee.org/document/4160951
https://www.ncbi.nlm.nih.gov/pubmed/17431299
https://www.proquest.com/docview/864116318
https://www.proquest.com/docview/34411693
https://www.proquest.com/docview/70384306
https://www.proquest.com/docview/880658518
https://www.proquest.com/docview/903614889
Volume 29
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 2160-9292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014503
  issn: 0162-8828
  databaseCode: RIE
  dateStart: 19790101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB61PcGBQssjFIoPHDiQrZM4iX2sFqoWaRGCViqnyHZshICk6mYv_HpmnMcCIhK3SJk8nJmxv4lnvgF4STGAyzSPraJfN0LpWFruY8O9t14bUXuqRl69L86vxLvr_HoHXk-1MM65kHzmFnQY9vLr1m7oV9kJggdCBLuwW8qir9WadgxEHrogI4JBD8cwYqDxSbg6ufxwurro2QqpKo54QmndTAPf63YxCt1VKDdSr_Hz-L6vxTzwDAvQ2T6sxlfv806-LTadWdiff7E6_u_Y7sO9AYmy0950HsCOaw5gf-zywAanP4C7v1EWHsLnN19poqEEGpoo2cDP-oXppmYfx2yktmGtZxc_cLJin1zHQutNt2YhQYEtddOGcky2pN4gQzbeQ7g6e3u5PI-H9gyxRYzYxU5wK5SXLhV1qVODkaZOLAKuOq2lqnkhTcpzDO9coqxO69zwQttU5rmV1pskewR7-Dj3BJi2IiltoUvrvJC6MFq7uii1Q2PR3ogIFqOeKjtwl1MLje9ViGG4qoKOqadmWZGOI3g1XXDT03bMix6SNiaxQRERHP9hCNvbyDIjlroIjkbLqAa_X1eyEAki3ERG8GI6iw5LuzC6ce1mXWWCRFQ2L4GTsBQYykXAZiQkbYcjVpbzIgqhCYa6UkXwuDfb7QgG63_675EfwZ0xKZInz2Cvu92454i8OnMcXO4XpC0qlg
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Nb9QwEB2VcoAeKLRQQqH1gQMHsnUSJ7GP1UK1C90KwVYqp8h2bISABLHZC78ej-NkAbESt0iZfDgzY7-JZ94APMcYwGSSxlrgrxsmZMw1tbGi1morFastViMvrorZNXtzk9_swMuxFsYY45PPzAQP_V5-3eo1_io7c-ABEcEtuJ0zxvK-WmvcM2C574PsMIzzcRdIBCKfhIqz5bvzxbznK8S6OGQKxZUz9Yyvm-XI91fB7Ei5ch_I9p0ttkNPvwRd7MNiePk-8-TLZN2pif75F6_j_47uPtwLWJSc98bzAHZMcwD7Q58HEtz-APZ-Iy08hI-vPuNUgyk0OFWSwND6icimJu-HfKS2Ia0l829uuiIfTEd8802zIj5FgUxl0_qCTDLF7iAhH-8hXF-8Xk5ncWjQEGuHErvYMKqZsNykrC5lqlysKRPtIFed1lzUtOAqpbkL8EwitEzrXNFC6pTnuebaqiR7BLvuceYxEKlZUupCltpYxmWhpDR1UUrjzEVaxSKYDHqqdGAvxyYaXysfxVBReR1jV82yQh1H8GK84HtP3LFd9BC1MYoFRURw8ochbG7Dywx56iI4HiyjCp6_qnjBEodxEx7B6XjWuSzuw8jGtOtVlTEUEdl2CTcNc-aCuQjIFgmOG-IOLfPtIsKBExfschHBUW-2mxEE63_y75Gfwp3ZcnFZXc6v3h7D3SFFkiZPYbf7sTbPHA7r1Il3v19b5S3j
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=Discriminative+learning+and+recognition+of+image+set+classes+using+canonical+correlations&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Kim%2C+Tae-Kyun&rft.au=Kittler%2C+Josef&rft.au=Cipolla%2C+Roberto&rft.date=2007-06-01&rft.issn=0162-8828&rft.volume=29&rft.issue=6&rft.spage=1005&rft_id=info:doi/10.1109%2FTPAMI.2007.1037&rft_id=info%3Apmid%2F17431299&rft.externalDocID=17431299
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon