A novel hybrid CNN–SVM classifier for recognizing handwritten digits
This paper presents a hybrid model of integrating the synergy of two superior classifiers: Convolutional Neural Network (CNN) and Support Vector Machine (SVM), which have proven results in recognizing different types of patterns. In this model, CNN works as a trainable feature extractor and SVM perf...
Uložené v:
| Vydané v: | Pattern recognition Ročník 45; číslo 4; s. 1318 - 1325 |
|---|---|
| Hlavní autori: | , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Kidlington
Elsevier Ltd
01.04.2012
Elsevier |
| Predmet: | |
| ISSN: | 0031-3203, 1873-5142 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | This paper presents a hybrid model of integrating the synergy of two superior classifiers: Convolutional Neural Network (CNN) and Support Vector Machine (SVM), which have proven results in recognizing different types of patterns. In this model, CNN works as a trainable feature extractor and SVM performs as a recognizer. This hybrid model automatically extracts features from the raw images and generates the predictions. Experiments have been conducted on the well-known MNIST digit database. Comparisons with other studies on the same database indicate that this fusion has achieved better results: a recognition rate of 99.81% without rejection, and a recognition rate of 94.40% with 5.60% rejection. These performances have been analyzed with reference to those by human subjects.
► We explored a new hybrid of Convolutional Neural Network and Support Vector Machine. ► Experiments were conducted on the MNIST database. ► The hybrid model has achieved better recognition and reliability performances. ► The best recognition rate was 99.81% without rejection. ► A reliability rate of 100% with 5.60% rejection was obtained. |
|---|---|
| AbstractList | This paper presents a hybrid model of integrating the synergy of two superior classifiers: Convolutional Neural Network (CNN) and Support Vector Machine (SVM), which have proven results in recognizing different types of patterns. In this model, CNN works as a trainable feature extractor and SVM performs as a recognizer. This hybrid model automatically extracts features from the raw images and generates the predictions. Experiments have been conducted on the well-known MNIST digit database. Comparisons with other studies on the same database indicate that this fusion has achieved better results: a recognition rate of 99.81% without rejection, and a recognition rate of 94.40% with 5.60% rejection. These performances have been analyzed with reference to those by human subjects. This paper presents a hybrid model of integrating the synergy of two superior classifiers: Convolutional Neural Network (CNN) and Support Vector Machine (SVM), which have proven results in recognizing different types of patterns. In this model, CNN works as a trainable feature extractor and SVM performs as a recognizer. This hybrid model automatically extracts features from the raw images and generates the predictions. Experiments have been conducted on the well-known MNIST digit database. Comparisons with other studies on the same database indicate that this fusion has achieved better results: a recognition rate of 99.81% without rejection, and a recognition rate of 94.40% with 5.60% rejection. These performances have been analyzed with reference to those by human subjects. ► We explored a new hybrid of Convolutional Neural Network and Support Vector Machine. ► Experiments were conducted on the MNIST database. ► The hybrid model has achieved better recognition and reliability performances. ► The best recognition rate was 99.81% without rejection. ► A reliability rate of 100% with 5.60% rejection was obtained. |
| Author | Suen, Ching Y. Niu, Xiao-Xiao |
| Author_xml | – sequence: 1 givenname: Xiao-Xiao surname: Niu fullname: Niu, Xiao-Xiao email: archernxx@hotmail.com – sequence: 2 givenname: Ching Y. surname: Suen fullname: Suen, Ching Y. email: suen@encs.concordia.ca |
| BackLink | http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=25604047$$DView record in Pascal Francis |
| BookMark | eNqFkLtOHDEUQC1EpCwkf5BiGqQ0M_gxY--kiIRWPCIRUuTRWtee68WrwV5sA4KKf-AP8yWZ1SIKilDd4p5zr3T2yG6IAQn5xGjDKJOHq2YNxcZlwyljDe0bytkOmbG5EnXHWr5LZpQKVgtOxXuyl_OKUqamxYycHFUh3uJYXd6b5IdqcXHx9_Hp55_vlR0hZ-88psrFVCWcHgT_4MOyuoQw3CVfCoZq8Etf8gfyzsGY8ePz3Ce_T45_Lc7q8x-n3xZH57UVsi81IHdzJ93AFTgplFNGWSOgHSTiXDBlemrAtAqkA9khqM5IIbHnpjPKgNgnn7d31yle32Au-spni-MIAeNN1kwqxlvRSTWhB88oZAujSxCsz3qd_BWke807SVvabrh2y9kUc07oXhBG9SavXultXr3Jq2mvp7yT9uWVZn2B4mMoCfz4lvx1K-PU6nZKrLP1GCwOfupc9BD9_w_8A7oBm_M |
| CODEN | PTNRA8 |
| CitedBy_id | crossref_primary_10_3233_JIFS_221389 crossref_primary_10_1016_j_neunet_2014_08_001 crossref_primary_10_1016_j_petsci_2023_11_010 crossref_primary_10_1007_s13369_021_05471_4 crossref_primary_10_3390_a15040129 crossref_primary_10_1109_TIM_2022_3192258 crossref_primary_10_1515_bmt_2020_0038 crossref_primary_10_3390_bioengineering10030294 crossref_primary_10_1016_j_inffus_2021_09_012 crossref_primary_10_1016_j_patrec_2017_05_019 crossref_primary_10_1016_j_biosystemseng_2020_07_019 crossref_primary_10_1016_j_neucom_2022_06_086 crossref_primary_10_1016_j_imavis_2024_104987 crossref_primary_10_1142_S021812662550402X crossref_primary_10_3390_math11041050 crossref_primary_10_1016_j_nucengdes_2021_111328 crossref_primary_10_1007_s41066_019_00158_6 crossref_primary_10_3233_IDT_230382 crossref_primary_10_1016_j_nanoen_2021_106654 crossref_primary_10_1007_s00500_020_05455_w crossref_primary_10_1109_JBHI_2021_3073632 crossref_primary_10_1016_j_bspc_2018_07_015 crossref_primary_10_1007_s10846_016_0440_2 crossref_primary_10_1007_s11760_016_1048_5 crossref_primary_10_1016_j_compbiomed_2025_110693 crossref_primary_10_1016_j_ultras_2022_106854 crossref_primary_10_3233_JIFS_233910 crossref_primary_10_3390_s21186273 crossref_primary_10_1007_s00521_014_1758_y crossref_primary_10_1007_s00521_020_04735_8 crossref_primary_10_1007_s11045_016_0466_4 crossref_primary_10_3390_ani12182425 crossref_primary_10_1016_j_istruc_2025_109959 crossref_primary_10_1109_ACCESS_2021_3056558 crossref_primary_10_1016_j_irbm_2020_07_002 crossref_primary_10_3390_s19194218 crossref_primary_10_1016_j_neucom_2018_02_100 crossref_primary_10_3390_app121910155 crossref_primary_10_1080_13682199_2023_2215031 crossref_primary_10_1038_s41598_022_17362_1 crossref_primary_10_1007_s12046_020_01484_1 crossref_primary_10_3390_agriculture13020352 crossref_primary_10_3390_sym9050075 crossref_primary_10_1007_s13042_019_00966_x crossref_primary_10_1016_j_patrec_2017_01_020 crossref_primary_10_3390_su15021502 crossref_primary_10_1016_j_jhydrol_2019_124482 crossref_primary_10_1016_j_patcog_2024_110637 crossref_primary_10_1007_s40846_016_0182_4 crossref_primary_10_1016_j_asoc_2022_109197 crossref_primary_10_1080_24751839_2019_1660845 crossref_primary_10_1109_ACCESS_2019_2938829 crossref_primary_10_1016_j_neunet_2025_107125 crossref_primary_10_1002_ett_3823 crossref_primary_10_1016_j_jelekin_2018_07_005 crossref_primary_10_1016_j_patcog_2017_08_004 crossref_primary_10_1007_s13748_022_00290_6 crossref_primary_10_1016_j_vibspec_2023_103647 crossref_primary_10_1088_1757_899X_928_3_032036 crossref_primary_10_1109_TETCI_2023_3297841 crossref_primary_10_1016_j_eswa_2021_114708 crossref_primary_10_1007_s00521_024_09657_3 crossref_primary_10_1007_s11042_023_16923_4 crossref_primary_10_1007_s11760_021_01997_0 crossref_primary_10_1016_j_engappai_2023_106237 crossref_primary_10_1007_s12293_015_0152_3 crossref_primary_10_1007_s11063_025_11783_5 crossref_primary_10_1016_j_procs_2015_12_018 crossref_primary_10_1109_ACCESS_2019_2897060 crossref_primary_10_1007_s11277_021_08903_4 crossref_primary_10_1007_s40595_014_0038_1 crossref_primary_10_1109_ACCESS_2017_2705798 crossref_primary_10_1007_s42979_020_00168_1 crossref_primary_10_1155_2023_2753941 crossref_primary_10_3390_app8122649 crossref_primary_10_1016_j_patcog_2013_04_016 crossref_primary_10_1109_ACCESS_2018_2853620 crossref_primary_10_1016_j_patcog_2013_04_018 crossref_primary_10_1016_j_neunet_2013_07_012 crossref_primary_10_1002_adma_202413430 crossref_primary_10_1016_j_bspc_2021_102814 crossref_primary_10_1155_2016_5642856 crossref_primary_10_1007_s13369_023_08170_4 crossref_primary_10_1016_j_procs_2020_03_309 crossref_primary_10_1109_ACCESS_2022_3204821 crossref_primary_10_1016_j_neucom_2019_07_098 crossref_primary_10_1109_ACCESS_2021_3087647 crossref_primary_10_1007_s00521_019_04163_3 crossref_primary_10_1155_2022_2034685 crossref_primary_10_3389_fninf_2022_973010 crossref_primary_10_1080_21642583_2021_1888819 crossref_primary_10_1109_TCBB_2022_3216661 crossref_primary_10_1080_10447318_2023_2175494 crossref_primary_10_1007_s10845_022_02053_5 crossref_primary_10_1016_j_imu_2024_101504 crossref_primary_10_1007_s10032_024_00501_x crossref_primary_10_1016_j_infrared_2019_103075 crossref_primary_10_38124_ijisrt_24may601 crossref_primary_10_1109_TBME_2018_2845706 crossref_primary_10_1007_s12524_022_01506_x crossref_primary_10_7717_peerj_cs_2960 crossref_primary_10_1007_s10618_020_00722_8 crossref_primary_10_1089_big_2020_0190 crossref_primary_10_1038_s41598_019_38966_0 crossref_primary_10_1002_asna_20240057 crossref_primary_10_1016_j_jvcir_2018_07_011 crossref_primary_10_1007_s11042_019_08355_w crossref_primary_10_1109_ACCESS_2020_3039531 crossref_primary_10_1016_j_asoc_2019_105959 crossref_primary_10_1007_s11069_022_05326_7 crossref_primary_10_3390_sym11091151 crossref_primary_10_1109_TFUZZ_2014_2370677 crossref_primary_10_1155_2023_8134627 crossref_primary_10_1007_s12206_022_1103_9 crossref_primary_10_1016_j_knosys_2020_105922 crossref_primary_10_1016_j_knosys_2022_110079 crossref_primary_10_3390_sym16111413 crossref_primary_10_1088_1742_6596_2171_1_012049 crossref_primary_10_3390_jimaging5040044 crossref_primary_10_1080_09540091_2019_1609420 crossref_primary_10_3390_app10165430 crossref_primary_10_1016_j_ecoinf_2021_101411 crossref_primary_10_1007_s13369_024_08710_6 crossref_primary_10_1016_j_patrec_2018_04_008 crossref_primary_10_1016_j_patcog_2016_10_018 crossref_primary_10_1007_s10044_014_0433_3 crossref_primary_10_3390_rs11202370 crossref_primary_10_1109_ACCESS_2018_2864553 crossref_primary_10_1109_TPDS_2021_3127712 crossref_primary_10_1016_j_asoc_2016_12_024 crossref_primary_10_3390_rs14020355 crossref_primary_10_1007_s11709_022_0819_z crossref_primary_10_1007_s10845_023_02109_0 crossref_primary_10_3389_fpls_2022_1006292 crossref_primary_10_32604_cmc_2023_038556 crossref_primary_10_1007_s00500_016_2199_6 crossref_primary_10_1021_acs_energyfuels_4c05402 crossref_primary_10_1016_j_procs_2015_07_529 crossref_primary_10_1007_s11220_019_0231_5 crossref_primary_10_1016_j_compbiomed_2021_104803 crossref_primary_10_1016_j_neucom_2015_08_013 crossref_primary_10_3390_s20123344 crossref_primary_10_1007_s00339_021_04512_x crossref_primary_10_1002_ima_22826 crossref_primary_10_1155_2019_6134610 crossref_primary_10_3389_fpls_2023_1234067 crossref_primary_10_1016_j_jocs_2017_11_011 crossref_primary_10_1007_s10845_020_01540_x crossref_primary_10_1016_j_sna_2022_113773 crossref_primary_10_1109_ACCESS_2020_3040298 crossref_primary_10_1016_j_neucom_2020_06_110 crossref_primary_10_1111_exsy_12842 crossref_primary_10_1109_ACCESS_2018_2878553 crossref_primary_10_3390_sym12101742 crossref_primary_10_1016_j_patcog_2016_12_005 crossref_primary_10_1155_2013_867924 crossref_primary_10_1016_j_combustflame_2021_111501 crossref_primary_10_1016_j_neucom_2017_08_062 crossref_primary_10_1016_j_patrec_2013_11_014 crossref_primary_10_1109_TIE_2017_2764861 crossref_primary_10_1016_j_compmedimag_2020_101782 crossref_primary_10_3390_s21061999 crossref_primary_10_1016_j_asoc_2021_108084 crossref_primary_10_1049_iet_its_2017_0136 crossref_primary_10_1007_s11042_018_6781_z crossref_primary_10_1007_s11042_020_09545_7 crossref_primary_10_38124_ijisrt_25jul782 crossref_primary_10_1016_j_ymssp_2024_111770 crossref_primary_10_1109_ACCESS_2020_3036912 crossref_primary_10_1109_ACCESS_2021_3079131 crossref_primary_10_1002_qre_3103 crossref_primary_10_1016_j_cosrev_2021_100374 crossref_primary_10_3233_IDA_173361 crossref_primary_10_3233_JIFS_230128 crossref_primary_10_3390_info9040097 crossref_primary_10_1515_bmt_2021_0170 crossref_primary_10_1007_s13369_017_2652_6 crossref_primary_10_1016_j_patrec_2016_01_016 crossref_primary_10_1016_j_engappai_2022_104978 crossref_primary_10_1109_ACCESS_2021_3131002 crossref_primary_10_1109_ACCESS_2022_3199358 crossref_primary_10_3390_app10175988 crossref_primary_10_3390_s20247013 crossref_primary_10_1007_s10462_019_09720_9 crossref_primary_10_1007_s11220_021_00363_1 crossref_primary_10_1186_s13638_017_0993_1 crossref_primary_10_3390_sym10120736 crossref_primary_10_3390_cancers15143608 crossref_primary_10_3390_ijgi10100687 crossref_primary_10_1016_j_aci_2015_05_001 crossref_primary_10_2196_41819 crossref_primary_10_3390_s19092056 crossref_primary_10_1016_j_eswa_2020_113784 crossref_primary_10_3390_s21020434 crossref_primary_10_1016_j_asoc_2015_08_038 crossref_primary_10_1007_s41870_021_00650_w crossref_primary_10_1016_j_patrec_2019_07_009 crossref_primary_10_3390_electronics10040427 crossref_primary_10_2514_1_J060117 crossref_primary_10_3233_JIFS_152549 crossref_primary_10_3389_fbuil_2020_00136 crossref_primary_10_1007_s00521_023_08644_4 crossref_primary_10_1080_09540091_2023_2286186 crossref_primary_10_1016_j_inffus_2020_10_002 crossref_primary_10_1016_j_ijmedinf_2025_106083 crossref_primary_10_1088_1755_1315_252_2_022046 crossref_primary_10_1109_ACCESS_2020_3037107 crossref_primary_10_1063_5_0165621 crossref_primary_10_1016_j_asoc_2022_109113 crossref_primary_10_1016_j_patcog_2016_07_012 crossref_primary_10_1016_j_patcog_2017_10_013 crossref_primary_10_3390_app122312432 crossref_primary_10_1016_j_neunet_2018_02_010 crossref_primary_10_1007_s11063_025_11741_1 crossref_primary_10_1155_2019_7541814 crossref_primary_10_1007_s42250_025_01239_7 crossref_primary_10_1016_j_procir_2020_05_091 crossref_primary_10_3390_math10224366 crossref_primary_10_1007_s00500_016_2095_0 crossref_primary_10_1016_j_asoc_2019_105661 crossref_primary_10_3233_JIFS_212378 crossref_primary_10_1016_j_patcog_2014_12_015 crossref_primary_10_1016_j_patcog_2018_12_015 crossref_primary_10_1007_s11063_019_10062_4 crossref_primary_10_1049_cit2_12347 crossref_primary_10_1049_iet_bmt_2018_5081 crossref_primary_10_1002_ppj2_20065 crossref_primary_10_1016_j_patcog_2015_11_005 crossref_primary_10_1016_j_lwt_2024_116458 crossref_primary_10_1007_s00500_015_1757_7 crossref_primary_10_1016_j_neucom_2016_08_024 crossref_primary_10_1016_j_procir_2022_05_184 crossref_primary_10_3389_fmats_2024_1431179 crossref_primary_10_1109_ACCESS_2019_2913620 crossref_primary_10_1016_j_neucom_2017_02_081 crossref_primary_10_1016_j_patcog_2014_07_023 crossref_primary_10_1109_TIFS_2017_2766583 crossref_primary_10_3390_app12115493 crossref_primary_10_1007_s11220_020_00288_1 crossref_primary_10_1016_j_procs_2016_05_512 crossref_primary_10_1109_ACCESS_2017_2716191 crossref_primary_10_1007_s10032_021_00368_2 crossref_primary_10_1016_j_triboint_2019_05_029 crossref_primary_10_3390_electronics12051243 crossref_primary_10_3390_app15010111 crossref_primary_10_1155_2017_5169675 crossref_primary_10_1007_s12293_016_0191_4 crossref_primary_10_1016_j_infrared_2016_08_009 crossref_primary_10_1016_j_petrol_2020_108105 crossref_primary_10_1016_j_asoc_2021_107115 crossref_primary_10_1016_j_neucom_2018_10_090 crossref_primary_10_1017_jfm_2023_573 crossref_primary_10_1007_s41095_020_0181_9 crossref_primary_10_1007_s00521_021_06693_1 crossref_primary_10_1109_ACCESS_2019_2946313 crossref_primary_10_1016_j_ijepes_2020_106583 crossref_primary_10_1109_ACCESS_2019_2960161 crossref_primary_10_1007_s11760_020_01807_z crossref_primary_10_3390_diagnostics10050329 crossref_primary_10_3390_electronics12122663 crossref_primary_10_1038_s41598_020_60277_y crossref_primary_10_1007_s42452_019_1579_9 crossref_primary_10_1016_j_infrared_2016_03_006 crossref_primary_10_1108_IJICC_04_2019_0031 crossref_primary_10_1145_3379449 crossref_primary_10_3390_info8040142 crossref_primary_10_1007_s11042_022_11978_1 crossref_primary_10_1007_s12559_021_09896_9 crossref_primary_10_3390_app12083715 crossref_primary_10_1002_ett_3612 crossref_primary_10_1038_s41598_024_74025_z crossref_primary_10_1007_s11042_023_14496_w crossref_primary_10_1016_j_patcog_2017_10_025 crossref_primary_10_1016_j_cogsys_2018_06_008 crossref_primary_10_3233_JIFS_169862 crossref_primary_10_3390_app122111301 crossref_primary_10_1007_s10015_019_00545_x crossref_primary_10_1109_ACCESS_2025_3559794 crossref_primary_10_17706_IJCEE_2019_11_1_41_52 crossref_primary_10_1109_TIM_2018_2890329 crossref_primary_10_3390_electronics12030645 crossref_primary_10_1016_j_patcog_2020_107420 crossref_primary_10_1016_j_newast_2015_11_001 crossref_primary_10_32604_cmc_2021_018758 crossref_primary_10_1007_s11042_023_15402_0 crossref_primary_10_1016_j_robot_2021_103829 crossref_primary_10_1007_s00521_020_05015_1 crossref_primary_10_1016_j_infrared_2018_07_013 crossref_primary_10_1007_s11063_023_11250_z crossref_primary_10_1016_j_eswa_2023_121214 crossref_primary_10_1080_08839514_2020_1723876 crossref_primary_10_1049_iet_ipr_2017_0745 crossref_primary_10_3390_electronics14010107 crossref_primary_10_1038_s41598_025_07676_1 crossref_primary_10_1364_AO_57_000322 crossref_primary_10_1016_j_neucom_2019_12_083 crossref_primary_10_1109_ACCESS_2024_3397465 crossref_primary_10_3389_fgene_2019_01303 crossref_primary_10_1016_j_aquaculture_2021_737128 crossref_primary_10_1049_iet_ipr_2017_0184 crossref_primary_10_1155_2016_3049632 crossref_primary_10_1007_s42979_021_00791_6 crossref_primary_10_1111_mice_12546 crossref_primary_10_1016_j_neucom_2019_10_013 crossref_primary_10_1364_AO_438287 crossref_primary_10_1109_TAES_2016_160061 crossref_primary_10_1016_j_ascom_2018_07_002 crossref_primary_10_1016_j_image_2018_08_003 crossref_primary_10_1049_joe_2019_0439 crossref_primary_10_1007_s10846_022_01652_x crossref_primary_10_1109_TASLP_2016_2632307 crossref_primary_10_1177_1369433220975574 crossref_primary_10_1177_0037549717709932 crossref_primary_10_1080_17455030_2022_2070683 crossref_primary_10_1155_2017_3792805 crossref_primary_10_1007_s10462_017_9555_5 crossref_primary_10_1007_s11947_017_2050_9 crossref_primary_10_1145_2629509 |
| Cites_doi | 10.1162/NECO_a_00052 10.1109/5.726791 10.1016/j.patcog.2006.10.011 10.1109/IVS.2005.1505106 10.1109/ICDAR.2009.80 10.1109/ICDAR.2003.1227801 10.1109/ICDAR.2005.200 10.1016/j.patrec.2004.10.019 10.1109/ICPR.2010.493 10.1109/72.991427 10.1109/TPAMI.2007.1153 |
| ContentType | Journal Article |
| Copyright | 2011 Elsevier Ltd 2015 INIST-CNRS |
| Copyright_xml | – notice: 2011 Elsevier Ltd – notice: 2015 INIST-CNRS |
| DBID | AAYXX CITATION IQODW 7SC 8FD JQ2 L7M L~C L~D |
| DOI | 10.1016/j.patcog.2011.09.021 |
| DatabaseName | CrossRef Pascal-Francis Computer and Information Systems 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 |
| DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Computer and Information Systems Abstracts |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science Applied Sciences |
| EISSN | 1873-5142 |
| EndPage | 1325 |
| ExternalDocumentID | 25604047 10_1016_j_patcog_2011_09_021 S0031320311004006 |
| GroupedDBID | --K --M -D8 -DT -~X .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 29O 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABFRF ABHFT ABJNI ABMAC ABTAH ABXDB ABYKQ ACBEA ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADMXK ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FD6 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM KZ1 LG9 LMP LY1 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UNMZH VOH WUQ XJE XPP ZMT ZY4 ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD AFXIZ AGCQF AGRNS BNPGV IQODW SSH 7SC 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c369t-ae2f8f6fd27af637f7b7cb3a4d6ee8317b90bab47a6fa65ea75b636e92b5b7ba3 |
| ISICitedReferencesCount | 471 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000300459000009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0031-3203 |
| IngestDate | Thu Oct 02 11:15:10 EDT 2025 Mon Jul 21 09:15:01 EDT 2025 Tue Nov 18 22:33:35 EST 2025 Sat Nov 29 07:27:03 EST 2025 Fri Feb 23 02:33:56 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | Convolutional Neural Network Hybrid model Support Vector Machine Handwritten digit recognition Performance evaluation Automatic classification Cellular neural nets Support vector machine Pattern recognition Neural network Signal classification Database Handwritten character recognition Manuscript character |
| Language | English |
| License | CC BY 4.0 |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c369t-ae2f8f6fd27af637f7b7cb3a4d6ee8317b90bab47a6fa65ea75b636e92b5b7ba3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PQID | 1671243567 |
| PQPubID | 23500 |
| PageCount | 8 |
| ParticipantIDs | proquest_miscellaneous_1671243567 pascalfrancis_primary_25604047 crossref_primary_10_1016_j_patcog_2011_09_021 crossref_citationtrail_10_1016_j_patcog_2011_09_021 elsevier_sciencedirect_doi_10_1016_j_patcog_2011_09_021 |
| PublicationCentury | 2000 |
| PublicationDate | 2012-04-01 |
| PublicationDateYYYYMMDD | 2012-04-01 |
| PublicationDate_xml | – month: 04 year: 2012 text: 2012-04-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | Kidlington |
| PublicationPlace_xml | – name: Kidlington |
| PublicationTitle | Pattern recognition |
| PublicationYear | 2012 |
| Publisher | Elsevier Ltd Elsevier |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier |
| References | Hastie, Tibshirani (bib9) 1988; 26 P.Y. Simard, D. Steinkraus, J.C. Platt, Best practice for convolutional neural networks applied to visual document analysis, in: Proceedings of the International Conference on Document Analysis and Recognition, Edinburgh, Scotland, 2, 2003, pp. 958–962. D.C. Ciresan, U. Meier, L.M. Gambardella, J. Schmidhuber, Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition, CoRR, abs/1003.0358, 2010. Vapnik (bib5) 1995 K. Mori, M. Matsugu, T. Suzuki, Face recognition using SVM fed with intermediate output of CNN for face detection, in: Proceedings of the IAPR Conference on Machine Vision Applications, Tsukuba Science City, Japan, May 2005, pp. 410–413. H. Cecotti, A. Belaid, Rejection strategy for convolutional neural network for adaptive topology applied to handwritten digits recognition, in: Proceedings of International Conference on Document Analysis and Recognition, Seoul, Korea, 2005, pp. 765–769. M. Szarvas, A. Yoshizawa, M. Yamamoto, J. Ogata, Pedestrian detection with convolutional neural networks, in: Proceedings of the IEEE on Intelligent Vehicles Symposium, June 2005, pp. 224–229. Wu, Lin, Weng (bib8) 2004; 5 . Hsu, Lin (bib6) 2002; 13 LeCun, Bottou, Bengio, Haffner (bib10) 1998; 86 W. Pan, T.D. Bui, C.Y. Suen, Isolated handwritten Farsi numerals recognition using sparse and over-complete representations, in: Proceedings of the International Conference on Document Analysis and Recognition, Barcelona, Spain, July 2009, pp. 586–590. Ranzato, Poultney, Chopra, LeCun (bib12) 2006 J.X. Dong, HeroSvm 2.1 Keysers, Deselaers, Gollan, Ney (bib17) 2007; 29 Lauer, Suen, Bloch (bib4) June 2007; 40 2001. C.C. Chang, C.J. Lin, LIBSVM: A Library for Support Vector Machines, Software Available at Suen, Tan (bib20) 2005; 26 Simard, Cun, Denker (bib15) 1993; 5 Y. Mizukami, K. Yamaguchi, J. Warrell, P. Li, S. Prince, CUDA implementation of deformable pattern recognition and its application to MNIST handwritten digit database, in: Proceedings of the 20th International Conference on Pattern Recognition, Istanbul, Turkey, 2010, pp. 2000–2004. The MNIST Database of Handwritten Digits Keysers (10.1016/j.patcog.2011.09.021_bib17) 2007; 29 Hsu (10.1016/j.patcog.2011.09.021_bib6) 2002; 13 Ranzato (10.1016/j.patcog.2011.09.021_bib12) 2006 Wu (10.1016/j.patcog.2011.09.021_bib8) 2004; 5 Vapnik (10.1016/j.patcog.2011.09.021_bib5) 1995 Hastie (10.1016/j.patcog.2011.09.021_bib9) 1988; 26 Lauer (10.1016/j.patcog.2011.09.021_bib4) 2007; 40 LeCun (10.1016/j.patcog.2011.09.021_bib10) 1998; 86 10.1016/j.patcog.2011.09.021_bib19 10.1016/j.patcog.2011.09.021_bib3 10.1016/j.patcog.2011.09.021_bib18 10.1016/j.patcog.2011.09.021_bib2 10.1016/j.patcog.2011.09.021_bib1 Simard (10.1016/j.patcog.2011.09.021_bib15) 1993; 5 10.1016/j.patcog.2011.09.021_bib16 Suen (10.1016/j.patcog.2011.09.021_bib20) 2005; 26 10.1016/j.patcog.2011.09.021_bib7 10.1016/j.patcog.2011.09.021_bib14 10.1016/j.patcog.2011.09.021_bib13 10.1016/j.patcog.2011.09.021_bib11 |
| References_xml | – start-page: 1134 year: 2006 end-page: 1144 ident: bib12 article-title: Efficient learning of sparse representations with an energy-based model publication-title: Advances in Neural Information Processing Systems – reference: The MNIST Database of Handwritten Digits, – volume: 26 start-page: 369 year: 2005 end-page: 379 ident: bib20 article-title: Analysis of errors on handwritten digits made by a multitude of classifiers publication-title: Pattern Recognition Letters – reference: M. Szarvas, A. Yoshizawa, M. Yamamoto, J. Ogata, Pedestrian detection with convolutional neural networks, in: Proceedings of the IEEE on Intelligent Vehicles Symposium, June 2005, pp. 224–229. – volume: 40 start-page: 1816 year: June 2007 end-page: 1824 ident: bib4 article-title: A trainable feature extractor for handwritten digit recognition publication-title: Pattern Recognition – reference: W. Pan, T.D. Bui, C.Y. Suen, Isolated handwritten Farsi numerals recognition using sparse and over-complete representations, in: Proceedings of the International Conference on Document Analysis and Recognition, Barcelona, Spain, July 2009, pp. 586–590. – reference: P.Y. Simard, D. Steinkraus, J.C. Platt, Best practice for convolutional neural networks applied to visual document analysis, in: Proceedings of the International Conference on Document Analysis and Recognition, Edinburgh, Scotland, 2, 2003, pp. 958–962. – reference: H. Cecotti, A. Belaid, Rejection strategy for convolutional neural network for adaptive topology applied to handwritten digits recognition, in: Proceedings of International Conference on Document Analysis and Recognition, Seoul, Korea, 2005, pp. 765–769. – volume: 26 start-page: 451 year: 1988 end-page: 471 ident: bib9 article-title: Classification by pairwise coupling publication-title: The Annals of Statistics – reference: J.X. Dong, HeroSvm 2.1, – reference: D.C. Ciresan, U. Meier, L.M. Gambardella, J. Schmidhuber, Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition, CoRR, abs/1003.0358, 2010. – volume: 86 start-page: 2278 year: 1998 end-page: 2324 ident: bib10 article-title: Gradient-based learning applied to document recognition publication-title: Proceedings of the IEEE – volume: 5 start-page: 50 year: 1993 end-page: 58 ident: bib15 article-title: Efficient pattern recognition using a new transformation distance publication-title: Advances in Neural Information Processing Systems – reference: , 2001. – volume: 29 start-page: 1422 year: 2007 end-page: 1435 ident: bib17 article-title: Deformation models for image recognition publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – year: 1995 ident: bib5 article-title: The Nature of Statistical Learning Theory – volume: 5 start-page: 975 year: 2004 end-page: 1005 ident: bib8 article-title: Probability estimates for multi-class classification by pairwise coupling publication-title: Journal of Machine Learning Research – reference: Y. Mizukami, K. Yamaguchi, J. Warrell, P. Li, S. Prince, CUDA implementation of deformable pattern recognition and its application to MNIST handwritten digit database, in: Proceedings of the 20th International Conference on Pattern Recognition, Istanbul, Turkey, 2010, pp. 2000–2004. – reference: K. Mori, M. Matsugu, T. Suzuki, Face recognition using SVM fed with intermediate output of CNN for face detection, in: Proceedings of the IAPR Conference on Machine Vision Applications, Tsukuba Science City, Japan, May 2005, pp. 410–413. – volume: 13 start-page: 415 year: 2002 end-page: 425 ident: bib6 article-title: A comparison of methods for multi-class support vector machines publication-title: IEEE Transactions on Neural Networks – reference: . – reference: C.C. Chang, C.J. Lin, LIBSVM: A Library for Support Vector Machines, Software Available at – ident: 10.1016/j.patcog.2011.09.021_bib19 – volume: 5 start-page: 975 year: 2004 ident: 10.1016/j.patcog.2011.09.021_bib8 article-title: Probability estimates for multi-class classification by pairwise coupling publication-title: Journal of Machine Learning Research – ident: 10.1016/j.patcog.2011.09.021_bib1 doi: 10.1162/NECO_a_00052 – volume: 26 start-page: 451 issue: 1 year: 1988 ident: 10.1016/j.patcog.2011.09.021_bib9 article-title: Classification by pairwise coupling publication-title: The Annals of Statistics – ident: 10.1016/j.patcog.2011.09.021_bib14 – volume: 86 start-page: 2278 issue: 11 year: 1998 ident: 10.1016/j.patcog.2011.09.021_bib10 article-title: Gradient-based learning applied to document recognition publication-title: Proceedings of the IEEE doi: 10.1109/5.726791 – ident: 10.1016/j.patcog.2011.09.021_bib3 – volume: 40 start-page: 1816 issue: 6 year: 2007 ident: 10.1016/j.patcog.2011.09.021_bib4 article-title: A trainable feature extractor for handwritten digit recognition publication-title: Pattern Recognition doi: 10.1016/j.patcog.2006.10.011 – ident: 10.1016/j.patcog.2011.09.021_bib7 – volume: 5 start-page: 50 year: 1993 ident: 10.1016/j.patcog.2011.09.021_bib15 article-title: Efficient pattern recognition using a new transformation distance publication-title: Advances in Neural Information Processing Systems – ident: 10.1016/j.patcog.2011.09.021_bib2 doi: 10.1109/IVS.2005.1505106 – ident: 10.1016/j.patcog.2011.09.021_bib11 doi: 10.1109/ICDAR.2009.80 – ident: 10.1016/j.patcog.2011.09.021_bib13 doi: 10.1109/ICDAR.2003.1227801 – ident: 10.1016/j.patcog.2011.09.021_bib18 doi: 10.1109/ICDAR.2005.200 – year: 1995 ident: 10.1016/j.patcog.2011.09.021_bib5 – start-page: 1134 year: 2006 ident: 10.1016/j.patcog.2011.09.021_bib12 article-title: Efficient learning of sparse representations with an energy-based model – volume: 26 start-page: 369 year: 2005 ident: 10.1016/j.patcog.2011.09.021_bib20 article-title: Analysis of errors on handwritten digits made by a multitude of classifiers publication-title: Pattern Recognition Letters doi: 10.1016/j.patrec.2004.10.019 – ident: 10.1016/j.patcog.2011.09.021_bib16 doi: 10.1109/ICPR.2010.493 – volume: 13 start-page: 415 issue: 2 year: 2002 ident: 10.1016/j.patcog.2011.09.021_bib6 article-title: A comparison of methods for multi-class support vector machines publication-title: IEEE Transactions on Neural Networks doi: 10.1109/72.991427 – volume: 29 start-page: 1422 issue: 8 year: 2007 ident: 10.1016/j.patcog.2011.09.021_bib17 article-title: Deformation models for image recognition publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2007.1153 |
| SSID | ssj0017142 |
| Score | 2.5805757 |
| Snippet | This paper presents a hybrid model of integrating the synergy of two superior classifiers: Convolutional Neural Network (CNN) and Support Vector Machine (SVM),... |
| SourceID | proquest pascalfrancis crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1318 |
| SubjectTerms | Applied sciences Artificial intelligence Classifiers Computer science; control theory; systems Connectionism. Neural networks Convolutional Neural Network Digits Exact sciences and technology Handwritten digit recognition Hybrid model Information, signal and communications theory Mathematical models Pattern recognition Recognition Rejection Signal and communications theory Signal processing Signal representation. Spectral analysis Signal, noise Support Vector Machine Support vector machines Telecommunications and information theory |
| Title | A novel hybrid CNN–SVM classifier for recognizing handwritten digits |
| URI | https://dx.doi.org/10.1016/j.patcog.2011.09.021 https://www.proquest.com/docview/1671243567 |
| Volume | 45 |
| WOSCitedRecordID | wos000300459000009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-5142 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017142 issn: 0031-3203 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Nb9MwFLdg44CE-EaUj8lI3KJMSezY8bEaRQyJaIcVlVNkJ_aWaUqqphuDvx47ttOMChUOXKzEShzF75fnX57fBwDvE4kZTXEVRmmpQswrFXKRiLBMFGUcKbPK9MUmaJ5niwU7ccU4u76cAG2a7OaGLf-rqHWfFrYJnf0HcQ-D6g59rIWuWy123f6V4KdB017Ly-D8hwnGCo5yrTO_fglKQ5NrZYJLjGehcxz6aSwFxnj-fVWvNX0OqvqstsmdPGU96TNwNsHgarTZuM-P50ZEi5q3oWkGc818ltu9fDP8t7Flwbho4LFlwYe8jNUnikOURGisPm02SAcTPNKFMXKaVbpTG-G8pbOt-eDicKnXnvbMZVVlh5GNnL6dIvu3pWtwKDTEDUeY3gX7CU2ZVm_70-PZ4vOwoURjbBPHuzfwUZS9q9_2k__EUh4seae_HWWLnmyt3z0pOX0MHrq_CTi1KHgC7sjmKXjk_iyg09ud7vLFO3zfM_BhCnucQIsT6HACNziBGidwhBM4wgm0OHkO5h9np0efQldSIywRYeuQy0RliqgqoVwRRBUVtBSI44pImWkuKVgkuMCUE8VJKjlNBUFEskSkggqOXoC9pm3kSwAlygRRpMpizjCtJBPUVKDiqUJRJqt0ApCfwqJ0-eZN2ZPLwjsWXhR24gsz8UXECj3xExAOdy1tvpUd11MvncJxRssFCw2vHXce3BLm8DiPpQl456VbaJ1rNtJ4I9urrogJ1bQYpYS-2jXIa3B_82m9AXvr1ZV8C-6V1-u6Wx04lP4C9PmiTw |
| linkProvider | Elsevier |
| 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+novel+hybrid+CNN-SVM+classifier+for+recognizing+handwritten+digits&rft.jtitle=Pattern+recognition&rft.au=NIU%2C+Xiao-Xiao&rft.au=SUEN%2C+Ching+Y&rft.date=2012-04-01&rft.pub=Elsevier&rft.issn=0031-3203&rft.volume=45&rft.issue=4&rft.spage=1318&rft.epage=1325&rft_id=info:doi/10.1016%2Fj.patcog.2011.09.021&rft.externalDBID=n%2Fa&rft.externalDocID=25604047 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon |