Group sparse autoencoder
Unsupervised feature extraction is gaining a lot of research attention following its success to represent any kind of noisy data. Owing to the presence of a lot of training parameters, these feature learning models are prone to overfitting. Different regularization methods have been explored in the...
Uloženo v:
| Vydáno v: | Image and vision computing Ročník 60; s. 64 - 74 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.04.2017
|
| Témata: | |
| ISSN: | 0262-8856, 1872-8138 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Unsupervised feature extraction is gaining a lot of research attention following its success to represent any kind of noisy data. Owing to the presence of a lot of training parameters, these feature learning models are prone to overfitting. Different regularization methods have been explored in the literature to avoid overfitting in deep learning models. In this research, we consider autoencoder as the feature learning architecture and propose ℓ2,1-norm based regularization to improve its learning capacity, called as Group Sparse AutoEncoder (GSAE). ℓ2,1-norm is based on the postulate that the features from the same class will have a common sparsity pattern in the feature space. We present the learning algorithm for group sparse encoding using majorization–minimization approach. The performance of the proposed algorithm is also studied on three baseline image datasets: MNIST, CIFAR-10, and SVHN. Further, using GSAE, we propose a novel deep learning based image representation for minutia detection from latent fingerprints. Latent fingerprints contain only a partial finger region, very noisy ridge patterns, and depending on the surface it is deposited, contain significant background noise. We formulate the problem of minutia extraction as a two-class classification problem and learn the descriptor using the novel formulation of GSAE. Experimental results on two publicly available latent fingerprint datasets show that the proposed algorithm yields state-of-the-art results for automated minutia extraction.
•Group Sparse AutoEncoder (GSAE) learns better discriminative features compared to an unsupervised autoencoder.•Class label based ℓ2,1-regularization is incorporated to squared error reconstruction loss function using a majorization-minimization approach.•The proposed GSAE is used to learn minutia representation from noisy latent fingerprint images.•Results on standard image datasets, MNIST, CIFAR-10, and SVHN and latent fingerprint image datasets, NIST SD-27 and MOLF, show effectiveness of the proposed GSAE feature extraction approach. |
|---|---|
| AbstractList | Unsupervised feature extraction is gaining a lot of research attention following its success to represent any kind of noisy data. Owing to the presence of a lot of training parameters, these feature learning models are prone to overfitting. Different regularization methods have been explored in the literature to avoid overfitting in deep learning models. In this research, we consider autoencoder as the feature learning architecture and propose ℓ2,1-norm based regularization to improve its learning capacity, called as Group Sparse AutoEncoder (GSAE). ℓ2,1-norm is based on the postulate that the features from the same class will have a common sparsity pattern in the feature space. We present the learning algorithm for group sparse encoding using majorization–minimization approach. The performance of the proposed algorithm is also studied on three baseline image datasets: MNIST, CIFAR-10, and SVHN. Further, using GSAE, we propose a novel deep learning based image representation for minutia detection from latent fingerprints. Latent fingerprints contain only a partial finger region, very noisy ridge patterns, and depending on the surface it is deposited, contain significant background noise. We formulate the problem of minutia extraction as a two-class classification problem and learn the descriptor using the novel formulation of GSAE. Experimental results on two publicly available latent fingerprint datasets show that the proposed algorithm yields state-of-the-art results for automated minutia extraction.
•Group Sparse AutoEncoder (GSAE) learns better discriminative features compared to an unsupervised autoencoder.•Class label based ℓ2,1-regularization is incorporated to squared error reconstruction loss function using a majorization-minimization approach.•The proposed GSAE is used to learn minutia representation from noisy latent fingerprint images.•Results on standard image datasets, MNIST, CIFAR-10, and SVHN and latent fingerprint image datasets, NIST SD-27 and MOLF, show effectiveness of the proposed GSAE feature extraction approach. |
| Author | Singh, Richa Majumdar, Angshul Sankaran, Anush Vatsa, Mayank |
| Author_xml | – sequence: 1 givenname: Anush surname: Sankaran fullname: Sankaran, Anush email: anushs@iiitd.ac.in – sequence: 2 givenname: Mayank orcidid: 0000-0001-5952-2274 surname: Vatsa fullname: Vatsa, Mayank email: mayank@iiitd.ac.in – sequence: 3 givenname: Richa surname: Singh fullname: Singh, Richa email: rsingh@iiitd.ac.in – sequence: 4 givenname: Angshul surname: Majumdar fullname: Majumdar, Angshul email: angshul@iiitd.ac.in |
| BookMark | eNqFj0FLwzAYhoNMsJvePXjYH2j90jZJ40GQ4aYw8KLn0CZfIGU2JekG_nsz6smDXr7vPbzPC8-SLAY_ICF3FAoKlN_3hftsTy4WJVBRAC0A2AXJaCPKvKFVsyAZlDzlhvErsoyxBwABQmbkdhf8cVzHsQ0R1-1x8jhobzBck0vbHiLe_PwV-dg-v29e8v3b7nXztM91BXzKO7SGY1d13EgJzOgyRQYgrTBWWIGdsTWlHNMVspSMa8tlzQEl012lqxV5mHd18DEGtEq7qZ2cH6bQuoOioM6Oqlezozo7KqAqOSa4_gWPIdXC13_Y44xhEjs5DCpql7zRuIB6Usa7vwe-AcSrb4I |
| CitedBy_id | crossref_primary_10_1049_ipr2_12113 crossref_primary_10_1109_TIP_2018_2840880 crossref_primary_10_1080_09715010_2017_1408433 crossref_primary_10_1109_TII_2019_2938890 crossref_primary_10_1016_j_neucom_2019_04_090 crossref_primary_10_1016_j_asoc_2025_113378 crossref_primary_10_1016_j_eswa_2019_04_012 crossref_primary_10_1016_j_cam_2023_115532 crossref_primary_10_1016_j_jvcir_2018_11_035 crossref_primary_10_1007_s11063_020_10223_w crossref_primary_10_1109_TASE_2022_3222759 crossref_primary_10_1109_ACCESS_2020_2972132 crossref_primary_10_1109_TITS_2018_2886280 crossref_primary_10_1007_s12065_020_00424_6 crossref_primary_10_1007_s10916_017_0814_4 crossref_primary_10_1007_s11042_017_5174_z crossref_primary_10_1007_s00500_020_04717_x crossref_primary_10_1109_JSTARS_2025_3580654 crossref_primary_10_1016_j_neucom_2020_02_051 crossref_primary_10_1109_TGRS_2021_3139931 crossref_primary_10_1109_TIFS_2023_3280742 crossref_primary_10_3390_cells8060521 crossref_primary_10_1002_int_21948 crossref_primary_10_3390_app13127055 crossref_primary_10_1016_j_asoc_2018_09_030 crossref_primary_10_3390_jcp3040037 crossref_primary_10_1371_journal_pone_0203192 crossref_primary_10_1016_j_neunet_2018_07_016 crossref_primary_10_1016_j_neucom_2018_07_050 crossref_primary_10_1049_2024_3179667 crossref_primary_10_1016_j_ins_2018_06_043 |
| Cites_doi | 10.1038/nature14539 10.1016/j.imavis.2006.02.007 10.1007/BF02551274 10.1109/TIP.2015.2487860 10.1162/neco.2008.12-07-661 10.1162/neco.1996.8.7.1341 10.1109/TIFS.2015.2446438 10.1162/neco.2006.18.7.1527 10.1109/TPAMI.2012.155 10.1109/TPAMI.2010.52 10.1109/ACCESS.2015.2428631 10.1049/ip-vis:20031078 10.1016/j.patcog.2016.04.014 10.1126/science.1127647 10.1109/TIT.2013.2245716 10.1109/TPAMI.2008.128 10.1162/neco.1992.4.4.473 10.1016/0893-6080(89)90020-8 10.1109/ACCESS.2014.2349879 10.1561/2200000006 |
| ContentType | Journal Article |
| Copyright | 2017 Elsevier B.V. |
| Copyright_xml | – notice: 2017 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.imavis.2017.01.005 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering |
| EISSN | 1872-8138 |
| EndPage | 74 |
| ExternalDocumentID | 10_1016_j_imavis_2017_01_005 S0262885617300136 |
| GroupedDBID | --K --M .~1 0R~ 1B1 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABOCM ABTAH ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD 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 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UHS UNMZH VOH WUQ XFK 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 |
| ID | FETCH-LOGICAL-c306t-befd6eb3b6d9905dc23b65009f7df7f7ebdf4116ef41792956cf69460e95cb3c3 |
| ISICitedReferencesCount | 42 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000399517800008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0262-8856 |
| IngestDate | Sat Nov 29 01:53:27 EST 2025 Tue Nov 18 22:54:55 EST 2025 Fri Feb 23 02:23:24 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Group sparsity Latent fingerprint Supervised autoencoder Minutia extraction |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c306t-befd6eb3b6d9905dc23b65009f7df7f7ebdf4116ef41792956cf69460e95cb3c3 |
| ORCID | 0000-0001-5952-2274 |
| PageCount | 11 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_imavis_2017_01_005 crossref_primary_10_1016_j_imavis_2017_01_005 elsevier_sciencedirect_doi_10_1016_j_imavis_2017_01_005 |
| PublicationCentury | 2000 |
| PublicationDate | April 2017 2017-04-00 |
| PublicationDateYYYYMMDD | 2017-04-01 |
| PublicationDate_xml | – month: 04 year: 2017 text: April 2017 |
| PublicationDecade | 2010 |
| PublicationTitle | Image and vision computing |
| PublicationYear | 2017 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Goodfellow, Warde-Farley, Mirza, Courville, Bengio (bb0060) 2013 Hong, Yu, Wan, Tao, Wang (bb0080) 2015; 24 Hinton, Salakhutdinov (bb0165) 2006; 313 Maltoni, Maio, Jain, Prabhakar (bb0200) 2009 Cybenko (bb0020) 1989; 2 Hornik, Stinchcombe, White (bb0025) 1989; 2 Sutskever, Hinton (bb0030) 2008; 20 Wan, Zeiler, Zhang, Cun, Fergus (bb0065) 2013 Netzer, Wang, Coates, Bissacco, Wu, Ng (bb0105) 2011 Fingerprint minutiae from latent and matching tenprint images, NIST Special Database 27. Available Sankaran, Pandey, Vatsa, Singh (bb0235) 2014 NBIS (NIST Biometric Image Software), Developed by National Institute of Standards and Technology (NIST) CASIA-Fingerprint V5, Chinese Academy of Sciences Institute of Automation (CASIA) Fingerprint Image Database Version 5.0. Lee, Gallagher, Tu (bb0195) 2016 Hinton, Osindero, Teh (bb0055) 2006; 18 Jia, Yang, Zang, Zhang, Tian (bb0255) 2012 Bengio, Lamblin, Popovici, Larochelle (bb0035) 2007; 19 . Srivastava, Hinton, Krizhevsky, Sutskever, Salakhutdinov (bb0045) 2014; 15 Nie, Huang, Cai, Ding (bb0135) 2010 Zheng, Yang (bb0085) 2006; 24 Fraz ao, Alexandre (bb0070) 2014 NIST 8-Bit Gray Scale Images of Fingerprint Image Groups (FIGS), NIST Special Database 14. Sang, Jin, Wan (bb0120) 2014; vol. I Rifai, Vincent, Muller, Glorot, Bengio (bb0050) 2011 Ortega-Garcia, Fierrez-Aguilar, Simon, Gonzalez, Faundez-Zanuy, Espinosa, Satue, Hernaez, Igarza, Vivaracho, Escudero, Moro (bb0250) 2003; 150 Sankaran, Dhamecha, Vatsa, Singh (bb0220) 2011 LeCun, Cortes (bb0095) 2010 Sankaran, Vatsa, Singh (bb0115) 2015; 3 Yang, Shen, Ma, Huang, Zhou (bb0140) 2011; vol. 22 Bengio (bb0015) 2009; 2 LeCun, Bengio, Hinton (bb0005) 2015; 521 Sankaran, Goswami, Vatsa, Singh, Majumdar (bb0265) 2017; 61 Krizhevsky, Hinton (bb0100) 2009 Davenport, Baraniuk, Scott (bb0155) 2006; vol 5 Majumdar, Ward (bb0130) 2012 Mairal (bb0090) 2013 MarcAurelio Ranzato, Chopra, LeCun (bb0010) 2007 Boyd, Parikh, Chu, Peleato, Eckstein (bb0150) 2011; 3 Feng, Zhou, Jain (bb0210) 2013; 35 Vincent, Larochelle, Lajoie, Bengio, Manzagol (bb0175) 2010; 11 Nowlan, Hinton (bb0040) 1992; 4 Swersky, Ranzato, Buchman, Marlin, Freitas (bb0180) 2011 Hong, Yu, Tao, Wang (bb0075) 2015; 62 Blumensath (bb0145) 2013; 59 Chen, Weinberger, Sha, Bengio (bb0170) 2014 Sankaran, Vatsa, Singh (bb0205) 2014; 2 Torralba, Fergus, Freeman (bb0160) 2008; 30 Cappelli, Ferrara, Maltoni (bb0230) 2010; 32 Gao, Zhang, Jia, Lu, Zhang (bb0125) 2015; 10 J.T. Springenberg, A. Dosovitskiy, T. Brox, M. Riedmiller, Striving for simplicity: the all convolutional net, arXiv preprint arXiv:1412.6806. Wolpert (bb0185) 1996; 8 Cybenko (10.1016/j.imavis.2017.01.005_bb0020) 1989; 2 MarcAurelio Ranzato (10.1016/j.imavis.2017.01.005_bb0010) 2007 Goodfellow (10.1016/j.imavis.2017.01.005_bb0060) 2013 Maltoni (10.1016/j.imavis.2017.01.005_bb0200) 2009 Wolpert (10.1016/j.imavis.2017.01.005_bb0185) 1996; 8 10.1016/j.imavis.2017.01.005_bb0260 Cappelli (10.1016/j.imavis.2017.01.005_bb0230) 2010; 32 Ortega-Garcia (10.1016/j.imavis.2017.01.005_bb0250) 2003; 150 Sutskever (10.1016/j.imavis.2017.01.005_bb0030) 2008; 20 Nie (10.1016/j.imavis.2017.01.005_bb0135) 2010 Sankaran (10.1016/j.imavis.2017.01.005_bb0115) 2015; 3 Jia (10.1016/j.imavis.2017.01.005_bb0255) 2012 Sankaran (10.1016/j.imavis.2017.01.005_bb0205) 2014; 2 Bengio (10.1016/j.imavis.2017.01.005_bb0015) 2009; 2 Davenport (10.1016/j.imavis.2017.01.005_bb0155) 2006; vol 5 LeCun (10.1016/j.imavis.2017.01.005_bb0095) 2010 Srivastava (10.1016/j.imavis.2017.01.005_bb0045) 2014; 15 Swersky (10.1016/j.imavis.2017.01.005_bb0180) 2011 Nowlan (10.1016/j.imavis.2017.01.005_bb0040) 1992; 4 Chen (10.1016/j.imavis.2017.01.005_bb0170) 2014 Sankaran (10.1016/j.imavis.2017.01.005_bb0235) 2014 Netzer (10.1016/j.imavis.2017.01.005_bb0105) 2011 Sankaran (10.1016/j.imavis.2017.01.005_bb0220) 2011 10.1016/j.imavis.2017.01.005_bb0245 LeCun (10.1016/j.imavis.2017.01.005_bb0005) 2015; 521 10.1016/j.imavis.2017.01.005_bb0240 Lee (10.1016/j.imavis.2017.01.005_bb0195) 2016 Boyd (10.1016/j.imavis.2017.01.005_bb0150) 2011; 3 Blumensath (10.1016/j.imavis.2017.01.005_bb0145) 2013; 59 Bengio (10.1016/j.imavis.2017.01.005_bb0035) 2007; 19 Hong (10.1016/j.imavis.2017.01.005_bb0080) 2015; 24 Yang (10.1016/j.imavis.2017.01.005_bb0140) 2011; vol. 22 10.1016/j.imavis.2017.01.005_bb0110 Hinton (10.1016/j.imavis.2017.01.005_bb0055) 2006; 18 Gao (10.1016/j.imavis.2017.01.005_bb0125) 2015; 10 Majumdar (10.1016/j.imavis.2017.01.005_bb0130) 2012 Rifai (10.1016/j.imavis.2017.01.005_bb0050) 2011 Vincent (10.1016/j.imavis.2017.01.005_bb0175) 2010; 11 10.1016/j.imavis.2017.01.005_bb0190 Sankaran (10.1016/j.imavis.2017.01.005_bb0265) 2017; 61 Zheng (10.1016/j.imavis.2017.01.005_bb0085) 2006; 24 Hong (10.1016/j.imavis.2017.01.005_bb0075) 2015; 62 Hornik (10.1016/j.imavis.2017.01.005_bb0025) 1989; 2 Torralba (10.1016/j.imavis.2017.01.005_bb0160) 2008; 30 Krizhevsky (10.1016/j.imavis.2017.01.005_bb0100) 2009 Hinton (10.1016/j.imavis.2017.01.005_bb0165) 2006; 313 Feng (10.1016/j.imavis.2017.01.005_bb0210) 2013; 35 Fraz ao (10.1016/j.imavis.2017.01.005_bb0070) 2014 Sang (10.1016/j.imavis.2017.01.005_bb0120) 2014; vol. I Wan (10.1016/j.imavis.2017.01.005_bb0065) 2013 Mairal (10.1016/j.imavis.2017.01.005_bb0090) 2013 |
| References_xml | – volume: 24 start-page: 819 year: 2006 end-page: 826 ident: bb0085 article-title: Supervised locality pursuit embedding for pattern classification publication-title: Image Vis. Comput. – start-page: 1058 year: 2013 end-page: 1066 ident: bb0065 article-title: Regularization of neural networks using dropconnect publication-title: International Conference on Machine Learning – volume: 62 start-page: 3742 year: 2015 end-page: 3751 ident: bb0075 article-title: Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval publication-title: IEEE Trans. Ind. Electron. – volume: vol. 22 start-page: 1589 year: 2011 ident: bb0140 article-title: L2, 1-norm regularized discriminative feature selection for unsupervised learning publication-title: International Joint Conference on Artificial Intelligence – volume: 32 start-page: 2128 year: 2010 end-page: 2141 ident: bb0230 article-title: Minutia cylinder-code: a new representation and matching technique for fingerprint recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2013 ident: bb0060 article-title: Maxout networks publication-title: International Conference on Machine Learning – year: 2010 ident: bb0095 article-title: MNIST Handwritten Digit Database – start-page: 5 year: 2011 ident: bb0105 article-title: Reading digits in natural images with unsupervised feature learning publication-title: NIPS Workshop on Deep Learning and Unsupervised Feature Learning – start-page: 3421 year: 2012 end-page: 3424 ident: bb0130 article-title: Synthesis and analysis prior algorithms for joint-sparse recovery publication-title: IEEE International Conference on Acoustics, Speech and Signal Processing – volume: 30 start-page: 1958 year: 2008 end-page: 1970 ident: bb0160 article-title: 80 million tiny images: a large data set for nonparametric object and scene recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: bb0005 article-title: Deep learning publication-title: Nature – volume: 2 start-page: 1 year: 2009 end-page: 127 ident: bb0015 article-title: Learning deep architectures for AI publication-title: Found. Trends Mach. Learn. – reference: CASIA-Fingerprint V5, Chinese Academy of Sciences Institute of Automation (CASIA) Fingerprint Image Database Version 5.0. – start-page: 833 year: 2011 end-page: 840 ident: bb0050 article-title: Contractive auto-encoders: explicit invariance during feature extraction publication-title: International Conference on Machine Learning – year: 2016 ident: bb0195 article-title: Generalizing pooling functions in convolutional neural networks: mixed, gated, and tree publication-title: International Conference on Artificial Intelligence and Statistics – volume: 61 start-page: 674 year: 2017 end-page: 685 ident: bb0265 article-title: Class sparsity signature based restricted Boltzmann machine publication-title: Pattern Recogn. – reference: NIST 8-Bit Gray Scale Images of Fingerprint Image Groups (FIGS), NIST Special Database 14. – start-page: 1 year: 2014 end-page: 7 ident: bb0235 article-title: On latent fingerprint minutiae extraction using stacked denoising sparse autoencoders publication-title: IEEE International Joint Conference on Biometrics – year: 2007 ident: bb0010 article-title: Efficient learning of sparse representations with an energy-based model publication-title: Advances in Neural Information Processing Systems – volume: 2 start-page: 359 year: 1989 end-page: 366 ident: bb0025 article-title: Multilayer feedforward networks are universal approximators publication-title: Neural Netw. – volume: 2 start-page: 982 year: 2014 end-page: 1004 ident: bb0205 article-title: Latent fingerprint matching: a survey publication-title: IEEE Access – start-page: 3001 year: 2012 end-page: 3004 ident: bb0255 article-title: A cross-device matching fingerprint database from multi-type sensors publication-title: International Conference on Pattern Recognition – volume: 8 start-page: 1341 year: 1996 end-page: 1390 ident: bb0185 article-title: The lack of a priori distinctions between learning algorithms publication-title: Neural computation – volume: 35 start-page: 925 year: 2013 end-page: 940 ident: bb0210 article-title: Orientation field estimation for latent fingerprint enhancement publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1 year: 2011 end-page: 6 ident: bb0220 article-title: On matching latent to latent fingerprints publication-title: Proceedings of International Joint Conference on Biometrics – volume: 59 start-page: 3466 year: 2013 end-page: 3474 ident: bb0145 article-title: Compressed sensing with nonlinear observations and related nonlinear optimization problems publication-title: IEEE Trans. Inf. Theory – volume: 2 start-page: 303 year: 1989 end-page: 314 ident: bb0020 article-title: Approximation by superpositions of a sigmoidal function publication-title: Math. Control Signals Syst. – volume: 4 start-page: 473 year: 1992 end-page: 493 ident: bb0040 article-title: Simplifying neural networks by soft weight-sharing publication-title: Neural Comput. – volume: 3 start-page: 1 year: 2011 end-page: 122 ident: bb0150 article-title: Distributed optimization and statistical learning via the alternating direction method of multipliers publication-title: Found. Trends® Mach. Learn. – start-page: 282 year: 2014 end-page: 289 ident: bb0070 article-title: Dropall: generalization of two convolutional neural network regularization methods publication-title: Image Analysis and Recognition – volume: 20 start-page: 2629 year: 2008 end-page: 2636 ident: bb0030 article-title: Deep, narrow sigmoid belief networks are universal approximators publication-title: Neural Comput. – volume: 313 start-page: 504 year: 2006 end-page: 507 ident: bb0165 article-title: Reducing the dimensionality of data with neural networks publication-title: Science – reference: NBIS (NIST Biometric Image Software), Developed by National Institute of Standards and Technology (NIST), – reference: Fingerprint minutiae from latent and matching tenprint images, NIST Special Database 27. Available: – volume: 19 start-page: 153 year: 2007 ident: bb0035 article-title: Greedy layerwise training of deep networks publication-title: Advances in neural information processing systems – volume: 3 start-page: 653 year: 2015 end-page: 665 ident: bb0115 article-title: Multisensor optical and latent fingerprint database publication-title: IEEE Access – year: 2009 ident: bb0100 article-title: Learning Multiple Layers of Features from Tiny Images – volume: 15 start-page: 1929 year: 2014 end-page: 1958 ident: bb0045 article-title: Dropout: a simple way to prevent neural networks from overfitting publication-title: J. Mach. Learn. Res. – volume: 150 start-page: 395 year: 2003 end-page: 401 ident: bb0250 article-title: MCYT baseline corpus: a bimodal biometric database publication-title: IEE Proceedings on Vision, Image and Signal Processing – volume: vol. I start-page: 521 year: 2014 end-page: 531 ident: bb0120 article-title: Discriminative feature learning for action recognition using a stacked denoising autoencoder publication-title: Intelligent Data Analysis and Its Applications – volume: 18 start-page: 1527 year: 2006 end-page: 1554 ident: bb0055 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Comput. – volume: 10 start-page: 2108 year: 2015 end-page: 2118 ident: bb0125 article-title: Single sample face recognition via learning deep supervised autoencoders publication-title: IEEE Trans. Inf. Forensics Secur. – start-page: 1813 year: 2010 end-page: 1821 ident: bb0135 article-title: Efficient and robust feature selection via joint L2, 1-norms minimization publication-title: Advances in Neural Information Processing Systems – reference: J.T. Springenberg, A. Dosovitskiy, T. Brox, M. Riedmiller, Striving for simplicity: the all convolutional net, arXiv preprint arXiv:1412.6806. – reference: . – start-page: 1201 year: 2011 end-page: 1208 ident: bb0180 article-title: On autoencoders and score matching for energy based models publication-title: International Conference on Machine Learning – start-page: 1476 year: 2014 end-page: 1484 ident: bb0170 article-title: Marginalized denoising auto-encoders for nonlinear representations publication-title: International Conference on Machine Learning – volume: vol 5 year: 2006 ident: bb0155 article-title: Controlling False Alarms with Support Vector Machines publication-title: International Conference on Acoustics, Speech and Signal Processing, 2006 – year: 2009 ident: bb0200 article-title: Handbook of Fingerprint Recognition – volume: 24 start-page: 5659 year: 2015 end-page: 5670 ident: bb0080 article-title: Multimodal deep autoencoder for human pose recovery publication-title: IEEE Trans. Image Process. – volume: 11 start-page: 3371 year: 2010 end-page: 3408 ident: bb0175 article-title: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion publication-title: J. Mach. Learn. Res. – start-page: 2283 year: 2013 end-page: 2291 ident: bb0090 article-title: Stochastic majorization–minimization algorithms for large-scale optimization publication-title: Advances in Neural Information Processing Systems – volume: 15 start-page: 1929 issue: 1 year: 2014 ident: 10.1016/j.imavis.2017.01.005_bb0045 article-title: Dropout: a simple way to prevent neural networks from overfitting publication-title: J. Mach. Learn. Res. – ident: 10.1016/j.imavis.2017.01.005_bb0190 – start-page: 1201 year: 2011 ident: 10.1016/j.imavis.2017.01.005_bb0180 article-title: On autoencoders and score matching for energy based models – start-page: 1 year: 2011 ident: 10.1016/j.imavis.2017.01.005_bb0220 article-title: On matching latent to latent fingerprints – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.imavis.2017.01.005_bb0005 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – ident: 10.1016/j.imavis.2017.01.005_bb0245 – start-page: 833 year: 2011 ident: 10.1016/j.imavis.2017.01.005_bb0050 article-title: Contractive auto-encoders: explicit invariance during feature extraction – volume: 19 start-page: 153 year: 2007 ident: 10.1016/j.imavis.2017.01.005_bb0035 article-title: Greedy layerwise training of deep networks publication-title: Advances in neural information processing systems – volume: 24 start-page: 819 issue: 8 year: 2006 ident: 10.1016/j.imavis.2017.01.005_bb0085 article-title: Supervised locality pursuit embedding for pattern classification publication-title: Image Vis. Comput. doi: 10.1016/j.imavis.2006.02.007 – start-page: 1476 year: 2014 ident: 10.1016/j.imavis.2017.01.005_bb0170 article-title: Marginalized denoising auto-encoders for nonlinear representations – volume: 2 start-page: 303 issue: 4 year: 1989 ident: 10.1016/j.imavis.2017.01.005_bb0020 article-title: Approximation by superpositions of a sigmoidal function publication-title: Math. Control Signals Syst. doi: 10.1007/BF02551274 – start-page: 1 year: 2014 ident: 10.1016/j.imavis.2017.01.005_bb0235 article-title: On latent fingerprint minutiae extraction using stacked denoising sparse autoencoders – year: 2013 ident: 10.1016/j.imavis.2017.01.005_bb0060 article-title: Maxout networks – volume: 24 start-page: 5659 issue: 12 year: 2015 ident: 10.1016/j.imavis.2017.01.005_bb0080 article-title: Multimodal deep autoencoder for human pose recovery publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2015.2487860 – volume: vol. 22 start-page: 1589 year: 2011 ident: 10.1016/j.imavis.2017.01.005_bb0140 article-title: L2, 1-norm regularized discriminative feature selection for unsupervised learning – volume: 20 start-page: 2629 issue: 11 year: 2008 ident: 10.1016/j.imavis.2017.01.005_bb0030 article-title: Deep, narrow sigmoid belief networks are universal approximators publication-title: Neural Comput. doi: 10.1162/neco.2008.12-07-661 – start-page: 1813 year: 2010 ident: 10.1016/j.imavis.2017.01.005_bb0135 article-title: Efficient and robust feature selection via joint L2, 1-norms minimization – volume: 8 start-page: 1341 issue: 7 year: 1996 ident: 10.1016/j.imavis.2017.01.005_bb0185 article-title: The lack of a priori distinctions between learning algorithms publication-title: Neural computation doi: 10.1162/neco.1996.8.7.1341 – ident: 10.1016/j.imavis.2017.01.005_bb0240 – ident: 10.1016/j.imavis.2017.01.005_bb0110 – volume: 10 start-page: 2108 issue: 10 year: 2015 ident: 10.1016/j.imavis.2017.01.005_bb0125 article-title: Single sample face recognition via learning deep supervised autoencoders publication-title: IEEE Trans. Inf. Forensics Secur. doi: 10.1109/TIFS.2015.2446438 – volume: 3 start-page: 1 issue: 1 year: 2011 ident: 10.1016/j.imavis.2017.01.005_bb0150 article-title: Distributed optimization and statistical learning via the alternating direction method of multipliers publication-title: Found. Trends® Mach. Learn. – volume: 11 start-page: 3371 year: 2010 ident: 10.1016/j.imavis.2017.01.005_bb0175 article-title: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion publication-title: J. Mach. Learn. Res. – volume: 18 start-page: 1527 issue: 7 year: 2006 ident: 10.1016/j.imavis.2017.01.005_bb0055 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Comput. doi: 10.1162/neco.2006.18.7.1527 – volume: vol 5 year: 2006 ident: 10.1016/j.imavis.2017.01.005_bb0155 article-title: Controlling False Alarms with Support Vector Machines – volume: 35 start-page: 925 issue: 4 year: 2013 ident: 10.1016/j.imavis.2017.01.005_bb0210 article-title: Orientation field estimation for latent fingerprint enhancement publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2012.155 – volume: 32 start-page: 2128 issue: 12 year: 2010 ident: 10.1016/j.imavis.2017.01.005_bb0230 article-title: Minutia cylinder-code: a new representation and matching technique for fingerprint recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2010.52 – start-page: 2283 year: 2013 ident: 10.1016/j.imavis.2017.01.005_bb0090 article-title: Stochastic majorization–minimization algorithms for large-scale optimization – volume: 3 start-page: 653 year: 2015 ident: 10.1016/j.imavis.2017.01.005_bb0115 article-title: Multisensor optical and latent fingerprint database publication-title: IEEE Access doi: 10.1109/ACCESS.2015.2428631 – volume: 150 start-page: 395 issue: 6 year: 2003 ident: 10.1016/j.imavis.2017.01.005_bb0250 article-title: MCYT baseline corpus: a bimodal biometric database publication-title: IEE Proceedings on Vision, Image and Signal Processing doi: 10.1049/ip-vis:20031078 – volume: 61 start-page: 674 year: 2017 ident: 10.1016/j.imavis.2017.01.005_bb0265 article-title: Class sparsity signature based restricted Boltzmann machine publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2016.04.014 – start-page: 3421 year: 2012 ident: 10.1016/j.imavis.2017.01.005_bb0130 article-title: Synthesis and analysis prior algorithms for joint-sparse recovery – volume: 313 start-page: 504 issue: 5786 year: 2006 ident: 10.1016/j.imavis.2017.01.005_bb0165 article-title: Reducing the dimensionality of data with neural networks publication-title: Science doi: 10.1126/science.1127647 – volume: 59 start-page: 3466 issue: 6 year: 2013 ident: 10.1016/j.imavis.2017.01.005_bb0145 article-title: Compressed sensing with nonlinear observations and related nonlinear optimization problems publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.2013.2245716 – start-page: 282 year: 2014 ident: 10.1016/j.imavis.2017.01.005_bb0070 article-title: Dropall: generalization of two convolutional neural network regularization methods – year: 2009 ident: 10.1016/j.imavis.2017.01.005_bb0100 – start-page: 5 year: 2011 ident: 10.1016/j.imavis.2017.01.005_bb0105 article-title: Reading digits in natural images with unsupervised feature learning – start-page: 1058 year: 2013 ident: 10.1016/j.imavis.2017.01.005_bb0065 article-title: Regularization of neural networks using dropconnect – volume: 30 start-page: 1958 issue: 11 year: 2008 ident: 10.1016/j.imavis.2017.01.005_bb0160 article-title: 80 million tiny images: a large data set for nonparametric object and scene recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2008.128 – year: 2007 ident: 10.1016/j.imavis.2017.01.005_bb0010 article-title: Efficient learning of sparse representations with an energy-based model – year: 2016 ident: 10.1016/j.imavis.2017.01.005_bb0195 article-title: Generalizing pooling functions in convolutional neural networks: mixed, gated, and tree – volume: 4 start-page: 473 issue: 4 year: 1992 ident: 10.1016/j.imavis.2017.01.005_bb0040 article-title: Simplifying neural networks by soft weight-sharing publication-title: Neural Comput. doi: 10.1162/neco.1992.4.4.473 – volume: vol. I start-page: 521 year: 2014 ident: 10.1016/j.imavis.2017.01.005_bb0120 article-title: Discriminative feature learning for action recognition using a stacked denoising autoencoder – volume: 62 start-page: 3742 issue: 6 year: 2015 ident: 10.1016/j.imavis.2017.01.005_bb0075 article-title: Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval publication-title: IEEE Trans. Ind. Electron. – volume: 2 start-page: 359 issue: 5 year: 1989 ident: 10.1016/j.imavis.2017.01.005_bb0025 article-title: Multilayer feedforward networks are universal approximators publication-title: Neural Netw. doi: 10.1016/0893-6080(89)90020-8 – start-page: 3001 year: 2012 ident: 10.1016/j.imavis.2017.01.005_bb0255 article-title: A cross-device matching fingerprint database from multi-type sensors – year: 2010 ident: 10.1016/j.imavis.2017.01.005_bb0095 – year: 2009 ident: 10.1016/j.imavis.2017.01.005_bb0200 – ident: 10.1016/j.imavis.2017.01.005_bb0260 – volume: 2 start-page: 982 year: 2014 ident: 10.1016/j.imavis.2017.01.005_bb0205 article-title: Latent fingerprint matching: a survey publication-title: IEEE Access doi: 10.1109/ACCESS.2014.2349879 – volume: 2 start-page: 1 issue: 1 year: 2009 ident: 10.1016/j.imavis.2017.01.005_bb0015 article-title: Learning deep architectures for AI publication-title: Found. Trends Mach. Learn. doi: 10.1561/2200000006 |
| SSID | ssj0007079 |
| Score | 2.4059265 |
| Snippet | Unsupervised feature extraction is gaining a lot of research attention following its success to represent any kind of noisy data. Owing to the presence of a... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 64 |
| SubjectTerms | Group sparsity Latent fingerprint Minutia extraction Supervised autoencoder |
| Title | Group sparse autoencoder |
| URI | https://dx.doi.org/10.1016/j.imavis.2017.01.005 |
| Volume | 60 |
| WOSCitedRecordID | wos000399517800008&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: 1872-8138 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0007079 issn: 0262-8856 databaseCode: AIEXJ dateStart: 19950201 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6hlAMc2hJALbTIB27IyO_1HiPUqu2h4lBQbtY-aQJxIj9Q-ffMetZ2RKtAD1wsy9pdP2Y0Mzv-5htC3lOmrHCZn0qZ-InguZ-HJvB5SLnlwmMqwGYT9Po6n8_ZZ9eMs-7aCdCyzO_u2Oa_ihqugbBt6ewjxD0sChfgHIQORxA7HP9J8JheAkNR1foDb5u1papUDoTrwtDLlYXq2Jw51pZ3yPK26d2Yzbjw8juvuCMYaOsha_yVNzXHKp9fMGYYD3Nvh0r9Mc-9bFcKMdyz8lt962CILs0ArmtEp6A1ijIwnTmygPemE1sBONuHbOTOi2LrnXv2GVMFy4-LleVQsMg62rGmBunoj_p_8H-4qQE82OPSlgWuUthViiAsOi7bvYimDMzb3uzybH41OGVLBIjpNnyLvoqyg_rdf5qHo5StyOPmkOy7LYM3Q1G_IE90OSUHbvvgOeNcT8nzLW7Jl-So0wMP9cDb0oNX5Mv52c2nC9-1wfAl7OcaX2ijMi1ikSkIHVIlIzhNITY2VBlqqBbKJGGYaWO7yUWw4ZUmY0kWaJZKEcv4NZmU61IfES-VMRMiThINYZ2RTHBuko4zEXYBCc-OSdy_diEdR7xtVfKj2PXRj4k_zNogR8pfxtP-ixYuzsP4rQA12TnzzSPv9JY8G3X5hEyaqtWn5Kn82Szq6p3Tkd99U3Qp |
| 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=Group+sparse+autoencoder&rft.jtitle=Image+and+vision+computing&rft.au=Sankaran%2C+Anush&rft.au=Vatsa%2C+Mayank&rft.au=Singh%2C+Richa&rft.au=Majumdar%2C+Angshul&rft.date=2017-04-01&rft.issn=0262-8856&rft.volume=60&rft.spage=64&rft.epage=74&rft_id=info:doi/10.1016%2Fj.imavis.2017.01.005&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_imavis_2017_01_005 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0262-8856&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0262-8856&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0262-8856&client=summon |