Hyperspectral Image Classification with Capsule Network Using Limited Training Samples
Deep learning techniques have boosted the performance of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs) have shown superior performance to that of the conventional machine learning algorithms. Recently, a novel type of neural networks called capsule net...
Uloženo v:
| Vydáno v: | Sensors (Basel, Switzerland) Ročník 18; číslo 9; s. 3153 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Switzerland
MDPI AG
18.09.2018
MDPI |
| Témata: | |
| ISSN: | 1424-8220, 1424-8220 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Deep learning techniques have boosted the performance of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs) have shown superior performance to that of the conventional machine learning algorithms. Recently, a novel type of neural networks called capsule networks (CapsNets) was presented to improve the most advanced CNNs. In this paper, we present a modified two-layer CapsNet with limited training samples for HSI classification, which is inspired by the comparability and simplicity of the shallower deep learning models. The presented CapsNet is trained using two real HSI datasets, i.e., the PaviaU (PU) and SalinasA datasets, representing complex and simple datasets, respectively, and which are used to investigate the robustness or representation of every model or classifier. In addition, a comparable paradigm of network architecture design has been proposed for the comparison of CNN and CapsNet. Experiments demonstrate that CapsNet shows better accuracy and convergence behavior for the complex data than the state-of-the-art CNN. For CapsNet using the PU dataset, the Kappa coefficient, overall accuracy, and average accuracy are 0.9456, 95.90%, and 96.27%, respectively, compared to the corresponding values yielded by CNN of 0.9345, 95.11%, and 95.63%. Moreover, we observed that CapsNet has much higher confidence for the predicted probabilities. Subsequently, this finding was analyzed and discussed with probability maps and uncertainty analysis. In terms of the existing literature, CapsNet provides promising results and explicit merits in comparison with CNN and two baseline classifiers, i.e., random forests (RFs) and support vector machines (SVMs). |
|---|---|
| AbstractList | Deep learning techniques have boosted the performance of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs) have shown superior performance to that of the conventional machine learning algorithms. Recently, a novel type of neural networks called capsule networks (CapsNets) was presented to improve the most advanced CNNs. In this paper, we present a modified two-layer CapsNet with limited training samples for HSI classification, which is inspired by the comparability and simplicity of the shallower deep learning models. The presented CapsNet is trained using two real HSI datasets, i.e., the PaviaU (PU) and SalinasA datasets, representing complex and simple datasets, respectively, and which are used to investigate the robustness or representation of every model or classifier. In addition, a comparable paradigm of network architecture design has been proposed for the comparison of CNN and CapsNet. Experiments demonstrate that CapsNet shows better accuracy and convergence behavior for the complex data than the state-of-the-art CNN. For CapsNet using the PU dataset, the Kappa coefficient, overall accuracy, and average accuracy are 0.9456, 95.90%, and 96.27%, respectively, compared to the corresponding values yielded by CNN of 0.9345, 95.11%, and 95.63%. Moreover, we observed that CapsNet has much higher confidence for the predicted probabilities. Subsequently, this finding was analyzed and discussed with probability maps and uncertainty analysis. In terms of the existing literature, CapsNet provides promising results and explicit merits in comparison with CNN and two baseline classifiers, i.e., random forests (RFs) and support vector machines (SVMs). Deep learning techniques have boosted the performance of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs) have shown superior performance to that of the conventional machine learning algorithms. Recently, a novel type of neural networks called capsule networks (CapsNets) was presented to improve the most advanced CNNs. In this paper, we present a modified two-layer CapsNet with limited training samples for HSI classification, which is inspired by the comparability and simplicity of the shallower deep learning models. The presented CapsNet is trained using two real HSI datasets, i.e., the PaviaU (PU) and SalinasA datasets, representing complex and simple datasets, respectively, and which are used to investigate the robustness or representation of every model or classifier. In addition, a comparable paradigm of network architecture design has been proposed for the comparison of CNN and CapsNet. Experiments demonstrate that CapsNet shows better accuracy and convergence behavior for the complex data than the state-of-the-art CNN. For CapsNet using the PU dataset, the Kappa coefficient, overall accuracy, and average accuracy are 0.9456, 95.90%, and 96.27%, respectively, compared to the corresponding values yielded by CNN of 0.9345, 95.11%, and 95.63%. Moreover, we observed that CapsNet has much higher confidence for the predicted probabilities. Subsequently, this finding was analyzed and discussed with probability maps and uncertainty analysis. In terms of the existing literature, CapsNet provides promising results and explicit merits in comparison with CNN and two baseline classifiers, i.e., random forests (RFs) and support vector machines (SVMs).Deep learning techniques have boosted the performance of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs) have shown superior performance to that of the conventional machine learning algorithms. Recently, a novel type of neural networks called capsule networks (CapsNets) was presented to improve the most advanced CNNs. In this paper, we present a modified two-layer CapsNet with limited training samples for HSI classification, which is inspired by the comparability and simplicity of the shallower deep learning models. The presented CapsNet is trained using two real HSI datasets, i.e., the PaviaU (PU) and SalinasA datasets, representing complex and simple datasets, respectively, and which are used to investigate the robustness or representation of every model or classifier. In addition, a comparable paradigm of network architecture design has been proposed for the comparison of CNN and CapsNet. Experiments demonstrate that CapsNet shows better accuracy and convergence behavior for the complex data than the state-of-the-art CNN. For CapsNet using the PU dataset, the Kappa coefficient, overall accuracy, and average accuracy are 0.9456, 95.90%, and 96.27%, respectively, compared to the corresponding values yielded by CNN of 0.9345, 95.11%, and 95.63%. Moreover, we observed that CapsNet has much higher confidence for the predicted probabilities. Subsequently, this finding was analyzed and discussed with probability maps and uncertainty analysis. In terms of the existing literature, CapsNet provides promising results and explicit merits in comparison with CNN and two baseline classifiers, i.e., random forests (RFs) and support vector machines (SVMs). |
| Author | Pu, Shengliang Deng, Fei Chen, Xuehong Shi, Yusheng Yuan, Ting Pu, Shengyan |
| AuthorAffiliation | 3 State Environmental Protection Key Laboratory of Satellites Remote Sensing, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China; shiys@radi.ac.cn 1 School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China; fdeng@sgg.whu.edu.cn (F.D.); shengliangpu@163.com (S.P.); ztyuan@whu.edu.cn (T.Y.) 4 State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China 2 State Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing 100875, China; cxh1216@gmail.com |
| AuthorAffiliation_xml | – name: 1 School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China; fdeng@sgg.whu.edu.cn (F.D.); shengliangpu@163.com (S.P.); ztyuan@whu.edu.cn (T.Y.) – name: 3 State Environmental Protection Key Laboratory of Satellites Remote Sensing, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China; shiys@radi.ac.cn – name: 2 State Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing 100875, China; cxh1216@gmail.com – name: 4 State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China |
| Author_xml | – sequence: 1 givenname: Fei surname: Deng fullname: Deng, Fei – sequence: 2 givenname: Shengliang orcidid: 0000-0003-4685-5621 surname: Pu fullname: Pu, Shengliang – sequence: 3 givenname: Xuehong surname: Chen fullname: Chen, Xuehong – sequence: 4 givenname: Yusheng orcidid: 0000-0001-7256-3628 surname: Shi fullname: Shi, Yusheng – sequence: 5 givenname: Ting surname: Yuan fullname: Yuan, Ting – sequence: 6 givenname: Shengyan surname: Pu fullname: Pu, Shengyan |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30231574$$D View this record in MEDLINE/PubMed |
| BookMark | eNplkk1v1DAQhq2qqJ8c-AMoEhc4LI0_kjgXpGoFdKUVHNpytWad8daLYwc7oeq_x9ttq7b44tH4nWfGM3NM9n3wSMg7Wn7mvC3PEpVly2nF98gRFUzMJGPl_jP7kByntClLxjmXB-SQZ4tWjTgivy7uBoxpQD1GcMWihzUWcwcpWWM1jDb44taON8UchjQ5LH7geBvi7-I6Wb8ulra3I3bFVQTrt45L6AeH6ZS8MeASvn24T8j1t69X84vZ8uf3xfx8OdOibscZpYCC0qqWAlHSrqq0bBC5FtQANrrqmJHQdqhNuzKmFRKbRgO0ZiU6TQ0_IYsdtwuwUUO0PcQ7FcCqe0eIawVxtNqh4lgBdlRnLMscI1vsAEDKkpk6J8-sLzvWMK167DT6bUteQF--eHuj1uGvqmld5S9kwMcHQAx_Jkyj6m3S6Bx4DFNSjOZTiZptpR9eSTdhij63KqtYLZtaCJFV759X9FTK4_iy4Gwn0DGkFNEobcf7oeUCrVO0VNsFUU8LkiM-vYp4hP6v_Qd717xl |
| CitedBy_id | crossref_primary_10_1049_ipr2_12330 crossref_primary_10_3390_rs14184639 crossref_primary_10_3389_fcomp_2020_00024 crossref_primary_10_1088_2515_7620_ade6d0 crossref_primary_10_1117_1_JEI_31_6_061817 crossref_primary_10_1049_iet_ipr_2019_0869 crossref_primary_10_3390_app10113769 crossref_primary_10_1109_TGRS_2020_3040203 crossref_primary_10_2478_ijanmc_2024_0003 crossref_primary_10_1155_2022_2836486 crossref_primary_10_3390_rs12203294 crossref_primary_10_1109_JSEN_2024_3386173 crossref_primary_10_1007_s10489_020_01725_0 crossref_primary_10_1109_TSM_2021_3134625 crossref_primary_10_1007_s11042_023_15017_5 crossref_primary_10_3390_rs13091629 crossref_primary_10_1109_JSTARS_2020_2968930 crossref_primary_10_3390_rs13030526 crossref_primary_10_1016_j_engappai_2023_106017 crossref_primary_10_1109_TGRS_2019_2945255 crossref_primary_10_1109_TGRS_2021_3049292 crossref_primary_10_1038_s41598_020_68453_w crossref_primary_10_1007_s00521_024_09527_y crossref_primary_10_1016_j_neucom_2022_08_073 crossref_primary_10_1038_s41598_020_70916_z crossref_primary_10_3390_rs13142646 crossref_primary_10_1109_TGRS_2025_3566399 crossref_primary_10_3389_fnbot_2021_648374 crossref_primary_10_3390_rs14071652 crossref_primary_10_1109_JSTARS_2021_3101511 crossref_primary_10_1109_TGRS_2024_3361906 crossref_primary_10_1007_s42044_023_00169_2 crossref_primary_10_1109_ACCESS_2024_3460394 crossref_primary_10_1109_LGRS_2020_2991405 crossref_primary_10_32604_cmc_2023_032429 crossref_primary_10_1007_s10462_023_10466_8 crossref_primary_10_1109_JSTARS_2019_2916495 crossref_primary_10_3390_app14209499 crossref_primary_10_3390_math9222984 crossref_primary_10_1109_TGRS_2020_3028223 crossref_primary_10_32604_cmc_2022_025202 crossref_primary_10_1080_23311916_2023_2203890 crossref_primary_10_3390_rs15071871 crossref_primary_10_1016_j_isprsjprs_2019_09_006 crossref_primary_10_1109_JSTSP_2019_2902305 crossref_primary_10_1080_07038992_2023_2248270 crossref_primary_10_3390_rs11050494 crossref_primary_10_1080_01431161_2022_2133579 crossref_primary_10_1007_s10489_024_06139_w crossref_primary_10_3390_rs12091395 crossref_primary_10_1016_j_neucom_2024_129027 crossref_primary_10_1109_TGRS_2023_3304836 crossref_primary_10_1109_TPWRD_2021_3049861 crossref_primary_10_1109_JSTARS_2020_3046414 crossref_primary_10_1109_ACCESS_2021_3111168 crossref_primary_10_1007_s41870_022_01075_9 crossref_primary_10_1016_j_infrared_2023_104983 crossref_primary_10_1007_s00521_023_08664_0 crossref_primary_10_3390_app122211393 crossref_primary_10_1049_ell2_70392 crossref_primary_10_3390_rs13163132 crossref_primary_10_1007_s11571_021_09777_9 crossref_primary_10_3390_s19030718 crossref_primary_10_1109_ACCESS_2020_3029174 crossref_primary_10_1007_s44174_025_00424_z crossref_primary_10_1109_LGRS_2020_2983196 crossref_primary_10_3390_s24144714 crossref_primary_10_1002_ima_22569 crossref_primary_10_1109_TGRS_2021_3135506 crossref_primary_10_3389_fpls_2022_1002312 crossref_primary_10_1007_s00500_020_04933_5 crossref_primary_10_1109_TGRS_2019_2912468 crossref_primary_10_1038_s41598_021_97901_4 crossref_primary_10_1007_s11042_021_11203_5 crossref_primary_10_1016_j_cosrev_2023_100584 crossref_primary_10_3390_electronics13101863 crossref_primary_10_1186_s40494_021_00614_0 crossref_primary_10_1016_j_bspc_2024_106636 crossref_primary_10_1007_s11042_023_15444_4 crossref_primary_10_3390_rs13132445 crossref_primary_10_1093_comjnl_bxae011 crossref_primary_10_1016_j_jag_2021_102603 crossref_primary_10_1007_s00500_022_07446_5 crossref_primary_10_1007_s10489_020_02180_7 crossref_primary_10_1109_TGRS_2019_2918080 crossref_primary_10_1016_j_jag_2023_103614 crossref_primary_10_1109_JSTARS_2021_3126427 crossref_primary_10_3390_rs11030223 crossref_primary_10_1007_s13246_023_01259_y crossref_primary_10_1109_LGRS_2020_2979604 crossref_primary_10_1109_ACCESS_2024_3390558 crossref_primary_10_1145_3674500 crossref_primary_10_1002_ima_22706 crossref_primary_10_1049_iet_rsn_2020_0241 crossref_primary_10_3390_s21165575 crossref_primary_10_1007_s00521_023_09058_y crossref_primary_10_3390_s25113293 crossref_primary_10_1038_s41598_025_87030_7 crossref_primary_10_1007_s10707_023_00492_7 |
| Cites_doi | 10.1109/LGRS.2017.2681128 10.1109/34.709601 10.1109/TGRS.2016.2584107 10.1155/2015/258619 10.1109/JSTARS.2015.2489838 10.1038/nature14539 10.3390/rs9060629 10.1109/MGRS.2013.2244672 10.1109/JSTARS.2015.2406339 10.1111/tgis.12164 10.3389/fninf.2018.00062 10.1109/IGARSS.2017.8127330 10.1109/ICASSP.2018.8461418 10.1109/IGARSS.2015.7326945 10.3390/rs9010067 10.1145/3178876.3186015 10.3390/rs10020299 10.3390/rs71114680 10.1109/TGRS.2017.2765364 10.1016/j.rse.2014.11.001 10.1007/978-3-030-11015-4_38 10.1109/79.974718 10.1016/j.neucom.2016.09.010 10.1109/TGRS.2016.2616355 10.1109/LGRS.2014.2375188 10.1109/LGRS.2010.2068537 10.1109/TGRS.2004.842481 10.1109/JSTARS.2016.2615073 10.1007/978-1-4614-0143-8 10.1109/ICIP.2018.8451379 10.1016/j.rse.2010.03.003 10.1016/j.rse.2007.07.028 10.1109/TGRS.2005.846154 10.1109/ICALIP.2018.8455251 10.1109/JSTARS.2014.2329330 10.3390/rs10050783 10.1016/j.rse.2014.08.038 10.1109/TGRS.2004.831865 10.1109/JSTARS.2013.2257422 10.1109/TGRS.2017.2755542 10.1080/10095020.2012.719684 |
| ContentType | Journal Article |
| Copyright | 2018. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2018 by the authors. 2018 |
| Copyright_xml | – notice: 2018. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2018 by the authors. 2018 |
| DBID | AAYXX CITATION NPM 3V. 7X7 7XB 88E 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA GHDGH K9. M0S M1P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM DOA |
| DOI | 10.3390/s18093153 |
| DatabaseName | CrossRef PubMed ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) ProQuest Hospital Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One ProQuest Central Korea Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) ProQuest Health & Medical Collection Medical Database Proquest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Central China ProQuest Central ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Health & Medical Research Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic Publicly Available Content Database CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1424-8220 |
| ExternalDocumentID | oai_doaj_org_article_3e5aed1ce7c248ef89edaaa8802f6e81 PMC6165568 30231574 10_3390_s18093153 |
| Genre | Journal Article |
| GeographicLocations | Beijing China United States--US China |
| GeographicLocations_xml | – name: China – name: Beijing China – name: United States--US |
| GrantInformation_xml | – fundername: Research Fund of State Key Laboratory of Geohazard Prevention and Geoenvironment Protection grantid: SKLGP2018Z006 |
| GroupedDBID | --- 123 2WC 53G 5VS 7X7 88E 8FE 8FG 8FI 8FJ AADQD AAHBH AAYXX ABDBF ABUWG ACUHS ADBBV ADMLS ADRAZ AENEX AFFHD AFKRA AFZYC ALMA_UNASSIGNED_HOLDINGS BENPR BPHCQ BVXVI CCPQU CITATION CS3 D1I DU5 E3Z EBD ESX F5P FYUFA GROUPED_DOAJ GX1 HH5 HMCUK HYE IPNFZ KQ8 L6V M1P M48 MODMG M~E OK1 OVT P2P P62 PHGZM PHGZT PIMPY PJZUB PPXIY PQQKQ PROAC PSQYO RIG RNS RPM TUS UKHRP XSB ~8M ALIPV NPM 3V. 7XB 8FK AZQEC DWQXO K9. PKEHL PQEST PQUKI PRINS 7X8 PUEGO 5PM |
| ID | FETCH-LOGICAL-c469t-11ae4115684ee81d55c87ee3c41fae7c5d2f8a9decf9bff948e77caa9fb4dc1f3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 130 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000446940600412&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1424-8220 |
| IngestDate | Tue Oct 14 19:06:35 EDT 2025 Tue Nov 04 02:03:32 EST 2025 Thu Oct 02 03:06:02 EDT 2025 Sat Nov 29 14:42:31 EST 2025 Thu Apr 03 07:05:45 EDT 2025 Sat Nov 29 07:12:25 EST 2025 Tue Nov 18 21:50:40 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 9 |
| Keywords | capsule network deep learning image classification possibility density hyperspectral |
| Language | English |
| License | Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c469t-11ae4115684ee81d55c87ee3c41fae7c5d2f8a9decf9bff948e77caa9fb4dc1f3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0003-4685-5621 0000-0001-7256-3628 |
| OpenAccessLink | https://doaj.org/article/3e5aed1ce7c248ef89edaaa8802f6e81 |
| PMID | 30231574 |
| PQID | 2126876444 |
| PQPubID | 2032333 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_3e5aed1ce7c248ef89edaaa8802f6e81 pubmedcentral_primary_oai_pubmedcentral_nih_gov_6165568 proquest_miscellaneous_2111154628 proquest_journals_2126876444 pubmed_primary_30231574 crossref_citationtrail_10_3390_s18093153 crossref_primary_10_3390_s18093153 |
| PublicationCentury | 2000 |
| PublicationDate | 2018-09-18 |
| PublicationDateYYYYMMDD | 2018-09-18 |
| PublicationDate_xml | – month: 09 year: 2018 text: 2018-09-18 day: 18 |
| PublicationDecade | 2010 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland – name: Basel |
| PublicationTitle | Sensors (Basel, Switzerland) |
| PublicationTitleAlternate | Sensors (Basel) |
| PublicationYear | 2018 |
| Publisher | MDPI AG MDPI |
| Publisher_xml | – name: MDPI AG – name: MDPI |
| References | Melgani (ref_15) 2004; 42 Yan (ref_5) 2015; 158 ref_14 ref_11 ref_10 ref_54 Yu (ref_27) 2017; 219 Zhong (ref_43) 2018; 56 Chen (ref_50) 2011; 8 Kussul (ref_46) 2017; 14 Chutia (ref_17) 2016; 20 ref_19 Landgrebe (ref_4) 2002; 19 Chen (ref_18) 2017; 7 ref_24 ref_22 Li (ref_26) 2017; 55 Zhang (ref_3) 2012; 15 ref_20 LeCun (ref_23) 2015; 521 Hu (ref_45) 2015; 7 ref_29 Zhong (ref_28) 2015; 12 Bruzzone (ref_49) 2005; 43 Ho (ref_13) 1998; 20 Schneider (ref_51) 2010; 114 ref_36 ref_35 ref_34 ref_32 Makantasis (ref_33) 2018; 99 Hu (ref_21) 2015; 2015 ref_31 ref_30 Plaza (ref_2) 2009; 113 Govender (ref_8) 2007; 33 Plaza (ref_16) 2013; 1 ref_39 ref_38 ref_37 Gevaert (ref_7) 2015; 8 Du (ref_1) 2013; 6 Ham (ref_12) 2005; 43 ref_47 ref_44 He (ref_9) 2018; 56 ref_42 ref_41 ref_40 Sexton (ref_52) 2015; 156 Yang (ref_53) 2017; 10 Eslami (ref_6) 2016; 9 Chen (ref_25) 2016; 54 ref_48 |
| References_xml | – volume: 99 start-page: 1 year: 2018 ident: ref_33 article-title: Tensor-Based Classification Models for Hyperspectral Data Analysis publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 14 start-page: 778 year: 2017 ident: ref_46 article-title: Deep learning classification of land cover and crop types using remote sensing data publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2017.2681128 – volume: 20 start-page: 832 year: 1998 ident: ref_13 article-title: The Random Subspace Method for Constructing Decision Forests publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/34.709601 – volume: 54 start-page: 6232 year: 2016 ident: ref_25 article-title: Deep feature extraction and classification of hyperspectral images based on convolutional neural networks publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2016.2584107 – volume: 33 start-page: 145 year: 2007 ident: ref_8 article-title: A review of hyperspectral remote sensing and its application in vegetation and water resource studies publication-title: Water SA – volume: 2015 start-page: 258619 year: 2015 ident: ref_21 article-title: Deep convolutional neural networks for hyperspectral image classification publication-title: J. Sens. doi: 10.1155/2015/258619 – volume: 9 start-page: 1808 year: 2016 ident: ref_6 article-title: Developing a spectral-based strategy for urban object detection from airborne hyperspectral TIR and visible data publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2015.2489838 – volume: 521 start-page: 436 year: 2015 ident: ref_23 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – ident: ref_44 doi: 10.3390/rs9060629 – ident: ref_42 – volume: 1 start-page: 6 year: 2013 ident: ref_16 article-title: Hyperspectral Remote Sensing Data Analysis and Future Challenges publication-title: IEEE Geosci. Remote Sens. Mag. doi: 10.1109/MGRS.2013.2244672 – volume: 8 start-page: 3140 year: 2015 ident: ref_7 article-title: Generation of Spectral–Temporal Response Surfaces by Combining Multispectral Satellite and Hyperspectral UAV Imagery for Precision Agriculture Applications publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2015.2406339 – volume: 20 start-page: 463 year: 2016 ident: ref_17 article-title: Hyperspectral Remote Sensing Classifications: A Perspective Survey publication-title: Trans. GIS doi: 10.1111/tgis.12164 – ident: ref_39 doi: 10.3389/fninf.2018.00062 – ident: ref_48 doi: 10.1109/IGARSS.2017.8127330 – ident: ref_20 doi: 10.1109/ICASSP.2018.8461418 – ident: ref_31 – ident: ref_19 doi: 10.1109/IGARSS.2015.7326945 – ident: ref_29 doi: 10.3390/rs9010067 – ident: ref_40 doi: 10.1145/3178876.3186015 – ident: ref_41 – ident: ref_47 doi: 10.3390/rs10020299 – ident: ref_38 – volume: 7 start-page: 14680 year: 2015 ident: ref_45 article-title: Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery publication-title: Remote Sens. doi: 10.3390/rs71114680 – volume: 56 start-page: 1579 year: 2018 ident: ref_9 article-title: Recent Advances on Spectral-Spatial Hyperspectral Image Classification: An Overview and New Guidelines publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2017.2765364 – volume: 158 start-page: 295 year: 2015 ident: ref_5 article-title: Urban land cover classification using airborne LiDAR data: A review publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2014.11.001 – ident: ref_35 doi: 10.1007/978-3-030-11015-4_38 – ident: ref_30 – volume: 19 start-page: 17 year: 2002 ident: ref_4 article-title: Hyperspectral image data analysis publication-title: IEEE Signal Process. Mag. doi: 10.1109/79.974718 – volume: 219 start-page: 88 year: 2017 ident: ref_27 article-title: Convolutional neural networks for hyperspectral image classification publication-title: Neurocomputing doi: 10.1016/j.neucom.2016.09.010 – ident: ref_24 – volume: 55 start-page: 844 year: 2017 ident: ref_26 article-title: Hyperspectral image classification using deep pixel-pair features publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2016.2616355 – volume: 12 start-page: 1028 year: 2015 ident: ref_28 article-title: Discriminant tensor spectral-spatial feature extraction for hyperspectral image classification publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2014.2375188 – volume: 8 start-page: 317 year: 2011 ident: ref_50 article-title: Change vector analysis in posterior probability space: A new method for land cover change detection publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2010.2068537 – volume: 43 start-page: 492 year: 2005 ident: ref_12 article-title: Investigation of the random forest framework for classification of hyperspectral data publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2004.842481 – ident: ref_37 – ident: ref_14 – volume: 10 start-page: 1105 year: 2017 ident: ref_53 article-title: Multiscale integration approach for land cover classification based on minimal entropy of posterior probability publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2016.2615073 – ident: ref_10 doi: 10.1007/978-1-4614-0143-8 – ident: ref_34 doi: 10.1109/ICIP.2018.8451379 – volume: 114 start-page: 1733 year: 2010 ident: ref_51 article-title: Mapping global urban areas using MODIS 500-m data: New methods and datasets based on ‘urban ecoregions’ publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2010.03.003 – volume: 113 start-page: S110 year: 2009 ident: ref_2 article-title: Recent advances in techniques for hyperspectral image processing publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2007.07.028 – volume: 43 start-page: 1351 year: 2005 ident: ref_49 article-title: Kernel-based methods for hyperspectral image classification publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2005.846154 – ident: ref_11 doi: 10.1109/ICALIP.2018.8455251 – ident: ref_54 – volume: 7 start-page: 2094 year: 2017 ident: ref_18 article-title: Deep Learning-Based Classification of Hyperspectral Data publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2014.2329330 – ident: ref_32 doi: 10.3390/rs10050783 – volume: 156 start-page: 418 year: 2015 ident: ref_52 article-title: A model for the propagation of uncertainty from continuous estimates of tree cover to categorical forest cover and change publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2014.08.038 – volume: 42 start-page: 1778 year: 2004 ident: ref_15 article-title: Classification of hyperspectral remote sensing images with support vector machines publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2004.831865 – ident: ref_36 – volume: 6 start-page: 459 year: 2013 ident: ref_1 article-title: Foreword to the special issue on hyperspectral remote sensing: Theory, methods, and applications publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2013.2257422 – ident: ref_22 – volume: 56 start-page: 847 year: 2018 ident: ref_43 article-title: Spectral-Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2017.2755542 – volume: 15 start-page: 143 year: 2012 ident: ref_3 article-title: Recent advances in hyperspectral image processing publication-title: Geo-Spat. Inf. Sci. doi: 10.1080/10095020.2012.719684 |
| SSID | ssj0023338 |
| Score | 2.59456 |
| Snippet | Deep learning techniques have boosted the performance of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs) have... |
| SourceID | doaj pubmedcentral proquest pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 3153 |
| SubjectTerms | capsule network Classification deep learning hyperspectral image classification Laboratories Neural networks possibility density Probability Remote sensing World Wide Web |
| SummonAdditionalLinks | – databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NT9wwEB21Sw_tgX63oRSZqodeInDsJM4JAQLBZYUKVNwirz0BJJqlm6W_vzOON7AV6qXXeKJMNJ7xjD1-D-Ar5Ws5ZdUqNQXvVmncTq2cmNSjVkpnZVVZF8gmyvHYXFxUJ3HDrYttlYuYGAK1nzreI9-iEFuQ52qtd25_pcwaxaerkULjKawwUpkewcrewfjk-1ByKarAejwhRcX9VsdoVUrmamkVCmD9j2WYfzdKPlh5Dl_-r86vYDXmnGK3nySv4Qm2b-DFAyTCt_DjiOrR_tolaSCOf1KYEYEwk1uJgvUEb9mKfUtl9Q2Kcd8-LkLLgYjXpMRZJJwQp5ZRh7t3cH54cLZ_lEbKhdRRnTxPpbSoKUksjEakVDbPnSkRldOysVi63GeNsZVH11STpqm0wbJ01lbNRHsnG_UeRu20xY8gPC38JF1QwKCiTVtTKHS51fQFl0k_SeDbwgS1i3jkTItxU1NdwtaqB2sl8GUQve1BOB4T2mM7DgKMmx0eTGeXdXTDWmFu0UtHv5KR7o2p0FtrKYiRpvTDCawvLFlHZ-7qezMmsDkMkxvy2YptcXrHMpKBjYrMJPChnzSDJszLJPOS3i6XptOSqssj7fVVgPouZMEQcWv_VusTPKc8LrSxSLMOo_nsDj_DM_d7ft3NNqJP_AGRtRoN priority: 102 providerName: ProQuest |
| Title | Hyperspectral Image Classification with Capsule Network Using Limited Training Samples |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/30231574 https://www.proquest.com/docview/2126876444 https://www.proquest.com/docview/2111154628 https://pubmed.ncbi.nlm.nih.gov/PMC6165568 https://doaj.org/article/3e5aed1ce7c248ef89edaaa8802f6e81 |
| Volume | 18 |
| WOSCitedRecordID | wos000446940600412&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: DOA dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: M~E dateStart: 20010101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: 7X7 dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: BENPR dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: PIMPY dateStart: 20010101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3BTtwwEB1R6KEcKtpSSKErF_XQSwSOHds5FrQIDqxWLVTbU-S1xwIJAmKXHvvtHTvZaLdC6qUXH-xJ4ozH9rxk_AbgM_lrJXnVIjcqfq2SeJRbPjW5RymELHRVWZeSTejRyEwm1Xgp1VeMCWvpgVvFHQosLXruULtCGgymQm-tJbMrgsJ06Logr2cBpjqoJQh5tTxCgkD94SyyVAleipXdJ5H0P-dZ_h0gubTjnG7B685VZF_bLr6BNWzewuYSgeA7-HFGMLI9LUk3YOd3tDqwlOcyRgAlpbP4pZWdWELDt8hGbdQ3S5ECrDvdxC67PBHsu41kwbNtuDodXp6c5V2mhNwRvJ3nnFuU5NspI5F04svSGY0onOTBkuZKXwRjK48uVNMQKlKk1s7aKkyldzyI97De3De4C8zTfk3SiuY5YS1pjRLoSivpCa7gfprBl4UGa9fRiMdsFrc1wYmo7LpXdgYHvehDy53xnNBxHIZeINJdpwoygrozgvpfRpDB_mIQ624OzmralBWt9fQSGXzqm2n2xF8itsH7pyjDIx-RKkwGO-2Y9z2J6ZR4qelqvWINK11dbWlurhNDt-IqMrt9-B_vtgevyElLMSrc7MP6_PEJP8JL92t-M3scwAs90ak0A9g4Ho7G3wZpKlB58XtIdePzi_HPP1ygEpc |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB6VFIly4P0wFFgQSFysdr1re31ACApVorZRJAJqT2azOy6VihPiBMSf4jcyu37QoIpbD1ztSTxrfzueWc9-H8BzytdiyqpFqBK3WiVxO9R8okKLUggZpVmmjRebSIdDdXiYjdbgV7sXxrVVtjHRB2o7NW6NfItCbEIzV0r5evYtdKpR7utqK6FRw2IPf_6gkq16NXhHz_dFFO2-H-_0w0ZVIDRUCi5CzjVKyoMSJREpW4tjo1JEYSQvNKYmtlGhdGbRFNmkKDKpME2N1lkxkdbwQtD_XoJ1SWBXPVgfDQ5GR12JJ6jiq_mLhMi2tyrHjiV4LFbeel4c4LyM9u_GzDNvut3r_9s9ugHXmpyavaknwU1Yw_IWXD3DtHgbPvWp3q63ldKI2eArhVHmBUFdq5RHJ3NL0mxHz6rlKbJh3R7PfEsFa7aBsXEjqME-aMeqXN2BjxcysLvQK6cl3gdmKbEh64QCIhWlUqtEoIm1pCuYiNtJAC_bR56bhm_dyX6c5lR3OXTkHToCeNaZzmqSkfOM3jrcdAaOF9wfmM6P8ybM5AJjjZYbGkpEvhcqQ6u1piBNntKAA9hskZM3warK_8AmgKfdaQoz7tuRLnG6dDbcETclkQrgXg3SzhOnO8XjlH6drsB3xdXVM-XJF09lnvDEUeA9-LdbT-BKf3ywn-8PhnsPYYNyVt-yw9Um9BbzJT6Cy-b74qSaP27mI4PPFw3v3457e78 |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3fb9MwED6NDSF44OeAwACDQOIl6hw7if2AEGxUqwZVJQYaT5nrXLZJIy1Ny7R_jb-Oc-KEFU287YHX5Nqck8-X75zzdwAvia_FxKpFqBK3WiVxMzR8rMIcpRAySrU2tm42kQ6Han9fj1bgV7sXxpVVtjGxDtT5xLo18h6F2IRmrpSyV_iyiNF2_-30R-g6SLkvrW07jQYiu3h2Sulb9WawTc_6VRT1P-xt7YS-w0BoKS2ch5wblMSJEiURibnFsVUporCSFwZTG-dRoYzO0RZ6XBRaKkxTa4wuxjK3vBD0v1dgjSi5pDm2Nhp8Gn3r0j1B2V-jZSSE3uxVTilL8FgsvQHrRgEXsdu_izTPvfX6t_7n-3Ubbnquzd41k-MOrGB5F26cU2C8B193KA9vtpvS6NngO4VXVjcKdSVUNWqZW6pmW2ZaLU6QDZuyeVaXWjC_PYzt-UYb7LNxasvVOny5lIHdh9VyUuJDYDkRHrJOKFBSsiqNSgTa2Ei6go14Pg7gdfv4M-t12F07kJOM8jGHlKxDSgAvOtNpIz5ykdF7h6HOwOmF1wcms8PMh59MYGww55aGEpHvhdKYG2MoeJOnNOAANloUZT6IVdkfCAXwvDtN4cd9UzIlThbOhjtBpyRSATxoANt54vpR8TilX6dLUF5ydflMeXxUS5wnPHHSeI_-7dYzuEaYzj4OhruP4TpR2bqSh6sNWJ3PFvgErtqf8-Nq9tRPTQYHl43u3-OFhH8 |
| 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=Hyperspectral+Image+Classification+with+Capsule+Network+Using+Limited+Training+Samples&rft.jtitle=Sensors+%28Basel%2C+Switzerland%29&rft.au=Deng%2C+Fei&rft.au=Pu%2C+Shengliang&rft.au=Chen%2C+Xuehong&rft.au=Shi%2C+Yusheng&rft.date=2018-09-18&rft.issn=1424-8220&rft.eissn=1424-8220&rft.volume=18&rft.issue=9&rft.spage=3153&rft_id=info:doi/10.3390%2Fs18093153&rft.externalDBID=n%2Fa&rft.externalDocID=10_3390_s18093153 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1424-8220&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1424-8220&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1424-8220&client=summon |