{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:57:01Z","timestamp":1780444621535,"version":"3.54.1"},"reference-count":54,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T00:00:00Z","timestamp":1537228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Research Fund of State Key Laboratory of Geohazard Prevention and Geoenvironment Protection","award":["SKLGP2018Z006"],"award-info":[{"award-number":["SKLGP2018Z006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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).<\/jats:p>","DOI":"10.3390\/s18093153","type":"journal-article","created":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T11:52:29Z","timestamp":1537271549000},"page":"3153","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":129,"title":["Hyperspectral Image Classification with Capsule Network Using Limited Training Samples"],"prefix":"10.3390","volume":"18","author":[{"given":"Fei","family":"Deng","sequence":"first","affiliation":[{"name":"School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4685-5621","authenticated-orcid":false,"given":"Shengliang","family":"Pu","sequence":"additional","affiliation":[{"name":"School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuehong","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing 100875, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7256-3628","authenticated-orcid":false,"given":"Yusheng","family":"Shi","sequence":"additional","affiliation":[{"name":"State Environmental Protection Key Laboratory of Satellites Remote Sensing, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengyan","family":"Pu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2018,9,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1109\/JSTARS.2013.2257422","article-title":"Foreword to the special issue on hyperspectral remote sensing: Theory, methods, and applications","volume":"6","author":"Du","year":"2013","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"S110","DOI":"10.1016\/j.rse.2007.07.028","article-title":"Recent advances in techniques for hyperspectral image processing","volume":"113","author":"Plaza","year":"2009","journal-title":"Remote Sens. Environ."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1080\/10095020.2012.719684","article-title":"Recent advances in hyperspectral image processing","volume":"15","author":"Zhang","year":"2012","journal-title":"Geo-Spat. Inf. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/79.974718","article-title":"Hyperspectral image data analysis","volume":"19","author":"Landgrebe","year":"2002","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.rse.2014.11.001","article-title":"Urban land cover classification using airborne LiDAR data: A review","volume":"158","author":"Yan","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1808","DOI":"10.1109\/JSTARS.2015.2489838","article-title":"Developing a spectral-based strategy for urban object detection from airborne hyperspectral TIR and visible data","volume":"9","author":"Eslami","year":"2016","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"3140","DOI":"10.1109\/JSTARS.2015.2406339","article-title":"Generation of Spectral\u2013Temporal Response Surfaces by Combining Multispectral Satellite and Hyperspectral UAV Imagery for Precision Agriculture Applications","volume":"8","author":"Gevaert","year":"2015","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_8","first-page":"145","article-title":"A review of hyperspectral remote sensing and its application in vegetation and water resource studies","volume":"33","author":"Govender","year":"2007","journal-title":"Water SA"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1579","DOI":"10.1109\/TGRS.2017.2765364","article-title":"Recent Advances on Spectral-Spatial Hyperspectral Image Classification: An Overview and New Guidelines","volume":"56","author":"He","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Lein, J.K. (2011). Environmental Sensing: Analytical Techniques for Earth Observation, Springer.","DOI":"10.1007\/978-1-4614-0143-8"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zou, J., Yao, C., Li, T., and Bai, G. (arXiv, 2018). HSI-CNN: A Novel Convolution Neural Network for Hyperspectral Image, arXiv.","DOI":"10.1109\/ICALIP.2018.8455251"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1109\/TGRS.2004.842481","article-title":"Investigation of the random forest framework for classification of hyperspectral data","volume":"43","author":"Ham","year":"2005","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1109\/34.709601","article-title":"The Random Subspace Method for Constructing Decision Forests","volume":"20","author":"Ho","year":"1998","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_14","unstructured":"Gualtieri, J.A., and Chettri, S. (2000, January 24\u201328). Support vector machines for classification of hyperspectral data. Proceedings of the Geoscience and Remote Sensing Symposium (IGARSS 2000), Honolulu, HI, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1778","DOI":"10.1109\/TGRS.2004.831865","article-title":"Classification of hyperspectral remote sensing images with support vector machines","volume":"42","author":"Melgani","year":"2004","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/MGRS.2013.2244672","article-title":"Hyperspectral Remote Sensing Data Analysis and Future Challenges","volume":"1","author":"Plaza","year":"2013","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1111\/tgis.12164","article-title":"Hyperspectral Remote Sensing Classifications: A Perspective Survey","volume":"20","author":"Chutia","year":"2016","journal-title":"Trans. GIS"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2094","DOI":"10.1109\/JSTARS.2014.2329330","article-title":"Deep Learning-Based Classification of Hyperspectral Data","volume":"7","author":"Chen","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Makantasis, K., Karantzalos, K., Doulamis, A., and Doulamis, N. (2015, January 26\u201331). Deep supervised learning for hyperspectral data classification through convolutional neural networks. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy.","DOI":"10.1109\/IGARSS.2015.7326945"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Makantasis, K., Doulamis, A., Doulamis, N., Nikitakis, A., and Voulodimos, A. (arXiv, 2018). Tensor-based Nonlinear Classifier for High-Order Data Analysis, arXiv.","DOI":"10.1109\/ICASSP.2018.8461418"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"258619","DOI":"10.1155\/2015\/258619","article-title":"Deep convolutional neural networks for hyperspectral image classification","volume":"2015","author":"Hu","year":"2015","journal-title":"J. Sens."},{"key":"ref_22","unstructured":"Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, MIT Press."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_24","unstructured":"LeCun, Y. (2018, August 17). LeNet-5, Convolutional Neural Networks. Available online: http:\/\/yann.lecun.com\/exdb\/lenet."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"6232","DOI":"10.1109\/TGRS.2016.2584107","article-title":"Deep feature extraction and classification of hyperspectral images based on convolutional neural networks","volume":"54","author":"Chen","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1109\/TGRS.2016.2616355","article-title":"Hyperspectral image classification using deep pixel-pair features","volume":"55","author":"Li","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.neucom.2016.09.010","article-title":"Convolutional neural networks for hyperspectral image classification","volume":"219","author":"Yu","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1109\/LGRS.2014.2375188","article-title":"Discriminant tensor spectral-spatial feature extraction for hyperspectral image classification","volume":"12","author":"Zhong","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, H., and Shen, Q. (2017). Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sens., 9.","DOI":"10.3390\/rs9010067"},{"key":"ref_30","unstructured":"Sabour, S., Frosst, N., and Hinton, G.E. (2017, January 4\u20139). Dynamic routing between capsules. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_31","unstructured":"Xi, E., Bing, S., and Jin, Y. (arXiv, 2017). Capsule Network Performance on Complex Data, arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wei, W., Zhang, J., Zhang, L., Tian, C., and Zhang, Y. (2018). Deep Cube-Pair Network for Hyperspectral Imagery Classification. Remote Sens., 10.","DOI":"10.3390\/rs10050783"},{"key":"ref_33","first-page":"1","article-title":"Tensor-Based Classification Models for Hyperspectral Data Analysis","volume":"99","author":"Makantasis","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Afshar, P., Mohammadi, A., and Plataniotis, K.N. (arXiv, 2018). Brain Tumor Type Classification via Capsule Networks, arXiv.","DOI":"10.1109\/ICIP.2018.8451379"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Jaiswal, A., AbdAlmageed, W., and Natarajan, P. (arXiv, 2018). CapsuleGAN: Generative Adversarial Capsule Network, arXiv.","DOI":"10.1007\/978-3-030-11015-4_38"},{"key":"ref_36","unstructured":"Kumar, A.D. (arXiv, 2018). Novel Deep Learning Model for Traffic Sign Detection Using Capsule Networks, arXiv."},{"key":"ref_37","unstructured":"LaLonde, R., and Bagci, U. (arXiv, 2018). Capsules for Object Segmentation, arXiv."},{"key":"ref_38","unstructured":"Li, Y., Qian, M., Liu, P., Cai, Q., Li, X., Guo, J., Yan, H., Yu, F., Yuan, K., and Yu, J. (2018). The recognition of rice images by UAV based on capsule network. Clust. Comput., 1\u201310."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Qiao, K., Zhang, C., Wang, L., Yan, B., Chen, J., Zeng, L., and Tong, L. (arXiv, 2018). Accurate reconstruction of image stimuli from human fMRI based on the decoding model with capsule network architecture, arXiv.","DOI":"10.3389\/fninf.2018.00062"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, A., Han, J., Liu, Y., and Zhu, X. (2018, January 23\u201327). Sentiment Analysis by Capsules. Proceedings of the 2018 World Wide Web Conference on World Wide Web, Lyon, France.","DOI":"10.1145\/3178876.3186015"},{"key":"ref_41","unstructured":"Zhao, W., Ye, J., Yang, M., Lei, Z., Zhang, S., and Zhao, Z. (arXiv, 2018). Investigating Capsule Networks with Dynamic Routing for Text Classification, arXiv."},{"key":"ref_42","unstructured":"Andersen, P. (arXiv, 2018). Deep Reinforcement Learning using Capsules in Advanced Game Environments, arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1109\/TGRS.2017.2755542","article-title":"Spectral-Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework","volume":"56","author":"Zhong","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Guidici, D., and Clark, M.L. (2017). One-Dimensional convolutional neural network land-cover classification of multi-seasonal hyperspectral imagery in the San Francisco Bay Area, California. Remote Sens., 9.","DOI":"10.3390\/rs9060629"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"14680","DOI":"10.3390\/rs71114680","article-title":"Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery","volume":"7","author":"Hu","year":"2015","journal-title":"Remote Sens."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1109\/LGRS.2017.2681128","article-title":"Deep learning classification of land cover and crop types using remote sensing data","volume":"14","author":"Kussul","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Gao, Q., Lim, S., and Jia, X. (2018). Hyperspectral Image Classification Using Convolutional Neural Networks and Multiple Feature Learning. Remote Sens., 10.","DOI":"10.3390\/rs10020299"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Li, J., Ma, L., Jiang, H., and Zhao, H. (2017, January 23\u201328). Deep Residual Networks for Hyperspectral Image Classification. Proceedings of the Geoscience and Remote Sensing Symposium, Fort Worth, TX, USA.","DOI":"10.1109\/IGARSS.2017.8127330"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1109\/TGRS.2005.846154","article-title":"Kernel-based methods for hyperspectral image classification","volume":"43","author":"Bruzzone","year":"2005","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1109\/LGRS.2010.2068537","article-title":"Change vector analysis in posterior probability space: A new method for land cover change detection","volume":"8","author":"Chen","year":"2011","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.1016\/j.rse.2010.03.003","article-title":"Mapping global urban areas using MODIS 500-m data: New methods and datasets based on \u2018urban ecoregions\u2019","volume":"114","author":"Schneider","year":"2010","journal-title":"Remote Sens. Environ."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1016\/j.rse.2014.08.038","article-title":"A model for the propagation of uncertainty from continuous estimates of tree cover to categorical forest cover and change","volume":"156","author":"Sexton","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1109\/JSTARS.2016.2615073","article-title":"Multiscale integration approach for land cover classification based on minimal entropy of posterior probability","volume":"10","author":"Yang","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_54","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20136). Imagenet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems (NIPS), Lake Tahoe, NV, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/9\/3153\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:21:16Z","timestamp":1760196076000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/9\/3153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,18]]},"references-count":54,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2018,9]]}},"alternative-id":["s18093153"],"URL":"https:\/\/doi.org\/10.3390\/s18093153","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9,18]]}}}