[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-663522-105":3,"detail-sidebar-cat-0-en-105":80,"doc-detail-663522-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":73,"head_meta":75,"extra_data":77,"updated_unix":79},105,"en","deep-feature-extraction-and-classification-of-hyperspectral-images-based-on-convolutional-neural-networks","Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks","","A regularized deep feature extraction method is presented for hyperspectral image (HSI) classification using convolutional neural networks (CNN). Multiple convolutional and pooling layers learn nonlinear, discriminant, and invariant deep features for classification and target detection. To address imbalance from high dimensionality and limited training samples, L2 regularization and dropout are investigated to mitigate overfitting. A 3-D CNN-based feature extraction model with combined regularization is proposed, and a virtual sample enhanced strategy further improves performance. Experiments on Indian Pines, University of Pavia, and Kennedy Space Center demonstrate competitive results with sparse constraints.",{"@graph":14,"@context":72},[15,34,55],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/deep-feature-extraction-and-classification-of-hyperspectral-images-based-on-convolutional-neural-networks/663522/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/deep-feature-extraction-and-classification-of-hyperspectral-images-based-on-convolutional-neural-networks/663522.png","ImageObject",300,407,{"name":42,"@type":43},"Taylor Morgan","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-10-28",true,{"@type":52,"interactionType":53,"userInteractionCount":22},"InteractionCounter",{"@type":54},"ViewAction",{"@type":56,"mainEntity":57},"FAQPage",[58,64,68],{"name":59,"@type":60,"acceptedAnswer":61},"What is the main goal of the proposed method?","Question",{"text":62,"@type":63},"The method aims to perform hyperspectral image classification by learning effective deep features using a regularized CNN-based feature extraction approach.","Answer",{"name":65,"@type":60,"acceptedAnswer":66},"How does the paper address overfitting caused by limited training samples?",{"text":67,"@type":63},"It investigates regularization strategies such as L2 regularization and dropout to reduce overfitting in class modeling.",{"name":69,"@type":60,"acceptedAnswer":70},"Which datasets are used to evaluate the proposed models?",{"text":71,"@type":63},"The approach is tested on Indian Pines, University of Pavia, and Kennedy Space Center.","https://schema.org",{"og:url":32,"og:type":74,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":76,"canonical":32},"index,follow",{"doc_id":78,"site_id":7},663522,1793228921,{"code":4,"msg":81,"data":82},"success",[83,87,91,95,100,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":84,"show_sort_weight":85,"slug":86},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":88,"show_sort_weight":89,"slug":90},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":92,"show_sort_weight":93,"slug":94},"Exam",70,"exam",{"id":96,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},5,"Comic",60,"comic",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},6,"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":96,"slug":129},19,"General","general",{"code":4,"msg":81,"data":131},{"doc_id":78,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":22,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":117,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":79,"read_time":103},1099523885336,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks  \nYushi Chen, Member, IEEE, Hanlu Jiang, Chunyang Li, Xiuping Jia, Senior Member, IEEE, and  \nPedram Ghamisi, Member, IEEE  \nAbstract—Due to the advantages of deep learning, in this paper, a regularized deep feature extraction (FE) method is presented for hyperspectral image (HSI) classification using a convolutional neural network (CNN). The proposed approach employs several convolutional and pooling layers to extract deep features from HSIs, which are nonlinear, discriminant, and invariant. These features are useful for image classification and target detection. Furthermore, in order to address the common issue of imbalance between high dimensionality and limited availability of training samples for the classification of HSI, a few strategies such as L2 regularization and dropout are investigated to avoid overfittingin class data modeling. More importantly, we propose a 3-D CNN-based FE model with combined regularization to extract effective spectral–spatial features of hyperspectral imagery. Finally, in order to further improve the performance, a virtual sample enhanced method is proposed. The proposed approaches are carried out on three widely used hyperspectral data sets: Indian Pines, University of Pavia, and Kennedy Space Center. The obtained results reveal that the proposed models with sparse constraints provide competitive results to state-of-the-art methods. In addition, the proposed deep FE opens a new window for further research.  \nIndex Terms—Convolutional neural network (CNN), deep learning, feature extraction (FE), hyperspectral image (HSI) classification.  \nI. INTRODUCTION  \nHYPERSPECTRAL images (HSIs) are usually composed  \nof several hundreds of spectral data channels of the same scene. The detailed spectral information provided by hyperspectral sensors increases the power of accurately  \nY. Chen, H. Jiang, and C. Li are with the Department of Information Engineering, School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China (e-mail: [chenyushi@hit.edu.cn](chenyushi@hit.edu.cn); halo91@ [163.com](163.com); [lcy_buzz@mail.dlut.edu.cn](lcy_buzz@mail.dlut.edu.cn)).  \nX. Jia is with the School of Engineering and Information Technology, The University of New South Wales, Canberra, A.C.T. 2600, Australia (e-mail: [x.jia@adfa.edu.au](x.jia@adfa.edu.au)).  \nP. Ghamisi is with Signal Processing in Earth Observation, Technische Universität München, 80333 Munich, Germany, and also with the Remote Sensing Technology Institute (IMF), German Aerospace Center (DLR), 82234 Weßling, Germany (e-mail: [p.ghamisi@gmail.com](p.ghamisi@gmail.com)).  \ndifferentiating materials of interest with increased classification accuracy. Moreover, with respect to advances in hyperspectral technology, the fine spatial resolution of recently operated sensors makes the analysis of small spatial structures in images possible [1] . The aforementioned advances make the hyperspectral data a useful tool for a wide variety of applications. By increasing the dimensionality of the images in the spectral domain, theoretical and practical problems may arise. In this manner, conventional techniques which are developed for multispectral data are no longer efficient for the processing of high-dimensional data mostly due to the so-called curse of dimensionality [2] . In order to address the curse of dimensionality, feature extraction (FE) is considered as a crucial step in HSI processing [3] . However, due to the spatial variability of spectral signatures, HSI FE is still a challenging task [4] .  \nIn the early stage of the study on HSI FE, the focus was on spectral-based methods, including principal component analysis (PCA)[5], independent component analysis (ICA)[6], linear discriminant analysis [7], etc. [8], [9] . These methods apply linear transformations to extract potentially better features of the input data i","cbCaiiCsFWgshqlU","https://ap.wps.com/l/cbCaiiCsFWgshqlU","pdf",6762666,"English","# Abstract\n# I. INTRODUCTION","[{\"question\":\"What is the main goal of the proposed method?\",\"answer\":\"The method aims to perform hyperspectral image classification by learning effective deep features using a regularized CNN-based feature extraction approach.\"},{\"question\":\"How does the paper address overfitting caused by limited training samples?\",\"answer\":\"It investigates regularization strategies such as L2 regularization and dropout to reduce overfitting in class modeling.\"},{\"question\":\"Which datasets are used to evaluate the proposed models?\",\"answer\":\"The approach is tested on Indian Pines, University of Pavia, and Kennedy Space Center.\"}]","Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks | PDF"]