{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:27:08Z","timestamp":1760243228655,"version":"build-2065373602"},"reference-count":42,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2014,12,8]],"date-time":"2014-12-08T00:00:00Z","timestamp":1417996800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Multi-camera networks have gained great interest in video-based surveillance systems for security monitoring, access control, etc. Person re-identification is an essential and challenging task in multi-camera networks, which aims to determine if a given individual has already appeared over the camera network. Individual recognition often uses faces as a trial and requires a large number of samples during the training phrase. This is difficult to fulfill due to the limitation of the camera hardware system and the unconstrained image capturing conditions. Conventional face recognition algorithms often encounter the \u201csmall sample size\u201d (SSS) problem arising from the small number of training samples compared to the high dimensionality of the sample space. To overcome this problem, interest in the combination of multiple base classifiers has sparked research efforts in ensemble methods. However, existing ensemble methods still open two questions: (1) how to define diverse base classifiers from the small data; (2) how to avoid the diversity\/accuracy dilemma occurring during ensemble. To address these problems, this paper proposes a novel generic learning-based ensemble framework, which augments the small data by generating new samples based on a generic distribution and introduces a tailored 0\u20131 knapsack algorithm to alleviate the diversity\/accuracy dilemma. More diverse base classifiers can be generated from the expanded face space, and more appropriate base classifiers are selected for ensemble. Extensive experimental results on four benchmarks demonstrate the higher ability of our system to cope with the SSS problem compared to the state-of-the-art system.<\/jats:p>","DOI":"10.3390\/s141223509","type":"journal-article","created":{"date-parts":[[2014,12,8]],"date-time":"2014-12-08T11:15:56Z","timestamp":1418037356000},"page":"23509-23538","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Generic Learning-Based Ensemble Framework for Small Sample Size Face Recognition in Multi-Camera Networks"],"prefix":"10.3390","volume":"14","author":[{"given":"Cuicui","family":"Zhang","sequence":"first","affiliation":[{"name":"Graduate School of Informatices, Kyoto University, Kyoto 606-8501, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefeng","family":"Liang","sequence":"additional","affiliation":[{"name":"Graduate School of Informatices, Kyoto University, Kyoto 606-8501, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Matsuyama","sequence":"additional","affiliation":[{"name":"Graduate School of Informatices, Kyoto University, Kyoto 606-8501, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2014,12,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"8750","DOI":"10.3390\/s130708750","article-title":"Multi-View Human Activity Recognition in Distributed Camera Sensor Networks","volume":"13","author":"Ehsan","year":"2013","journal-title":"Sensors"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TNN.2007.901277","article-title":"MPCA: Multilinear Principal Component Analysis of Tensor Objects","volume":"19","author":"Lu","year":"2008","journal-title":"IEEE Trans. Neur. Netw."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1109\/TIFS.2009.2035976","article-title":"A Doubly Weighted Approach for Appearance-based Subspace Learning Methods","volume":"5","author":"Lu","year":"2010","journal-title":"IEEE Trans. Inform. Forensics Secur."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yang, M.H. (2002, January 20\u201321). Kernel Eigenfaces versus Kernel Fisherfaces: Face Recognition using Kernel Methods. Washington, WA, USA.","DOI":"10.1109\/AFGR.2002.4527207"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/s11263-006-8098-z","article-title":"Random Sampling for Subspace Face Recognition","volume":"70","author":"Wang","year":"2006","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1007\/s00521-009-0291-x","article-title":"Two-dimensional Canonical Correlation Analysis and its Application in Small Sample Size Face Recognition","volume":"19","author":"Sun","year":"2010","journal-title":"Neur. Comput. Appl."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Corcoran, P. (2011). Refinements and New Ideas in Face Recognition, InTech. ISBN: 978-953-307-368-2.","DOI":"10.5772\/743"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1007\/s11263-011-0426-2","article-title":"Fast and Accurate 3D Face Recognition using Registration to an Intrinsic Coordinate System and Fusion of Multiple Region Classifiers","volume":"93","author":"Spreeuwers","year":"2011","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhu, P., Zhang, L., Hu, Q., and Shiu, S. (2012, January 7\u201313). Multi-scale Patch based Collaborative Representation for Face Recognition with Margin Distribution Optimization. Florence, Italy.","DOI":"10.1007\/978-3-642-33718-5_59"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2497","DOI":"10.1016\/j.patcog.2013.01.037","article-title":"Adaptive Discriminant Learning for Face Recognition","volume":"46","author":"Kan","year":"2013","journal-title":"Patt. Recogn."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/TPAMI.2012.70","article-title":"Discriminative Multimanifold Analysis for Face Recognition from a Single Training Sample Per Person","volume":"35","author":"Lu","year":"2013","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell. (TPAMI)"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Lu, J., Tan, Y., and Wang, G. (2011, January 6\u201313). Discriminative Multi-Manifold Analysis for Face Recognition from a Single Training Sample Per Person. Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126464"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1109\/TIFS.2011.2156787","article-title":"A Discriminative Model for Age Invariant Face Recognition","volume":"6","author":"Li","year":"2011","journal-title":"IEEE Trans. Inform. Forensics Secur."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"954","DOI":"10.1109\/TIFS.2012.2189205","article-title":"Dictionary-based Face Recognition under Variable Lighting and Pose","volume":"7","author":"Patel","year":"2012","journal-title":"IEEE Trans. Inform. Forensics Secur."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1109\/TIFS.2012.2226580","article-title":"Component-based Representation in Automated Face Recognition","volume":"8","author":"Bonnen","year":"2013","journal-title":"IEEE Trans. Inform. Forensics Secur."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Topcu, B., and Erdogan, H. (2010, January 23\u201326). Decision Fusion for Patch-Based Face Recognition. Istanbul, Turkey.","DOI":"10.1109\/ICPR.2010.333"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/s10994-006-9449-2","article-title":"An Analysis of Diversity Measures","volume":"65","author":"Tang","year":"2006","journal-title":"Mach. Learn."},{"key":"ref_18","unstructured":"Zhang, C., Liang, X., and Matsuyama, T. (2012, January 11\u201315). Multi-subregion Face Recognition using Coarse-to-fine Quad-Tree Decomposition. Tsukuba, Japan."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/s100440200011","article-title":"Bagging, Boosting and the Random Subspace Method for Linear Classifiers","volume":"5","author":"Skurichina","year":"2002","journal-title":"Patt. Anal. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1109\/34.908974","article-title":"PCA versus LDA","volume":"23","author":"Martinez","year":"2001","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell. (TPAMI)"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1885","DOI":"10.1109\/TIP.2009.2021737","article-title":"Hierarchical Ensemble of Global and Local Classifiers for Face Recognition","volume":"18","author":"Su","year":"2009","journal-title":"IEEE Trans. Image Process."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/TPAMI.2004.1261097","article-title":"Two-dimensional PCA: A New Approach to Appearance-based Face Representation and Recognition","volume":"26","author":"Yang","year":"2004","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell. (TPAMI)"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1016\/S0167-8655(02)00134-4","article-title":"Face Recognition with One Training Image Per Person","volume":"23","author":"Wu","year":"2002","journal-title":"Patt. Recogn. Lett."},{"key":"ref_24","first-page":"1354","article-title":"Studies on Hyperspectral Face Recognition in Visible Spectrum with Feature Band Selection","volume":"40","author":"Di","year":"2010","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell. (TPAMI)"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1016\/j.amc.2004.04.016","article-title":"A New Face Recognition Method based on SVD Perturbation for Single Example Image Per Person","volume":"163","author":"Zhang","year":"2005","journal-title":"Appl. Math. Comput."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Su, Y., Shan, S., Chen, X., and Gao, W. (2010, January 13\u201318). Adaptive Ggeneric Learning for Face Recognition from a Single Sample Per Person. San Francisco, CA, USA,.","DOI":"10.1109\/CVPR.2010.5539990"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1016\/j.patrec.2003.11.005","article-title":"An Improved Face Recognition Technique based on Modular PCA Approach","volume":"25","author":"Gottumukkal","year":"2004","journal-title":"Patt. Recogn. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1016\/j.patcog.2003.12.010","article-title":"Making FLDA Applicable to Face Recognition with One Sample Per Person","volume":"37","author":"Chen","year":"2004","journal-title":"Patt. Recogn."},{"key":"ref_29","unstructured":"Zhu, P., Zhang, L., Hu, Q., and Shiu, S. (2003, January 8\u201313). Locality Preserving Projections. British Columbia, Canada."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/TIFS.2010.2096810","article-title":"Periocular Biometrics in the Visible Spectrum","volume":"6","author":"Park","year":"2011","journal-title":"IEEE Trans. Inform. Forensics Secur."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/3-540-32390-2_6","article-title":"Margin-based Diversity Measures for Ensemble Classifiers","volume":"30","author":"Arodz","year":"2005","journal-title":"Adv. Soft Comput. Vol."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Cai, D., He, X., Hu, Y., Han, J., and Huang, T. (2007, January 17\u201322). Learning a Spatially Smooth Subspace for Face Recognition. Minnesota, MN, USA.","DOI":"10.1109\/CVPR.2007.383054"},{"key":"ref_33","unstructured":"Samaria, F.S., and Harter, A.C. (1994, January 5\u20137). Parameterisation of a Stochastic Model for Human Face Identification. Sarasota, FL, USA."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1109\/34.927464","article-title":"From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose","volume":"23","author":"Georghiades","year":"2001","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell. (TPAMI)"},{"key":"ref_35","unstructured":"Martinez, A.M., and Benavente, R. (1998). CVC Technical Report, The Ohio State University."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.1109\/34.879790","article-title":"The FERET Evaluation Methodology for Face Recognition Algorithms","volume":"22","author":"Phillips","year":"2000","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell. (TPAMI)"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Bolme, D.S., Beveridge, J.R., Teixeira, M., and Draper, B.A. (2003, January 1\u20133). The CSU Face Identification Evaluation System: Its Purpose, Features, and Structure. Graz, Austria.","DOI":"10.1007\/3-540-36592-3_29"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1016\/j.patrec.2004.03.012","article-title":"Enhanced (PC)2A for Face Recognition with One Training Image Per Person","volume":"25","author":"Chen","year":"2004","journal-title":"Patt. Recogn. Lett."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1109\/TNN.2005.849817","article-title":"Recognizing Partially Occluded, Expression Variant Faces from Single Training Image Per Person with SOM and Soft k-NN Ensemble","volume":"16","author":"Tan","year":"2005","journal-title":"IEEE Trans. Neur. Netw."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1109\/TPAMI.2005.55","article-title":"Face Recognition using Laplacianfaces","volume":"27","author":"He","year":"2005","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell. (TPAMI)"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1016\/j.patcog.2009.12.004","article-title":"Robust, Accurate and Efficient Face Recognition from a Single Training Image: A Uniform Pursuit Approach","volume":"43","author":"Deng","year":"2010","journal-title":"Patt. Recogn."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1016\/j.imavis.2008.12.009","article-title":"Semi-random Subspace Method for Face Recognition","volume":"27","author":"Zhu","year":"2009","journal-title":"J. Image Vision Comput."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/14\/12\/23509\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:10:36Z","timestamp":1760217036000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/14\/12\/23509"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12,8]]},"references-count":42,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2014,12]]}},"alternative-id":["s141223509"],"URL":"https:\/\/doi.org\/10.3390\/s141223509","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2014,12,8]]}}}