20,079 Hits in 5.9 sec

Manifold–Manifold Distance and its Application to Face Recognition With Image Sets

Ruiping Wang, Shiguang Shan, Xilin Chen, Qionghai Dai, Wen Gao
2012 IEEE Transactions on Image Processing  
Index Terms-Face recognition with image sets, hierarchical divisive clustering, manifold-manifold distance (MMD), principal angles, set similarity measure.  ...  The proposed method is applied to the task of face recognition with image sets, where identification is achieved by seeking the minimum MMD from the probe to the gallery of image sets.  ...  ACKNOWLEDGMENT The authors would like to thank Dr. T-K. Kim and Dr. L. Wolf for sharing the codes of DCC/CMSM/MSM and KPA, respectively.  ... 
doi:10.1109/tip.2012.2206039 pmid:22752133 fatcat:g4ipe3ydznbgra6dzqaate6raq

Fuzzy-Appearance Manifold and Fuzzy-Nearest Distance Calculation for Model-Less 3D Pose Estimation of Degraded Face Images

Benyamin Kusumoputro, Lina
2013 International Journal of Advanced Robotic Systems  
The pose estimation of an unknown face image is performed by firstly being projected onto the eigenspace domain then transformed to become an unknown fuzzy-point, and its fuzzydistance with all of the  ...  This paper presents the development of fuzzyappearance manifold and fuzzy-nearest distance calculation in the eigenspace domain for pose estimation of degraded face images.  ...  The first author would like to extend his gratitude to University of Indonesia Research Programme for funding the equipment and for providing other funds used during the research activities.  ... 
doi:10.5772/52938 fatcat:2qq4z3t3jzfdbcl3akngkjkjae

Face Recognition From a Single Sample Using Rlog Filter and Manifold Analysis

Jaya Susan Edith.S, A.Usha Ruby
2014 Advanced Computing An International Journal  
Recognition is done by the process of manifold to manifold matching. Hence there is an increment in the accuracy rate of face recognition.  ...  To overcome this drawback which sets back the system from the accurate functioning of face recognition this paper puts forward a novel technique which makes use of discriminative multi-manifold analysis  ...  And its various applications include security, surveillances, general identity verification, criminal justice systems, and other similar application.  ... 
doi:10.5121/acij.2014.5304 fatcat:x6tioabb4jaynkwp7igusp4abq

Advances in matrix manifolds for computer vision

Yui Man Lui
2012 Image and Vision Computing  
There are a wide range of important applications including face recognition, action recognition, clustering, visual tracking, and motion grouping and segmentation.  ...  The increased popularity of matrix manifolds is due partly to the need to characterize image features in non-Euclidean spaces.  ...  Ross Beveridge and Mr. Stephen O'Hara from Colorado State University for reading the manuscript.  ... 
doi:10.1016/j.imavis.2011.08.002 fatcat:wdzjikdbpfgobgopkvc4rmqkqy

A Benchmark and Comparative Study of Video-Based Face Recognition on COX Face Database

Zhiwu Huang, Shiguang Shan, Ruiping Wang, Haihong Zhang, Shihong Lao, Alifu Kuerban, Xilin Chen
2015 IEEE Transactions on Image Processing  
Third, we further propose a novel Point-to-Set Correlation Learning (PSCL) method, and experimentally show that it can be used as a promising baseline method for V2S/S2V face recognition on COX Face DB  ...  Face recognition with still face images has been widely studied, while the research on video-based face recognition is inadequate relatively, especially in terms of benchmark datasets and comparisons.  ...  ACKNOWLEDGMENT The authors would like to thank Prof. TurgLm IBRAHIM, Dr. Luhong Liang and Mr. Yan Li for giving us great helps in collecting and processing COX face database.  ... 
doi:10.1109/tip.2015.2493448 pmid:26513790 fatcat:73fbij3kc5aozamebnwpm5dssm

Regularized Clustering Based Double Manifold Discriminant Analysis for Low-Resolution Face Recognition

Yuqing Zhang, Xianwei Rong, Xiaoyan Yu
2021 ICIC Express Letters  
In this paper, we propose a regularized clustering-based double manifold discriminant analysis (RC-DMDA) method for low-resolution face recognition with single sample per person (SSPP).  ...  To evaluate the performance of the proposed method, high-resolution face images from benchmark datasets are down-sampled to low-resolution ones on account of the lack of test samples, and moreover only  ...  This work was supported by the National Natural Science Foundation of China under Grant 61401127 and Natural Science Foundation of Heilongjiang Province under Grant F2018022.  ... 
doi:10.24507/icicel.15.02.193 fatcat:7o64ndvqzze2bbw5n6tdovw2iq

Manifold Modeling with Learned Distance in Random Projection Space for Face Recognition

Grigorios Tsagkatakis, Andreas Savakis
2010 2010 20th International Conference on Pattern Recognition  
To address this impediment of manifold learning, we investigated the combination of manifold learning and distance metric learning for the generation of a representation that is both discriminative and  ...  We demonstrate that this approach is effective for multi view face recognition.  ...  The proposed scheme can be useful for face recognition and other applications, and may be extended to different combinations of distance metric learning and manifold learning approaches.  ... 
doi:10.1109/icpr.2010.165 dblp:conf/icpr/TsagkatakisS10 fatcat:zlixruu6ijbl7bmd2lzqi2ijzu

Demographic classification from face videos using manifold learning

Abdenour Hadid, Matti Pietikäinen
2013 Neurocomputing  
which encodes and exploits the correlation between the face images through manifold learning.  ...  Research on automatic demographic classification is still in its infancy despite the vast potential applications.  ...  Acknowledgment The financial support provided by the EU FP7 project TABULA RASA (grant agreement #257289), and the Academy of Finland is gratefully acknowledged.  ... 
doi:10.1016/j.neucom.2011.10.040 fatcat:c5jq666wgvb3rpfth5bfzcq53y

Grassmann Registration Manifolds for Face Recognition [chapter]

Yui Man Lui, J. Ross Beveridge
2008 Lecture Notes in Computer Science  
Second, we embed the approximated tangent spaces on a Grassmann manifold and employ a chordal distance as the means for comparing subspaces.  ...  Motivated by image perturbation and the geometry of manifolds, we present a novel method combining these two elements.  ...  Bolme from Colorado State University for calculating the error bounds for the FERET data sets.  ... 
doi:10.1007/978-3-540-88688-4_4 fatcat:f5fgpd277fhubcxdldypzo6u6i

Face Recognition and Retrieval in Video [chapter]

Caifeng Shan
2010 Studies in Computational Intelligence  
Face recognition in unconstrained environments remains challenging for most practical applications.  ...  Video data provides rich and redundant information, which can be exploited to resolve the inherent ambiguities of image-based recognition like sensitivity to low resolution, pose variations and occlusion  ...  Another problem with image-based face recognition is that it is possible to use a prerecorded face photo to confuse the recognition system to take it as a live subject [101] .  ... 
doi:10.1007/978-3-642-12900-1_9 fatcat:53dy35g7hzaaxocwoymcpad5s4

Subspace manifold learning with sample weights

Nathan Mekuz, Christian Bauckhage, John K. Tsotsos
2009 Image and Vision Computing  
Subspace manifold learning represents a popular class of techniques in statistical image analysis and object recognition.  ...  We demonstrate the application of the technique to face recognition, where a model exists to describe each face's probability of occurrence.  ...  Typically, a face recognition system is trained offline with a set of labeled images prior to being presented with a novel image to recognize.  ... 
doi:10.1016/j.imavis.2006.10.007 fatcat:vf2lgklcivaqxn4kelcnfivq4e

Kernel Learning for Extrinsic Classification of Manifold Features

Raviteja Vemulapalli, Jaishanker K. Pillai, Rama Chellappa
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
Experimental results on image set-based classification and activity recognition clearly demonstrate the superiority of the proposed approach over existing methods for classification of manifold features  ...  In computer vision applications, features often lie on Riemannian manifolds with known geometry.  ...  , we evaluate the proposed approach using three applications where manifold features are used: (i) Face recognition using image sets, (ii) Object recognition using image sets and (iii) Human activity recognition  ... 
doi:10.1109/cvpr.2013.233 dblp:conf/cvpr/VemulapalliPC13 fatcat:fwfmnkoeozdtdp3eyyisrivdje

An information-theoretic approach to face recognition from face motion manifolds

Ognjen Arandjelović, Roberto Cipolla
2006 Image and Vision Computing  
In this work we consider face recognition from Face Motion Manifolds (FMMs).  ...  The use of the Resistor-Average Distance (RAD) as a dissimilarity measure between densities confined to FMMs is motivated in the proposed information-theoretic approach to modelling face appearance.  ...  Acknowledgements We would like to thank the Toshiba Corporation for their kind support for our research, the people from the University of Cambridge Engineering Department who  ... 
doi:10.1016/j.imavis.2005.08.002 fatcat:vfqkulf5irharj756wninfezh4

Face recognition based on LDA in manifold subspace

Hung Phuoc Truong, Tue-Minh Dinh Vo, Thai Hoang Le
2016 EAI Endorsed Transactions on Context-aware Systems and Applications  
In practice, data collection is very huge and labeling data requires high-cost, thus the combination of a part of labeled data and unlabeled data for this algorithm in Manifold subspace is a novelty research  ...  Results are obtained from the experiments and compared to several related methods showing the effectiveness of our proposed method.  ...  This research is the extended version of the paper with title "Discriminative semi-supervised learning in manifold subspace for face recognition" in the International Conference on Context-Aware Systems  ... 
doi:10.4108/eai.2-5-2016.151209 fatcat:ifk72qzgrzab7jepjeuosg3sti

Model-Driven Domain Adaptation on Product Manifolds for Unconstrained Face Recognition

Huy Tho Ho, Raghuraman Gopalan
2014 International Journal of Computer Vision  
For cases with only one image per subject in the source domain, the identity of target domain faces is estimated using the geodesic distance on product manifolds.  ...  Furthermore, a probabilistic approach to the problem of classifying image sets on product manifolds is introduced.  ...  On the other hand, Cevikalp and Triggs [10] developed methods called AHISD (Affine Hull based Image Set Distance) and CHISD (Convex Hull based Image Set Distance) that characterized each image set by a  ... 
doi:10.1007/s11263-014-0720-x fatcat:rh52qz6rrnfvvn7lfwk6l7lh7a
« Previous Showing results 1 — 15 out of 20,079 results