16,818 Hits in 4.0 sec

Non-orthogonal binary subspace and its applications in computer vision

Hai Tao, R. Crabb, Feng Tang
2005 Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1  
(SSD) matching, appearance subspace projection and subspace-based object recognition.  ...  We investigate the optimized orthogonal matching pursuit method for finding the best NBS base vectors.  ...  For representing objects of symmetric appearance, symmetric two-box base vectors such as the one in Figure 2 (c) are more effective.  ... 
doi:10.1109/iccv.2005.169 dblp:conf/iccv/TaoCT05 fatcat:ntw42mj2lrbmrcc5weaw4iasom

Learning Discriminative Canonical Correlations for Object Recognition with Image Sets [chapter]

Tae-Kyun Kim, Josef Kittler, Roberto Cipolla
2006 Lecture Notes in Computer Science  
We address the problem of comparing sets of images for object recognition, where the sets may represent arbitrary variations in an object's appearance due to changing camera pose and lighting conditions  ...  Motivated by their proven effectiveness, a novel discriminative learning over sets is proposed for object recognition.  ...  They are grateful to Osamu Yamaguchi for motivating this study; to Ognjen Arandjelović for helpful discussions and to Gabriel Brostow for help with proof-reading.  ... 
doi:10.1007/11744078_20 fatcat:r5dvs5bsyrdwbmw2p4te447dlq

Joint Subspace and Low-Rank Coding Method for Makeup Face Recognition

Jianwei Lu, Guohua Zhou, Jiaqun Zhu, Lei Xue, Yi-Zhang Jiang
2021 Mathematical Problems in Engineering  
To adapt to the application of smart cities, in this study, we introduce a novel joint subspace and low-rank coding method for makeup face recognition.  ...  Facial makeup significantly changes the perceived appearance of the face and reduces the accuracy of face recognition.  ...  Joint Subspace and Low-Rank Coding Method for Makeup Face Recognition Objective Function of JSLC.  ... 
doi:10.1155/2021/9914452 fatcat:zas6u6n2mfhqtefdof5ynyb3ge

Face Recognition Using Classification-Based Linear Projections

Moshe Butman, Jacob Goldberger
2008 EURASIP Journal on Advances in Signal Processing  
Subspace methods have been successfully applied to face recognition tasks. In this study we propose a face recognition algorithm based on a linear subspace projection.  ...  The proposed face-recognition technique significantly outperforms traditional subspace-based approaches particulary in very low-dimensional representations.  ...  PCA-based algorithms select a subspace with maximum variation and they are optimal for object reconstruction.  ... 
doi:10.1155/2008/416318 fatcat:avd2ii5ckjacnpfquf6thzlgum

Human Centered Interfaces for Assisted Living [chapter]

Anastasios Tefas, Ioannis Pitas
2011 Advances in Intelligent and Soft Computing  
This paper is primarily focused on the description of the human centered interface specifications, research and implementations for systems geared towards the well-being of aged people.  ...  It has also importance for the provision of improved home care in cases of disabled persons or persons suffering from certain diseases that have high social impact.  ...  Acknowledgements This work has been funded by the Collaborative European Project MOBISERV FP7-248434 (, An Integrated Intelligent Home Environment for the Provision of Health, Nutrition  ... 
doi:10.1007/978-3-642-23169-8_1 dblp:conf/icmmi/TefasP11 fatcat:psnls5sbd5bqhn3wawia7l74x4


Dr. Karunakar Pothuganti
2020 Zenodo  
We contrast our proposed approach and PCA, LDA, and LPP techniques on two standard databases.  ...  Experimental results show that TSA accomplishes a better recognition rate while being considerably more effective.  ...  INTRODUCTION There is presently a lot of interest in appearance-based ways to deal with face recognition when utilizing appearance-based methodologies.  ... 
doi:10.5281/zenodo.4277480 fatcat:pzpjxiuwkrahdnylzx6r7gag3u

Optimal linear representations of images for object recognition

Xiuwen Liu, A. Srivastava, K. Gallivan
2004 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper proposes a stochastic gradient algorithm for finding optimal linear representations of images, for use in appearance-based object recognition.  ...  For solving this optimization problem on a Grassmann manifold, a stochastic gradient algorithm utilizing intrinsic flows is introduced.  ...  Acknowledgments Our thanks to the reviewers for their insightful comments, and to the producers of the ORL and PIE datasets for making them public.  ... 
doi:10.1109/tpami.2004.1273986 pmid:15460288 fatcat:qicdjwntt5hpjaowhdvxsx7lxy

Using Markov Random Field and subspaces to perform object tracking

Lin Ma, Weiming Hu
2011 The First Asian Conference on Pattern Recognition  
For each particle, we optimize each patch's position and use Markov Random Field to represent the structure of the patches, including each patch's own position and the relations between neighbor patches  ...  This paper combines Markov Random Field and subspaces to perform object tracking. We first sample some particles using particle filter, and then divide each particle to patches.  ...  IPCA [5] was a state of the art tracking method based on subspace. Camshift was also a classical method which represented the object by the statistical information of the object color appearance.  ... 
doi:10.1109/acpr.2011.6166655 dblp:conf/acpr/MaH11a fatcat:t3kj2tqvozck7ce2cezkyaefr4

On optimizing subspaces for face recognition

Jilin Tu, Xiaoming Liu, Peter Tu
2009 2009 IEEE 12th International Conference on Computer Vision  
We propose a subspace learning algorithm for face recognition by directly optimizing recognition performance scores.  ...  Our extensive experiments on a number of public databases and a real-world face database demonstrate that our algorithm can improve the performance of given subspace based face recognition algorithms targeted  ...  Deng Cai for sharing his subspace learning matlab code at /homes/dengcai2/Data/data.html.  ... 
doi:10.1109/iccv.2009.5459345 dblp:conf/iccv/TuLT09 fatcat:gufiulzovbhdnnd7tll43djm2u

Single and Multi-Objective Genetic Algorithms for the Selection of Ensemble of Classifiers

E.M. Dos Santos, R. Sabourin, P. Maupin
2006 The 2006 IEEE International Joint Conference on Neural Network Proceedings  
In our experiments, we observed that error rate applied in a single optimization approach was the best objective function to increase performance.  ...  The study presented in this paper, deals with these three aspects in a handwritten digit recognition problem.  ...  Since Random Subspace presents the advantage to deal with huge feature spaces, kNN appears to be a good candidate as learner in a Random Subspace-based ensemble.  ... 
doi:10.1109/ijcnn.2006.247267 dblp:conf/ijcnn/SantosSM06 fatcat:p2i733juevafzjk2wr3u6u3viu

An Active Illumination and Appearance (AIA) Model for Face Alignment

Fatih Kahraman, Muhittin Gokmen, Sune Darkner, Rasmus Larsen
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
Illumination conditions have an explicit effect on the performance of face recognition systems.  ...  The method provides a practical approach, since only one image with frontal illumination of each person for training, is sufficient. There is no need to build complex models for illumination.  ...  Stegmann for his early contributions to our ideas. We would like to thank Cenk D. Mendi for his helpful comments on this manuscript.  ... 
doi:10.1109/cvpr.2007.383399 dblp:conf/cvpr/KahramanGDL07 fatcat:denvmit65jfn7nmbvzwpntao3i

Intrinsic generalization analysis of low dimensional representations

Xiuwen Liu, Anuj Srivastava, DeLiang Wang
2003 Neural Networks  
We use experiments on large datasets to show that the representations that have better intrinsic generalization also lead to better recognition performance. q  ...  We demonstrate the limitations of linear subspace representations by sampling their intrinsic generalization, and propose a nonlinear representation that overcomes these limitations.  ...  The authors would like to thank the producers of the COIL, ORL, and texture datasets for making them publicly available.  ... 
doi:10.1016/s0893-6080(03)00089-3 pmid:12850005 fatcat:htxeyascc5anbl5373lyqhrbby

Intrinsic Illumination Subspace for Lighting Insensitive Face Recognition

Chia-Ping Chen, Chu-Song Chen
2012 IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)  
Based on this class-based generic subspace, we propose a lighting normalization method for lighting insensitive face recognition, where only a single input image is required.  ...  When only objects of the same class, such as faces, are concerned, a class-based generic intrinsic illumination subspace can be constructed in advance and used for novel objects of the same class.  ...  On the other hand, a much higher dimensional subspace is required for appearance images. B.  ... 
doi:10.1109/tsmcb.2011.2167322 pmid:21968744 fatcat:jgxtbva7ejc3rkglhshv2vzmoq

Occluded Image Object Recognition using Localized Nonnegative Matrix Factorization Methods [chapter]

Ivan Bajla, Daniel Soukup, Svorad Stolc
2011 Object Recognition  
Acknowledgements The research has been partially supported by the Slovak Grant Agency for Science VEGA (grant no. 2/0019/10).  ...  Introduction In the nineties, appearance-based methods for image object detection/recognition have evoked a renewed attention in computer vision community thanks to their capability to deal with combined  ...  Metrics For the vector subspace methods of image object recognition a metric should be specified first.  ... 
doi:10.5772/14124 fatcat:l6c3fjqrunca5hu6gwne2nbvvy

Probabilistic visual learning for object representation

B. Moghaddam, A. Pentland
1997 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We present an unsupervised technique for visual learning, which is based on density estimation in high-dimensional spaces using an eigenspace decomposition.  ...  These probability densities are then used to formulate a maximum-likelihood estimation framework for visual search and target detection for automatic object recognition and coding.  ...  We would also like to thank Wasiuddin Wahid for his hard work in helping us participate in the FERET testing.  ... 
doi:10.1109/34.598227 fatcat:is6hvdhogrgixhcpymhs7azb4e
« Previous Showing results 1 — 15 out of 16,818 results