Filters








10,232 Hits in 6.5 sec

CoLR: Classification-Oriented Local Representation for Image Recognition

Tan Guo, Lei Zhang, Xiaoheng Tan, Liu Yang, Zhiwei Guo, Fupeng Wei
2019 Complexity  
Then, the performance of the proposed model is evaluated on benchmark face datasets and deep object features.  ...  For this problem, this paper presents a novel representation learning method named classification-oriented local representation (CoLR) for image recognition.  ...  The performance of CoLR can be further enhanced using discriminative deep CNN features. (4) The emphasis of this paper is on learning a discriminative representation for classification on given dictionary  ... 
doi:10.1155/2019/7835797 fatcat:izsjnkksxvcfbmtf4npwnqi3ni

Sparsity Based Locality-Sensitive Discriminative Dictionary Learning for Video Semantic Analysis

Ben-Bright Benuwa, Yongzhao Zhan, Benjamin Ghansah, Ernest K. Ansah, Andriana Sarkodie
2018 Mathematical Problems in Engineering  
Dictionary learning (DL) and sparse representation (SR) based classifiers have greatly impacted the classification performance and have had good recognition rate on image data.  ...  In the proposed algorithm, a discriminant loss function for the category based on sparse coding of the sparse coefficients is introduced into structure of locality-sensitive dictionary learning (LSDL)  ...  the learning of dictionary discriminatively for group sparse representation, and discriminative dictionary learning for face recognition with low ranked regularization was also introduced in [21] .  ... 
doi:10.1155/2018/9312563 fatcat:qnrsbiwnxjdffcj3g5kkcvpxhe

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Fast Sparse Representation with Prototypes Huang, Junzhou Automatic Image Annotation Using Group Sparsity Huang, Kaiqi Visual Tracking via Incremental Self-tuning Particle Filtering on the Affine Group  ...  Using Sparse Linear Combinations Hsiao, Edward Making Specific Features Less Discriminative to Improve Point-based 3D Object Recognition Hsieh, Po-Jang Workshop: Nonparametric Hierarchical Bayesian Model  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

A Weighted Block Dictionary Learning Algorithm for Classification

Zhongrong Shi
2016 Mathematical Problems in Engineering  
Discriminative dictionary learning, playing a critical role in sparse representation based classification, has led to state-of-the-art classification results.  ...  These weight values can be computed conveniently as they are designed to adapt sparse coefficients.  ...  Finally, we trained class dictionary and learned classifier on the final spatial pyramid features using WBDL algorithm.  ... 
doi:10.1155/2016/3824027 fatcat:zcn6ivyx2vd6nm3fjn3dmzbbvm

Finding distinctive facial areas for face recognition

Ce Zhan, Wanqing Li, Philip Ogunbona
2010 2010 11th International Conference on Control Automation Robotics & Vision  
One of the key issues for local appearance based face recognition methods is that how to find the most discriminative facial areas.  ...  Abstract-One of the key issues for local appearance based face recognition methods is that how to find the most discriminative facial areas.  ...  Applications in face recognition In Section I, we have grouped the local appearance based face recognition approaches into two categories: one kind of the approaches extract features only on selected areas  ... 
doi:10.1109/icarcv.2010.5707381 dblp:conf/icarcv/ZhanLO10 fatcat:a7t2ajy3uvctxfuyxt6m5tzrxi

Feature Selection via Sparse Approximation for Face Recognition [article]

Yixiong Liang and Lei Wang and Yao Xiang and Beiji Zou
2011 arXiv   pre-print
In this paper, we propose a trainable feature selection algorithm based on the regularized frame for face recognition.  ...  Moreover, based on the same frame, we propose a sparse Ho-Kashyap (HK) procedure to obtain simultaneously the optimal sparse solution and the corresponding margin vector of the MSE criterion.  ...  One of the key issue to successful face recognition systems is the development of effective face representation, namely how to extract and select the discriminative features to represent face image.  ... 
arXiv:1102.2748v1 fatcat:n6vphecza5cadpq3xtnibiuchy

Integration of multi-feature fusion and dictionary learning for face recognition

Donghui Wang, Xikui Wang, Shu Kong
2013 Image and Vision Computing  
One popular scheme is to extend the sparse representation based classification framework with various sparse constraints.  ...  Yuan and Yan propose a multi-task joint sparse 18 representation based classification method (MTJSRC), which treats the recognition with multiple features as a multi-19 task problem, and each feature type  ...  The first one is to learn a fusion matrix based on Fisher criterion 371 from the training data to fuse the different features to a more discriminative and compact representation, and then 372 use DL framework  ... 
doi:10.1016/j.imavis.2013.10.002 fatcat:povnnew2ivaxnjspfpld77wooi

Latent Dictionary Learning for Sparse Representation Based Classification

Meng Yang, Dengxin Dai, Linlin Shen, Luc Van Gool
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
Experimental results demonstrate that our algorithm outperforms many recently proposed sparse representation and dictionary learning approaches for action, gender and face recognition.  ...  Correspondingly, a latent sparse representation based classifier is also presented.  ...  Based on KSVD [16] , Zhang and Li [10] also proposed a joint learning algorithm called discriminative KSVD (DKSVD) for face recognition, followed by the work proposed by Jiang et al.  ... 
doi:10.1109/cvpr.2014.527 dblp:conf/cvpr/YangDSG14 fatcat:lsonmzozzzcbbde72iyltlrlla

Learning With $\ell ^{1}$-Graph for Image Analysis

Bin Cheng, Jianchao Yang, Shuicheng Yan, Yun Fu, T.S. Huang
2010 IEEE Transactions on Image Processing  
Extensive experiments on three real-world datasets show the consistent superiority of 1 -graph over those classic graphs in data clustering, subspace learning, and semi-supervised learning tasks.  ...  Compared with the conventional -nearest-neighbor graph and -ball graph, the 1 -graph possesses the advantages: 1) greater robustness to data noise, 2) automatic sparsity, and 3) adaptive neighborhood for  ...  [15] employed the Bayesian models and imposed priors for deducing the sparse representation, and Wright et al. [19] proposed to use sparse representation for direct face recognition.  ... 
doi:10.1109/tip.2009.2038764 pmid:20031500 fatcat:lbju2dvonvb2hijji55ueqme6a

Semi-supervised Sparsity Pairwise Constraint Preserving Projections based on GA

Mingming Qi, Yang Xiang
2013 Applied Mathematics & Information Sciences  
On the one hand, the algorithm fuses unsupervised sparse reconstruction feature information and supervised pairwise constraint feature information in the process of dimensionality reduction, preserving  ...  reduction algorithms on sparse representation, the proposed algorithm is more efficient.  ...  Acknowledgments The research is supported by NSF of China(grant No. 71171148) and NSF of Zhejiang province(grant No. LQ12F02007, Y201122544).  ... 
doi:10.12785/amis/070326 fatcat:qhtjfj3hdfajph24afkllbq5bq

A survey of face recognition techniques under occlusion [article]

Dan Zeng, Raymond Veldhuis, Luuk Spreeuwers
2020 arXiv   pre-print
aware face recognition approaches, and 3) occlusion recovery based face recognition approaches.  ...  Second, we present how existing face recognition methods cope with the occlusion problem and classify them into three categories, which are 1) occlusion robust feature extraction approaches, 2) occlusion  ...  We group the approaches into engineered features and learning-based features.  ... 
arXiv:2006.11366v1 fatcat:pttwdep5zbellldwricxfzgzki

Discriminative models for robust image classification [article]

Umamahesh Srinivas
2016 arXiv   pre-print
Specifically, we propose a discriminative tree-based scheme for feature fusion by explicitly learning the conditional correlations among such multiple projections in an iterative manner.  ...  This dissertation explores the development of discriminative models for robust image classification that exploit underlying signal structure, via probabilistic graphical models and sparse signal representations  ...  In face recognition, PCA-based approaches have led to the use of eigenpictures [103] and eigenfaces [104] as features.  ... 
arXiv:1603.02736v1 fatcat:fejsihcelzgy5bh5roavgdj7b4

Subspace structural constraint-based discriminative feature learning via nonnegative low rank representation

Ao Li, Xin Liu, Yanbing Wang, Deyun Chen, Kezheng Lin, Guanglu Sun, Hailong Jiang, Kim Han Thung
2019 PLoS ONE  
In this paper, we propose a robust feature subspace learning approach based on a low-rank representation.  ...  Feature subspace learning plays a significant role in pattern recognition, and many efforts have been made to generate increasingly discriminative learning models.  ...  Acknowledgments The authors are grateful to the editor and anonymous reviewers for their valuable review comments on our work.  ... 
doi:10.1371/journal.pone.0215450 pmid:31063497 pmcid:PMC6504107 fatcat:jkmjgu5j5najnpvh6777je3ukm

A survey on heterogeneous face recognition: Sketch, infra-red, 3D and low-resolution

Shuxin Ouyang, Timothy Hospedales, Yi-Zhe Song, Xueming Li, Chen Change Loy, Xiaogang Wang
2016 Image and Vision Computing  
Heterogeneous face recognition (HFR) refers to matching face imagery across different domains.  ...  This survey provides a comprehensive review of established techniques and recent developments in HFR. Moreover, we offer a detailed account of datasets and benchmarks commonly used for evaluation.  ...  In [46] , a unified sparse coding-based model for coupled dictionary and feature space learning is proposed to simultaneously achieve synthesis and recognition in a common subspace.  ... 
doi:10.1016/j.imavis.2016.09.001 fatcat:hy666szkk5bgfoazyxgwy6hli4

A survey of face recognition techniques under occlusion

Dan Zeng, Raymond Veldhuis, Luuk Spreeuwers
2021 IET Biometrics  
approaches, 2) occlusion aware face recognition approaches, and 3) occlusion recovery based face recognition approaches.  ...  Second the authors analyse how the existing face recognition methods cope with the occlusion problem and classify them into three categories, which are given as: 1) occlusion robust feature extraction  ...  We group the approaches into engineered features and learning-based features.  ... 
doi:10.1049/bme2.12029 fatcat:bkks2gmblfabhgte4snl4x54eu
« Previous Showing results 1 — 15 out of 10,232 results