Filters








1,813 Hits in 4.0 sec

2D–3D face matching using CCA

Weilong Yang, Dong Yi, Zhen Lei, Jitao Sang, Stan Z. Li
2008 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition  
In this paper we propose a learning based 2D-3D face matching method using the CCA to learn the mapping between 2D face image and 3D face data.  ...  This method makes it possible to match the on-site 2D face image with enrolled 3D face data.  ...  face matching In this section, we will introduce the proposed CCA based 2D-3D face matching method, in which the CCA is used to learn the mapping between 2D face image and 3D face data.  ... 
doi:10.1109/afgr.2008.4813407 dblp:conf/fgr/YangYLSL08 fatcat:bgtun6r2wrel3jvwwdhhci7v5a

2D-3D Face Recognition Method Basedon a Modified CCA-PCA Algorithm

Patrik Kamencay, Robert Hudec, Miroslav Benco, Martina Zachariasova
2014 International Journal of Advanced Robotic Systems  
In this paper, we propose a 2D-3D face-matching method based on a principal component analysis (PCA) algorithm using canonical correlation analysis (CCA) to learn the mapping between a 2D face image and  ...  Testing the 2D-3D face match results gave a recognition rate for the CCA method of a quite poor 55% while the modified CCA method based on PCA-level fusion achieved a very good recognition score of 85%  ...  As can be seen in Table 1 and Figure 12 , the best 2D-3D face match results were obtained using the proposed CCADouble and CCA-PCA fusion algorithms.  ... 
doi:10.5772/58251 fatcat:xtug5reajvcwngyq6xaz5jlkd4

Asymmetric 3D/2D face recognition based on LBP facial representation and canonical correlation analysis

Di Huang, Mohsen Ardabilian, Yunhong Wang, Liming Chen
2009 2009 16th IEEE International Conference on Image Processing (ICIP)  
A weighted Chi square distance is computed as matching score between 2D LBP facial representations; Canonical Correlation Analysis (CCA) is applied to learn the mapping between the LBP-based range face  ...  In our approach, Local Binary Patterns (LBP) is used as an efficient facial representation for both 2D texture and 3D range images.  ...  i 3D/2D Face Matching Also as follows our discussion in section 2, LBP is used to preprocess 3D range images and 2D face texture images.  ... 
doi:10.1109/icip.2009.5413901 dblp:conf/icip/HuangAWC09 fatcat:zc5r55w3hzhj3gywidnzamgfem

An Efficient P-KCCA Algorithm for 2D-3D Face Recognition Using SVM

Patrik Kamencay, Robert Hudec, Miroslav Benco, Peter Sykora, Roman Radil
2015 Advances in Electrical and Electronic Engineering  
This method makes it possible to match the 2D face image with enrolled 3D face data. The resulting features are then classified using the SVM method.  ...  The experimental results show that the combination of P-KCCA method using SVM achieves a higher performance compared to the alone PCA, CCA and KCCA algorithms.  ...  There are several methods to tackle the 2D-3D face matching problem. Rama et al. [7] use Partial Principal Component Analysis (P2CA) to match 2D face image (probe) with 3D face data (gallery).  ... 
doi:10.15598/aeee.v13i4.1473 fatcat:ewn2v4pd4za25cqechjqgdhfse

Oriented Gradient Maps based automatic asymmetric 3D-2D face recognition

Di Huang, Mohsen Ardabilian, Yunhong Wang, Liming Chen
2012 2012 5th IAPR International Conference on Biometrics (ICB)  
Due to its property of being highly distinctive, these OGMs improve accuracies of both matching steps of asymmetric face recognition, i.e. (1) 3D-2D matching using Canonical Correlation Analysis (CCA);  ...  (2) 2D-2D matching using LBP histogram based features and Sparse Representation Classifier (SRC).  ...  Specifically, in 3D-2D matching, these OGMs of 2D and 3D facial images are used to replace 2D and 3D LBP faces as the input of CCA, while in 2D-2D matching, instead of extracting LBP histograms directly  ... 
doi:10.1109/icb.2012.6199769 dblp:conf/icb/HuangAWC12 fatcat:myrhd3gvsnh63hajvckfqk3ukm

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.  ...  Moreover, we offer a detailed account of datasets and benchmarks commonly used for evaluation. We finish by assessing the state of the field and discussing promising directions for future research.  ...  [44] proposed a 2D-3D face recognition approach with two separate stages: First, for 2D-2D matching, Sparse Representation Classifier (SRC) is used; Second, CCA is exploited to learn the projections  ... 
doi:10.1016/j.imavis.2016.09.001 fatcat:hy666szkk5bgfoazyxgwy6hli4

Cross-pose Face Recognition by Canonical Correlation Analysis [article]

Annan Li, Shiguang Shan, Xilin Chen, Bingpeng Ma, Shuicheng Yan, Wen Gao
2015 arXiv   pre-print
In our method, based on the data set with coupled face images of the same identities and across two different poses, CCA learns simultaneously two linear transforms, each for one pose.  ...  The pose problem is one of the bottlenecks in automatic face recognition.  ...  [49] used CCA to reconstruct 3D facial shape. Yang et al. [50] applied CCA to 2D-3D face matching.  ... 
arXiv:1507.08076v1 fatcat:airjyjndxvgtvlrol7i4hg2kwa

Cross-Modality 2D-3D Face Recognition via Multiview Smooth Discriminant Analysis Based on ELM

Yi Jin, Jiuwen Cao, Qiuqi Ruan, Xueqiao Wang
2014 Journal of Electrical and Computer Engineering  
Adding the Laplacian penalty constrain for the multiview feature learning, the proposed MSDA is first proposed to extract the cross-modality 2D-3D face features.  ...  In this paper, we propose a new approach for cross-modality 2D-3D face recognition (FR), which is called Multiview Smooth Discriminant Analysis (MSDA) based on Extreme Learning Machines (ELM).  ...  [20] proposed a 3D range image and 2D-3D face images matching method by using the facial curves and CCA.  ... 
doi:10.1155/2014/584241 fatcat:gqjvpddltnda7ngryopqfyuwti

A Survey on Heterogeneous Face Recognition: Sketch, Infra-red, 3D and Low-resolution [article]

Shuxin Ouyang, Timothy Hospedales, Yi-Zhe Song, Xueming Li
2014 arXiv   pre-print
Heterogeneous face recognition (HFR) refers to matching face imagery across different domains.  ...  Moreover, we offer a detailed account of datasets and benchmarks commonly used for evaluation. We finish by assessing the state of the field and discussing promising directions for future research.  ...  [Yang et al. 2008 ] used CCA to correspond the 2D and 3D face modalities and deal with their heterogeneous dimensionality.  ... 
arXiv:1409.5114v2 fatcat:pytctlmtonf6bhb4z3pszxoove

KCCA-based technique for profile face identification

Malek Nadil, Feryel Souami, Abdenour Labed, Hichem Sahbi
2016 EURASIP Journal on Image and Video Processing  
Recently, pose invariant techniques that exploit either 3D scans or 2D images of the same face to generate the corresponding 3D model have emerged.  ...  In this paper, we propose a profile face identification method based on correspondence mapping of 2D frontal face images.  ...  Finally, stereo vision [30] techniques where 3D face models are reconstructs from 2D face images in different poses can also be applied. 2D model versus 3D technique It is worth recalling that 3D-based  ... 
doi:10.1186/s13640-016-0123-8 fatcat:am3ifixpdrcdbdwhoi6ylf3ptm

3D and Infrared Face Reconstruction from RGB data using Canonical Correlation Analysis

M. Reiter, R. Donner, G. Langs, H. Bischof
2006 18th International Conference on Pattern Recognition (ICPR'06)  
We first use CCA to perform 3D face reconstruction and in a separate application we predict near-infrared (NIR) face texture. In both cases, the input data are color (RGB) face images.  ...  In this paper, we apply a multiple regression method based on Canonical Correlation Analysis (CCA) to face data modelling.  ...  using a 3D-depth map of the face.  ... 
doi:10.1109/icpr.2006.24 dblp:conf/icpr/ReiterDLB06 fatcat:wyfmndxa2fbglpxqu3fwztshry

Ultrasound Common Carotid Artery Segmentation Based on Active Shape Model

Xin Yang, Jiaoying Jin, Mengling Xu, Huihui Wu, Wanji He, Ming Yuchi, Mingyue Ding
2013 Computational and Mathematical Methods in Medicine  
It took 4.3 ± 0.5 mins to segment single 3D US images, while it took 11.7 ± 1.2 mins for manual segmentation.  ...  The proposed method is used to segment both media-adventitia-boundary (MAB) and lumen-intima-boundary (LIB) on transverse views slices from three-dimensional ultrasound (3D US) images.  ...  artery (CCA) from 3D US images.  ... 
doi:10.1155/2013/345968 pmid:23533535 pmcid:PMC3606761 fatcat:ejdyh6phzfalnk3aj6mzspvmwq

A linear estimation method for 3D pose and facial animation tracking

Jose Alonso Ybanez Zepeda, Franck Davoine, Maurice Charbit
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
The CCA is used to find the dependency between texture residuals and 3D face pose and facial gesture.  ...  The texture residuals are obtained from observed raw brightness shape-free 2D image patches that we build by means of a parameterized 3D geometric face model.  ...  Model-based approaches use a 2D or 3D object model that is projected onto the image and matched to the object to be tracked [9, 7] .  ... 
doi:10.1109/cvpr.2007.383406 dblp:conf/cvpr/ZepedaDC07 fatcat:r5c7szbfprgkhoqvgk2npr5aw4

View-Invariant Template Matching Using Homography Constraints [article]

Sina Lotfian, Hassan Foroosh
2017 arXiv   pre-print
Based on this property, we formulate the problem as an error function that indicates how likely two sets of 2D points are projections of the same set of 3D points under two different cameras.  ...  In this paper, we propose a method that can match objects in images taken under different viewpoints.  ...  For more clarity, we use upper case letters for 3D coordinates and lower case for 2D coordinates on the image plane.  ... 
arXiv:1705.04433v1 fatcat:izn2ttairndo7fqdve35zdfub4

A Comprehensive Survey on Pose-Invariant Face Recognition [article]

Changxing Ding, Dacheng Tao
2016 arXiv   pre-print
Compared to frontal face recognition, which has been intensively studied and has gradually matured in the past few decades, pose-invariant face recognition (PIFR) remains a largely unsolved problem.  ...  However, PIFR is crucial to realizing the full potential of face recognition for real-world applications, since face recognition is intrinsically a passive biometric technology for recognizing uncooperative  ...  Similar to , the 2D face image is aligned to the deformable 3D face model using the weak perspective projection model, after which the dense landmarks on the 3D model are projected to the 2D image.  ... 
arXiv:1502.04383v3 fatcat:opz5onz775cj5hxvoaggvmp52q
« Previous Showing results 1 — 15 out of 1,813 results