Filters








13,358 Hits in 5.3 sec

3D Face Recognition by Local Shape Difference Boosting [chapter]

Yueming Wang, Xiaoou Tang, Jianzhuang Liu, Gang Pan, Rong Xiao
2008 Lecture Notes in Computer Science  
A new approach, called Collective Shape Difference Classifier (CSDC), is proposed to improve the accuracy and computational efficiency of 3D face recognition.  ...  The CSDC learns the most discriminative local areas from the Pure Shape Difference Map (PSDM) and trains them as weak classifiers for assembling a collective strong classifier using the real-boosting approach  ...  differences of 3D models are effective and the local area is critical.  ... 
doi:10.1007/978-3-540-88682-2_46 fatcat:5krz5gv7rfbtzff37davbwuufi

Robust 3D Face Recognition by Local Shape Difference Boosting

Yueming Wang, Jianzhuang Liu, Xiaoou Tang
2010 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Index Terms-3D shape matching, collective shape difference classifier, face recognition, signed shape difference map.  ...  This paper proposes a new 3D face recognition approach, Collective Shape Difference Classifier (CSDC), to meet practical application requirements, i.e., high recognition performance, high computational  ...  Besides, we focus on face recognition only by 3D face shapes. For some multimodal methods mentioned, only their 3D face engines are discussed.  ... 
doi:10.1109/tpami.2009.200 pmid:20724762 fatcat:szopol27mjhx7flwfckov5kziq

Which 3D geometric facial features give up your identity?

Lahoucine Ballihi, Anuj Srivastava, Boulbaba Ben Amor, Mohamed Daoudi, Driss Aboutajdine
2012 2012 5th IAPR International Conference on Biometrics (ICB)  
The 3D face recognition literature has many papers that represent facial shapes as collections of curves of different kinds (level-curves, iso-level curves, radial curves, profiles, geodesic polarization  ...  In contrast with the holistic approaches, the approaches that match faces based on whole surfaces, the curve-based parametrization allows local analysis of facial shapes.  ...  Acknowledgements This research is supported in part by the ANR under the projects ANR FAR 3D ANR-07-SESU-004 and 3D Face Analyzer ANR 2010 INTB 0301 02.  ... 
doi:10.1109/icb.2012.6199768 dblp:conf/icb/BallihiSADA12 fatcat:ws3twon6sbcajga6p6jazh2kja

Video parsing based on head tracking and face recognition

Pengxu Li, Haizhou Ai, Yuan Li, Chang Huang
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
quality are selected and normalized according to face alignment results, and finally different segments are associated by face recognition.  ...  The system is based on face vision techniques including face detection and tracking, face alignment and recognition.  ...  It integrates the state-of-the-art head tracking, face alignment and face recognition algorithms.  ... 
doi:10.1145/1282280.1282288 dblp:conf/civr/LiALH07 fatcat:i36tzoradzd4rc2m7ulf46rab4

Boosting 3-D-Geometric Features for Efficient Face Recognition and Gender Classification

Lahoucine Ballihi, Boulbaba Ben Amor, Mohamed Daoudi, Anuj Srivastava, Driss Aboutajdine
2012 IEEE Transactions on Information Forensics and Security  
geometrical facial features that contribute most in 3D face recognition and gender classification.  ...  algorithm for face recognition and gender selection.  ...  ACKNOWLEDGMENT This research has been supported partialy by the ANR under the projects ANR FAR 3D ANR-07-SESU-004 and the 3D Face Analyzer ANR 2010 INTB 0301 02.  ... 
doi:10.1109/tifs.2012.2209876 fatcat:y3v5xk7vj5fg7glxs2joo2nb7q

Learning to Fuse 3D+2D Based Face Recognition at Both Feature and Decision Levels [chapter]

Stan Z. Li, ChunShui Zhao, Meng Ao, Zhen Lei
2005 Lecture Notes in Computer Science  
2D intensity images and 3D shape models are both useful for face recognition, but in different ways.  ...  In this paper, we propose a systematic framework for fusing 2D and 3D face recognition at both feature and decision levels, by exploring synergies of the two modalities at these levels.  ...  Boosted 3D and 2D Face Recognition An AdaBoost classifier is trained for 3D faces and another trained for 2D faces recognition, separately.  ... 
doi:10.1007/11564386_5 fatcat:wfpklacpxfhk5i56b6jfmlbzgq

Boosting 3D LBP-Based Face Recognition by Fusing Shape and Texture Descriptors on the Mesh

Naoufel Werghi, Claudio Tortorici, Stefano Berretti, Alberto Del Bimbo
2016 IEEE Transactions on Information Forensics and Security  
In this paper, we present a novel approach for fusing shape and texture local binary patterns (LBPs) on a mesh for 3D face recognition.  ...  Index Terms-Mesh-LBP, feature and score fusion, 3D face recognition.  ...  ACKNOWLEDGMENT Preliminary ideas and experiments of the face mesh-LBP based face recognition approach appeared in [49] .  ... 
doi:10.1109/tifs.2016.2515505 fatcat:dc4cgo5jbve73ftm4crtgotxb4

Boosting 3D LBP-based face recognition by fusing shape and texture descriptors on the mesh

Claudio Tortorici, Naoufel Werghi, Stefano Berretti
2015 2015 IEEE International Conference on Image Processing (ICIP)  
In this paper, we present a novel approach for fusing shape and texture local binary patterns (LBPs) on a mesh for 3D face recognition.  ...  Index Terms-Mesh-LBP, feature and score fusion, 3D face recognition.  ...  ACKNOWLEDGMENT Preliminary ideas and experiments of the face mesh-LBP based face recognition approach appeared in [49] .  ... 
doi:10.1109/icip.2015.7351287 dblp:conf/icip/TortoriciWB15 fatcat:b5clena5xbcz7hl4pdjbrk2xnq

Multi-feature fusion in advanced robotics applications

Zahid Riaz, Christoph Mayer, Michael Beetz, Bernd Radig, M. Saquib Sarfraz
2009 Proceedings of the 6th International Conference on Frontiers of Information Technology - FIT '09  
We study two different models with our proposed approach towards multifeature extraction. These features are efficiently used for human face information extraction for different applications.  ...  The approach follows in fitting a model to face image using robust objective function and extracting textural and temporal features for three major applications naming 1) face recognition, 2) facial expressions  ...  We start with the model fitting and extract the shape parameters by optimizing local objective function [9] .  ... 
doi:10.1145/1838002.1838039 dblp:conf/fit/RiazMBRS09 fatcat:b75vreufpzf2hgpnb2syii2yx4

Geometric based 3D facial gender classification

Lahoucine Ballihi, Boulbaba Ben Amor, Mohamed Daoudi, Anuj Srivastava, Driss Aboutajdine
2012 2012 5th International Symposium on Communications, Control and Signal Processing  
We expect that the shape of certain curves are similar within Male/Female classes and different when moving from one class to another.  ...  While most of previous work in the literature focuses on either 2D facial images, here, we study the use of 3D facial shape for automatic gender classification.  ...  BOOSTING FOR GENDER CLASSIFICATION Radial and iso-level curves capture locally the shape of different facial regions.  ... 
doi:10.1109/isccsp.2012.6217828 dblp:conf/isccsp/BallihiADSA12 fatcat:5jcd2aqr7nf43mew4h2gicglae

Boosting local descriptors for matching composite and digital face images

Paritosh Mittal, Aishwarya Jain, Richa Singh, Mayank Vatsa
2013 2013 IEEE International Conference on Image Processing  
This research designs a patch based face recognition algorithm that generates patches around fiducial features and extracts local information from these patches using Daisy descriptor.  ...  Sketch recognition is one of the most challenging applications of face recognition.  ...  However, different law enforcement applications have led to other challenging applications of face recognition such as matching digital face images with surveillance camera images, scanned images, and  ... 
doi:10.1109/icip.2013.6738576 dblp:conf/icip/MittalJSV13 fatcat:cfj6prxhkzhnfb4leu7n2iffea

Boosting Radial Strings for 3D Face Recognition with Expressions and Occlusions

Xun Yu, Yongsheng Gao, Jun Zhou
2016 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)  
Moreover, the most discriminative and stable radial strings are selected optimally by the well-known AdaBoost algorithm to achieve a composite classifier for 3D face recognition under facial expression  ...  In this paper, we present a new radial string representation and matching approach for 3D face recognition under expression variations and partial occlusions.  ...  [10] explored an efficient 3D face recognition that encoded a face scan by a set of local-feature descriptors called KMTS, then a TPWCRC framework was proposed to address the problem of 3D partial face  ... 
doi:10.1109/dicta.2016.7797014 dblp:conf/dicta/YuGZ16 fatcat:wwhupqgrp5cpfmkb4k3qt2rdiu

Learning Effective Intrinsic Features to Boost 3D-Based Face Recognition [chapter]

Chenghua Xu, Tieniu Tan, Stan Li, Yunhong Wang, Cheng Zhong
2006 Lecture Notes in Computer Science  
In this paper, we propose a novel approach to 3D-based face recognition. First, a novel representation, called intrinsic features, is presented to encode local 3D shapes.  ...  3D image data provide several advantages than 2D data for face recognition and overcome many problems with 2D intensity images based methods.  ...  This work is supported by research funds from the Natural Science  ... 
doi:10.1007/11744047_32 fatcat:36w5syvop5arbplbw67mpgp24e

Automatic fetal face detection by locating fetal facial features from 3D ultrasound images for navigating fetoscopic tracheal occlusion surgeries

Rong Xu, Jun Ohya, Bo Zhang, Masakatsu G. Fujie, Yoshinobu Sato
2013 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)  
In experiments, all key feature points are detected for each case, and thus a detection success rate of 100% is achieved by using 72 3D US images from a test database of 6 fetal faces in the frontal view  ...  Each feature is gradually identified from the candidates by a boosting traversal scheme based on the spatial relations between each feature.  ...  The different local surface shapes in a 3D facial mesh can be determined by the signs of the mean and Gaussian curvatures as shown in Table I .  ... 
doi:10.1109/fg.2013.6553722 dblp:conf/fgr/XuOZFS13 fatcat:eipbpnsffzh3vaskd3437dnsfm

Effective face frontalization in unconstrained images

Tal Hassner, Shai Harel, Eran Paz, Roee Enbar
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Recent reports have suggested that this process may substantially boost the performance of face recognition systems.  ...  Previous frontalization methods did this by attempting to approximate 3D facial shapes for each query image.  ...  Acknowledgments This research is based upon work supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA 2014  ... 
doi:10.1109/cvpr.2015.7299058 dblp:conf/cvpr/HassnerHPE15 fatcat:mfbgejqnzfbcbodllnmwrywebi
« Previous Showing results 1 — 15 out of 13,358 results