Filters








984 Hits in 6.2 sec

Robust Depth-Based Person Re-Identification

Ancong Wu, Wei-Shi Zheng, Jian-Huang Lai
2017 IEEE Transactions on Image Processing  
The effectiveness of our models was validated on publicly available depth pedestrian datasets as compared to related methods for person re-identification.  ...  Person re-identification (re-id) aims to match people across non-overlapping camera views. So far the RGB-based appearance is widely used in most existing works.  ...  in person re-identification.  ... 
doi:10.1109/tip.2017.2675201 pmid:28252397 fatcat:po4vvke3lncbvl6c5i6swu6rsi

Virtual face image generation for illumination and pose insensitive face recognition

Wen Gao, Shiguang Shan, Xiujuan Chai, Xiaowei Fu
2003 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)  
Based on this strategy, this paper presents some attempts by presenting a ratio-image based face relighting method and a face re-rotating approached based on linear shape prediction and image warp.  ...  However, enough samples are not always available for many practical applications.  ...  However, notice that all faces have similar 2D and 3D shapes, so we can try to first warp all faces to the same shape and then compute the ratio-image for relighting the standard face images.  ... 
doi:10.1109/icme.2003.1221270 dblp:conf/icmcs/GaoSCF03 fatcat:zpa643v2pfg67f3bfxqqeplp4i

Depth-based person re-identification

Ancong Wu, Wei-Shi Zheng, Jian-Huang Lai
2015 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)  
Person re-identification aims to match people across non-overlapping camera views.  ...  It is also insensitive to slight shape change and invariant to color change and background. We combine our descriptor with skeleton-based feature to get a complete representation of human body.  ...  Since both ED and PCM are rotation invariant, Eigen-depth feature is more tolerant to body shape change than PCM and more suitable for person re-identification.  ... 
doi:10.1109/acpr.2015.7486459 dblp:conf/acpr/WuZL15 fatcat:rxwtvpsg3revfpum5naijstq7y

A survey of approaches and trends in person re-identification

Apurva Bedagkar-Gala, Shishir K. Shah
2014 Image and Vision Computing  
In this paper, we explore the problem of person re-identification and discuss the current solutions.  ...  Given an image/video of a person taken from one camera, re-identification is the process of identifying the person from images/videos taken from a different camera.  ...  The distance model for matching exists in the covariance feature space. 4.3.2.1. Attribute based person re-identification.  ... 
doi:10.1016/j.imavis.2014.02.001 fatcat:3w7ju7pzl5gkbgl5djsbakrr7i

Mapping Appearance Descriptors on 3D Body Models for People Re-identification

Davide Baltieri, Roberto Vezzani, Rita Cucchiara
2014 International Journal of Computer Vision  
In this paper, we propose a complete re-identification framework which exploits non-articulated 3D body models to spatially map appearance descriptors (color and gradient histograms) into the vertices  ...  People Re-identification aims at associating multiple instances of a person's appearance acquired from different points of view, different cameras, or after a spatial or a limited temporal gap to the same  ...  The key points of this work are: 1. the definition of a non-articulated 3D body model for people re-identification; 2. the selection of color and texture descriptors to generate a model-based person signature  ... 
doi:10.1007/s11263-014-0747-z fatcat:bob3st5tjzcsfc6m3zvj4a7jci

Representation, Analysis, and Recognition of 3D Humans

Stefano Berretti, Mohamed Daoudi, Pavan Turaga, Anup Basu
2018 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
These deep features can be learned from point sets (and surfaces), landmarks and volumes.  ...  At large, the contra-position is between hand-crafted and learned features: these can capture the spatial information only or also account for the temporal dimension.  ...  Gait and Re-Identification. Person (re-)identification through gait analysis, as an interesting and non-intrusive biometric means, has been extensively studied in recent years.  ... 
doi:10.1145/3182179 fatcat:ds55t4md2na2tibtyg4llerf3q

Expressive facial style transfer for personalized memes mimic

Yanlong Tang, Xiaoguang Han, Yue Li, Liqian Ma, Ruofeng Tong
2019 The Visual Computer  
To conduct distortion-free transferring of exaggerated geometry, we propose a novel accurate feature curve-based face reconstruction algorithm for 3D-aware image warping.  ...  Furthermore, we propose an identity preserving blending model, based on a deep neural network, to enhance facial expressive textural details.  ...  Acknowledgements We thank the anonymous reviewers for the insightful and constructive comments, Matt Boyd-Surka for proofreading this manuscript, Jinghui Zhou, Keli Cheng and Xiaodong Gu for valuable discussions  ... 
doi:10.1007/s00371-019-01695-6 fatcat:pzg65wnzszhgdkvwe24j643pdq

Histogram of the node strength and histogram of the edge weight: two new features for RGB-D person re-identification

Zeynab Imani, Hadi Soltanizadeh
2018 Science China Information Sciences  
In this paper, novel features are proposed for RGB-D person re-identification.  ...  This paper presents a novel method for short-term person re-identification.  ...  features for RGB-D person re-identification.  ... 
doi:10.1007/s11432-016-9086-8 fatcat:du7spxtetrgqrhhlvhg2hxsoza

Template based Mole Detection for Face Recognition

Ramesha K, K B Raja, Venugopal K R, L M Patnaik
2010 Journal of clean energy technologies  
Face recognition is used for personal identification.  ...  The Template based Mole Detection for Face Recognition (TBMDFR) algorithm is proposed to verify authentication of a person by detection and validation of prominent moles present in the skin region of a  ...  Table 1 gives the algorithm of TBMDFR to detect and validate the mole present on face for personal identification. V.  ... 
doi:10.7763/ijcte.2010.v2.243 fatcat:ufjugr7iqvbl3bnkpp3rh2mzky

On soft biometrics

Mark S. Nixon, Paulo L. Correia, Kamal Nasrollahi, Thomas B. Moeslund, Abdenour Hadid, Massimo Tistarelli
2015 Pattern Recognition Letters  
The approaches lead to a new type of recognition, and one similar to Bertillonage which is one of the earliest approaches to human identification.  ...  Acknowledgments This work has been partially supported by the European Commission COST Action IC1106 "Integrating Biometrics and Forensics for the Digital Age"  ...  One such example is the usage of 3D ear shape, as ear contains little texture and the most descriptive attribute for gender recognition is its shape [Lei 2013 ].  ... 
doi:10.1016/j.patrec.2015.08.006 fatcat:h7jykhmqpvff5irda4xgrtpv4m

Orientation Driven Bag of Appearances for Person Re-identification [article]

Liqian Ma, Hong Liu, Liang Hu, Can Wang, Qianru Sun
2016 arXiv   pre-print
. body-structure based feature representation (BSFR) which introduces body structure pyramid for codebook learning and feature pooling in the vertical direction of human body.  ...  Person re-identification (re-id) consists of associating individual across camera network, which is valuable for intelligent video surveillance and has drawn wide attention.  ...  In this paper, we present a novel body-structure based feature representation (BSFR) approach for person re-identification.  ... 
arXiv:1605.02464v1 fatcat:l5hmyxy4svavfa5caatxzeyrqi

How Much Information Kinect Facial Depth Data Can Reveal About Identity, Gender and Ethnicity? [chapter]

Elhocine Boutellaa, Messaoud Bengherabi, Samy Ait-Aoudia, Abdenour Hadid
2015 Lecture Notes in Computer Science  
Four local feature extraction methods are investigated for both face texture and shape description.  ...  The low-cost depth sensors such as Microsoft Kinect introduced in late 2010 allow extracting directly 3D information, together with RGB color images.  ...  Authors are thankful for DGRSDT and MESRS for their support.  ... 
doi:10.1007/978-3-319-16181-5_55 fatcat:7tedvf43t5hg3irxz5es5afmcy

3D Assisted Face Recognition: Dealing With Expression Variations

Nesli Erdogmus, Jean-Luc Dugelay
2014 IEEE Transactions on Information Forensics and Security  
For this purpose, an animatable 3D model is generated for each user based on 17 automatically located landmark points.  ...  One of the most critical sources of variation in face recognition is facial expressions, especially in the frequent case where only a single sample per person is available for enrollment.  ...  After the hole and noise free face model (texture and shape) is obtained, 17 feature points are automatically detected using either shape, texture or both, according to the regional properties of the face  ... 
doi:10.1109/tifs.2014.2309851 fatcat:gymlitg6mreppgxd2l42qs4tse

INTELLIGENT CCTV FOR MASS TRANSPORT SECURITY: CHALLENGES AND OPPORTUNITIES FOR VIDEO AND FACE PROCESSING [chapter]

Conrad Sanderson, Abbas Bigdeli, Ting Shan, Shaokang Chen, Erik Berglund, Brian C. Lovell
2009 Series in Machine Perception and Artificial Intelligence  
The histogrambased bag-of-features technique is capable of achieving an average recognition accuracy of 89% for pose angles of around 25 degrees.  ...  However due to the amount of cameras installed, many sites have abandoned expensive human monitoring and only record video for forensic purposes.  ...  which represents the change between shape and texture.  ... 
doi:10.1142/9789812834461_0030 dblp:series/smpai/SandersonBSCBL09 fatcat:gpa62z5ryzbnbhnthpcmiakhra

Intelligent CCTV for Mass Transport Security: Challenges and Opportunities for Video and Face Processing

Conrad Sanderson, Abbas Bigdeli, Ting Shan, Shaokang Chen, Erik Berglund, Brian C. Lovell
2007 ELCVIA Electronic Letters on Computer Vision and Image Analysis  
The histogrambased bag-of-features technique is capable of achieving an average recognition accuracy of 89% for pose angles of around 25 degrees.  ...  However due to the amount of cameras installed, many sites have abandoned expensive human monitoring and only record video for forensic purposes.  ...  which represents the change between shape and texture.  ... 
doi:10.5565/rev/elcvia.140 fatcat:g6yitxaigzfdhccshsc7l4av3e
« Previous Showing results 1 — 15 out of 984 results